Optical flow evaluation results Statistics:     Average   SD   R2.5   R5.0   R10.0   A50   A75   A95  
Error type:   endpoint   angle   interpolation   normalized interpolation  
Show images: below table   above table        
R2.5
angle
error
avg. Army
(Hidden texture)
GT   im0   im1
Mequon
(Hidden texture)
GT   im0   im1
Schefflera
(Hidden texture)
GT   im0   im1
Wooden
(Hidden texture)
GT   im0   im1
Grove
(Synthetic)
GT   im0   im1
Urban
(Synthetic)
GT   im0   im1
Yosemite
(Synthetic)
GT   im0   im1
Teddy
(Stereo)
GT   im0   im1
rank all disc untext all disc untext all disc untext all disc untext all disc untext all disc untext all disc untext all disc untext
RAFT-it+_RVC [198]3.0 22.6 9 45.3 8 9.61 1 12.3 3 34.7 1 12.7 4 9.31 2 25.5 2 9.19 4 1.86 1 13.1 1 0.86 1 21.9 3 28.9 4 12.9 2 9.02 1 23.8 1 8.47 1 9.00 2 34.2 2 3.03 4 3.35 4 10.4 8 0.43 2
RAFT-it [194]5.9 25.3 14 49.8 22 15.4 9 13.6 5 37.1 4 13.6 5 9.70 3 27.5 4 8.99 3 2.35 2 15.3 2 1.46 3 25.0 9 33.2 15 13.6 3 12.0 4 27.3 3 11.5 2 11.5 4 43.8 8 3.87 7 2.67 3 8.82 3 0.90 5
MS_RAFT+_RVC [195]11.5 26.6 19 44.3 6 11.4 3 24.5 77 39.1 7 28.5 97 11.6 4 27.6 5 15.5 25 2.64 3 18.5 3 1.20 2 21.7 2 27.7 1 12.2 1 11.8 3 25.6 2 12.0 4 7.63 1 32.0 1 1.03 1 2.16 1 6.82 1 0.94 6
NNF-Local [75]19.0 20.0 3 43.3 3 13.0 5 15.9 16 45.3 31 16.1 19 12.5 7 34.1 13 12.8 14 9.68 24 32.0 15 7.01 29 23.3 6 30.0 6 16.2 7 22.0 42 45.4 14 23.8 72 25.8 34 44.8 11 17.6 32 4.37 15 14.4 35 0.48 3
NN-field [71]20.3 22.1 7 44.0 5 14.6 7 18.4 29 47.3 46 19.2 35 12.5 7 32.9 9 14.0 21 6.57 5 28.2 8 3.57 5 23.4 7 30.1 7 15.9 6 17.9 21 36.8 4 15.8 7 35.9 74 51.5 42 27.4 74 4.58 18 15.3 39 0.55 4
RAFT-TF_RVC [179]23.6 32.9 42 58.3 50 13.9 6 20.0 37 45.7 35 20.0 38 16.9 43 40.4 44 18.0 38 5.16 4 21.6 4 2.93 4 29.0 38 37.8 43 18.4 10 17.3 12 39.8 7 17.8 13 11.8 5 42.8 7 3.13 5 5.30 29 16.4 44 3.35 9
TC/T-Flow [77]25.9 19.9 2 46.9 13 10.2 2 16.0 17 47.8 48 13.9 8 13.0 11 36.6 27 11.1 7 8.90 17 35.0 43 6.10 17 27.2 21 35.7 27 21.0 19 15.7 7 47.2 23 15.8 7 21.0 17 39.2 4 42.1 105 7.86 53 19.5 56 10.9 70
ComponentFusion [94]26.5 20.0 3 46.3 10 14.8 8 16.6 20 40.3 10 18.5 31 11.7 6 33.6 11 10.9 6 7.09 9 35.2 45 4.45 9 27.6 24 36.0 30 21.4 22 21.5 36 54.1 62 20.2 36 31.8 63 56.8 74 16.2 24 5.46 30 12.8 27 7.47 39
ALD-Flow [66]26.8 21.6 6 46.0 9 15.9 11 15.5 12 41.3 14 15.6 15 13.1 13 35.2 18 12.2 9 8.17 14 33.4 27 5.35 13 28.1 28 37.3 41 20.3 15 16.4 10 47.4 25 16.0 9 26.5 37 45.4 13 41.8 103 8.39 58 22.3 68 11.3 74
ProFlow_ROB [142]27.0 24.2 12 53.3 38 15.8 10 15.6 13 44.5 26 14.8 11 15.5 25 43.0 51 11.8 8 6.94 7 33.1 24 3.97 7 30.0 45 39.9 54 19.6 12 16.2 9 49.1 34 16.1 10 14.9 8 54.0 59 13.9 22 7.47 48 21.2 63 8.63 52
nLayers [57]27.8 22.7 10 40.3 2 18.4 14 27.2 102 45.9 36 30.4 104 15.7 31 35.4 21 21.4 70 8.12 13 26.6 6 6.21 18 22.5 4 29.0 5 15.5 5 19.9 27 40.8 8 17.8 13 31.3 58 52.6 53 16.9 29 4.26 12 11.2 13 5.84 13
OFLAF [78]28.5 29.6 38 47.4 15 24.8 25 17.8 25 40.9 12 18.3 29 11.6 4 26.9 3 13.2 16 11.5 45 29.3 12 8.97 71 23.7 8 30.9 8 16.5 8 22.2 46 41.5 9 19.3 26 30.2 53 50.6 37 32.9 82 5.94 35 13.8 29 8.44 49
HAST [107]28.8 19.5 1 40.1 1 11.6 4 16.1 18 39.7 8 14.8 11 8.49 1 21.2 1 7.09 1 6.79 6 29.0 11 3.66 6 21.6 1 28.3 3 13.8 4 24.3 68 48.5 31 24.3 75 41.7 96 59.8 86 63.0 148 6.05 37 11.5 19 8.72 53
RNLOD-Flow [119]28.9 20.7 5 43.8 4 19.4 15 18.1 26 45.9 36 17.0 25 12.7 9 34.1 13 12.3 10 7.38 10 28.7 10 4.87 10 26.5 17 34.9 22 20.9 17 20.3 28 46.2 17 20.2 36 43.1 100 60.3 88 47.5 122 4.98 26 12.7 26 6.55 22
WLIF-Flow [91]29.5 27.0 24 47.0 14 23.1 22 21.7 51 46.6 43 23.3 51 14.8 19 36.2 23 16.3 32 9.33 21 32.2 19 6.64 23 27.7 25 35.1 24 23.4 41 21.6 37 47.7 27 19.2 23 28.7 47 45.3 12 32.0 81 4.50 17 11.2 13 6.43 18
MDP-Flow2 [68]30.9 35.3 56 55.4 45 30.2 56 14.2 6 39.7 8 14.2 10 13.6 14 31.4 6 12.9 15 12.2 50 34.1 35 8.19 54 27.7 25 35.0 23 22.1 25 22.4 50 45.4 14 21.5 52 27.1 38 54.1 60 16.5 25 5.87 34 14.0 31 4.25 10
OAR-Flow [123]32.2 25.6 16 54.9 42 22.4 19 18.7 30 44.8 28 19.1 32 17.2 45 43.7 54 18.0 38 8.53 16 31.6 14 5.65 14 29.7 43 39.3 48 20.9 17 14.5 5 47.3 24 13.4 5 14.1 7 38.0 3 20.7 46 9.84 74 21.1 62 16.1 91
Layers++ [37]32.8 28.0 36 48.8 18 30.9 59 23.3 67 45.6 34 25.5 75 13.7 15 31.4 6 18.1 40 8.08 12 24.9 5 5.87 15 22.9 5 28.1 2 19.6 12 22.2 46 46.3 19 20.7 40 39.6 90 55.9 69 35.0 84 4.16 8 9.78 5 6.81 24
TC-Flow [46]33.0 24.4 13 52.2 34 22.6 20 11.8 2 38.8 6 11.2 1 12.7 9 35.7 22 9.84 5 9.88 26 34.9 41 7.49 38 28.9 36 38.6 47 21.2 21 20.6 30 52.1 45 21.6 54 22.6 29 47.1 17 36.3 87 9.05 65 21.5 65 12.4 79
LME [70]35.1 31.5 40 51.4 29 21.0 18 14.7 8 36.9 3 15.7 16 16.0 36 35.2 18 19.8 60 11.8 47 36.6 49 8.08 48 28.6 33 36.0 30 25.5 55 21.1 34 49.0 33 19.8 33 29.8 50 50.0 32 21.5 50 6.61 40 15.1 36 7.95 45
AGIF+OF [84]35.5 26.3 17 48.8 18 24.1 23 24.9 79 52.0 78 26.2 77 16.0 36 39.4 38 19.7 57 8.96 18 32.0 15 6.64 23 26.7 19 33.7 16 21.5 24 21.4 35 49.4 35 18.5 18 28.2 44 49.6 29 30.5 79 4.63 21 11.3 18 7.30 35
CoT-AMFlow [174]35.8 34.5 49 56.8 47 30.1 54 15.6 13 40.5 11 16.6 23 13.9 16 33.0 10 13.9 19 12.5 61 34.7 40 8.83 68 28.1 28 35.2 26 25.1 52 21.9 41 47.1 22 21.1 45 29.8 50 50.0 32 21.5 50 6.22 38 14.1 32 7.10 32
PH-Flow [99]36.9 26.7 20 51.6 30 25.6 33 21.7 51 49.4 59 23.8 56 15.5 25 37.6 31 19.5 53 10.2 32 33.8 31 7.44 37 26.4 15 33.7 16 21.0 19 22.0 42 50.3 38 20.4 38 38.8 84 48.4 22 45.4 112 4.26 12 11.2 13 6.38 17
FC-2Layers-FF [74]37.1 26.9 23 48.6 17 28.3 47 22.1 55 48.8 54 23.8 56 14.1 17 32.4 8 19.6 55 9.10 19 28.3 9 6.47 21 25.5 10 31.7 9 23.0 35 23.3 58 47.7 27 21.8 55 44.1 104 56.3 73 46.0 117 3.54 5 9.08 4 5.44 12
NNF-EAC [101]38.2 34.9 50 54.8 40 29.9 53 15.6 13 41.7 16 15.9 17 15.1 23 34.8 16 15.7 26 12.4 55 35.1 44 8.33 58 28.1 28 35.7 27 22.9 32 24.5 71 46.2 17 22.7 65 31.6 61 49.1 25 20.1 44 7.54 50 17.1 48 7.44 38
Classic+CPF [82]38.2 27.1 28 51.2 28 25.5 32 23.9 71 51.4 74 25.1 71 15.9 33 39.3 37 19.4 51 9.17 20 32.8 22 6.69 25 27.3 22 34.5 20 23.9 42 21.0 33 48.7 32 18.0 16 35.6 73 49.9 31 45.7 114 4.25 11 10.7 9 6.61 23
IROF++ [58]38.5 27.4 30 50.7 25 26.7 40 22.1 55 50.1 69 24.1 61 16.3 39 40.0 42 19.6 55 10.6 39 34.3 36 7.72 43 27.9 27 35.7 27 22.5 27 22.3 48 54.1 62 19.9 34 25.5 33 49.6 29 11.5 18 5.49 31 14.1 32 6.54 21
Sparse-NonSparse [56]39.3 26.8 22 51.9 33 26.8 41 22.2 60 49.0 57 24.6 67 15.6 28 39.4 38 19.0 46 9.46 23 33.6 29 7.07 31 29.0 38 37.2 40 24.3 47 21.7 39 50.4 39 19.5 31 34.0 65 45.8 14 41.6 101 4.44 16 10.9 10 6.96 29
COFM [59]39.5 22.1 7 49.1 20 16.6 12 18.2 27 43.5 21 19.2 35 15.9 33 38.3 34 21.5 71 7.02 8 32.6 20 4.40 8 31.4 55 37.9 44 35.0 99 22.1 44 46.4 20 18.3 17 28.7 47 45.9 15 45.5 113 9.25 67 15.5 41 15.7 90
FESL [72]40.5 27.0 24 46.3 10 31.2 61 26.0 93 51.8 77 26.9 83 15.8 32 37.0 28 19.5 53 7.89 11 30.7 13 5.17 12 26.6 18 33.8 18 22.6 28 20.3 28 45.8 16 19.3 26 39.9 91 61.2 93 35.6 85 5.04 27 12.5 24 6.48 20
Efficient-NL [60]41.0 23.3 11 44.7 7 17.6 13 24.6 78 51.6 76 25.4 74 15.0 22 36.2 23 17.5 36 9.92 27 33.1 24 6.94 27 26.4 15 34.0 19 20.3 15 27.2 84 49.4 35 22.6 61 37.6 79 50.5 35 37.1 88 6.98 45 16.2 43 8.16 46
JOF [136]41.0 25.3 14 46.6 12 23.0 21 24.1 73 49.9 67 26.7 80 14.8 19 34.3 15 21.0 69 8.34 15 32.1 18 5.95 16 26.1 14 32.9 14 22.8 31 22.8 52 49.4 35 22.2 57 41.8 97 60.0 87 56.2 139 4.17 9 10.9 10 6.44 19
LSM [39]42.5 26.5 18 50.8 26 27.0 43 22.1 55 49.4 59 24.4 65 15.6 28 38.2 33 19.4 51 10.1 28 33.0 23 7.43 36 28.6 33 36.3 32 24.7 48 22.8 52 50.5 41 20.9 44 40.3 93 49.3 26 45.8 116 4.76 23 12.0 21 6.93 27
UnDAF [187]42.6 35.1 51 57.4 48 30.1 54 15.2 10 43.0 19 15.3 14 14.6 18 35.1 17 13.3 17 12.6 63 37.7 51 8.47 63 28.9 36 36.9 38 23.3 37 23.2 55 53.6 61 21.3 49 30.1 52 49.4 28 21.2 48 9.95 76 27.3 91 6.93 27
PMMST [112]43.0 42.4 83 58.9 53 40.2 81 22.1 55 45.3 31 24.7 70 17.9 50 38.4 35 18.8 43 12.2 50 28.1 7 8.26 56 25.7 11 32.7 12 18.5 11 22.3 48 45.3 13 20.8 42 28.5 46 50.7 38 18.3 35 8.51 62 16.8 45 8.73 54
Ramp [62]44.3 27.0 24 52.3 35 26.1 37 22.3 62 49.1 58 24.6 67 15.6 28 37.8 32 19.8 60 10.5 38 33.6 29 7.61 40 28.6 33 36.6 34 24.0 43 23.6 61 51.2 42 21.8 55 38.2 80 44.5 9 46.1 118 4.86 24 12.1 22 7.13 33
Classic+NL [31]44.6 27.2 29 47.8 16 28.4 49 22.0 54 49.4 59 24.1 61 15.5 25 37.4 30 19.8 60 10.4 36 33.8 31 7.40 35 28.5 31 36.4 33 24.2 46 23.3 58 52.2 47 21.1 45 43.9 102 52.5 50 44.6 109 4.60 20 11.2 13 7.04 31
2DHMM-SAS [90]47.1 26.7 20 51.8 32 25.6 33 22.2 60 51.3 72 23.8 56 17.8 48 42.3 48 20.0 65 10.4 36 34.6 38 7.52 39 28.5 31 36.6 34 24.0 43 22.7 51 54.5 65 20.6 39 39.0 86 47.8 20 45.1 110 5.51 32 13.9 30 7.73 43
FMOF [92]47.8 27.8 35 50.4 24 27.1 45 26.2 95 52.5 83 27.4 86 15.9 33 36.4 26 21.7 72 9.71 25 32.7 21 6.98 28 27.3 22 34.6 21 24.1 45 23.7 62 47.6 26 19.7 32 38.4 81 55.4 66 48.9 125 5.80 33 14.1 32 7.00 30
SVFilterOh [109]49.4 39.6 73 54.6 39 39.8 80 23.8 70 44.7 27 24.0 59 17.3 46 33.8 12 18.8 43 10.2 32 36.4 48 4.93 11 25.9 13 32.1 10 19.6 12 24.7 72 46.7 21 22.9 68 52.0 130 76.3 146 59.2 142 4.23 10 10.9 10 5.01 11
PRAFlow_RVC [177]49.8 47.3 99 65.0 65 33.2 69 30.3 108 52.1 80 31.6 106 24.2 81 50.0 70 26.7 90 10.1 28 32.0 15 6.60 22 31.3 54 39.8 52 22.9 32 21.7 39 43.1 11 22.3 59 15.9 9 51.9 46 1.85 3 4.96 25 12.5 24 3.07 8
S2D-Matching [83]50.5 27.7 32 50.2 23 28.4 49 22.1 55 48.8 54 24.3 63 16.5 41 40.0 42 19.3 49 10.6 39 33.8 31 7.78 44 29.1 41 36.7 37 25.0 50 24.4 70 53.0 58 22.6 61 47.0 116 53.6 56 50.8 130 4.58 18 11.2 13 7.54 40
SimpleFlow [49]51.2 28.6 37 51.6 30 29.5 52 25.0 80 51.3 72 28.2 92 18.6 55 43.0 51 23.3 78 10.1 28 33.5 28 7.04 30 29.9 44 37.9 44 26.2 58 27.8 89 52.2 47 24.0 73 35.1 71 47.9 21 29.7 78 4.66 22 12.4 23 6.92 26
ProbFlowFields [126]51.5 33.9 45 68.5 82 30.9 59 20.3 42 45.3 31 22.1 46 19.2 59 44.8 57 22.9 77 11.7 46 39.3 60 8.91 70 31.0 52 40.1 55 23.3 37 16.8 11 47.8 29 19.2 23 23.7 32 55.9 69 23.9 62 8.39 58 22.4 69 9.82 65
PMF [73]53.2 37.7 66 58.3 50 27.3 46 19.4 33 45.0 30 18.3 29 16.2 38 39.9 41 14.0 21 13.6 74 35.7 46 8.03 47 25.8 12 32.5 11 17.1 9 30.2 97 57.0 79 31.6 100 58.9 141 74.7 139 55.9 138 3.95 7 10.3 6 6.15 16
Adaptive [20]54.0 27.0 24 52.6 36 19.8 16 21.9 53 47.8 48 22.6 48 20.5 64 47.8 66 19.7 57 10.3 34 39.9 64 6.31 20 45.6 138 52.6 135 51.3 144 17.4 13 48.2 30 13.9 6 34.8 70 56.9 76 19.8 42 6.04 36 15.2 37 7.54 40
TV-L1-MCT [64]54.1 27.5 31 49.4 21 27.0 43 26.5 96 52.8 88 27.8 91 16.8 42 39.1 36 21.8 74 10.6 39 33.8 31 7.82 46 30.3 47 38.1 46 28.7 76 24.7 72 53.4 60 23.4 70 27.4 39 52.5 50 19.4 39 7.28 47 15.3 39 11.4 76
Correlation Flow [76]54.8 36.6 63 55.3 44 34.4 70 16.6 20 44.4 25 14.8 11 18.3 54 42.9 50 12.7 13 12.4 55 39.7 62 8.46 62 32.2 59 40.6 59 25.2 53 29.0 92 54.2 64 29.7 96 39.1 87 52.1 48 47.4 121 6.53 39 16.1 42 6.88 25
IROF-TV [53]54.9 30.9 39 54.8 40 31.6 63 22.8 66 50.5 70 25.1 71 16.9 43 40.8 45 20.8 67 14.0 77 43.7 81 10.1 79 31.2 53 39.5 49 28.6 74 26.8 83 58.7 89 25.6 79 18.8 12 48.4 22 8.08 16 5.28 28 13.6 28 7.77 44
AggregFlow [95]55.0 36.3 62 52.7 37 35.7 71 26.6 97 52.6 86 26.7 80 23.3 77 48.2 68 28.9 100 12.1 48 34.9 41 8.63 65 30.2 46 40.3 58 21.4 22 15.9 8 38.3 5 16.8 11 26.1 36 47.3 18 16.8 27 12.6 93 20.3 58 20.0 107
Occlusion-TV-L1 [63]56.3 34.3 48 58.5 52 25.1 27 20.0 37 46.5 42 20.8 42 22.3 74 49.9 69 20.6 66 12.6 63 41.7 71 8.41 61 35.2 82 44.9 90 32.3 89 17.7 17 52.6 52 21.1 45 28.2 44 52.5 50 13.0 19 9.66 70 23.7 74 10.6 68
PBOFVI [189]57.2 46.5 97 65.0 65 46.2 94 19.9 36 46.6 43 19.1 32 15.4 24 35.3 20 12.4 11 12.7 66 34.6 38 7.16 33 32.1 58 39.8 52 25.7 56 25.6 77 52.9 57 28.5 91 34.2 66 55.9 69 50.9 132 6.75 42 17.7 51 9.48 63
3DFlow [133]58.4 35.7 58 56.6 46 28.3 47 19.1 32 46.2 40 17.4 27 18.8 56 41.7 47 14.5 23 13.9 75 33.3 26 9.85 77 29.0 38 36.6 34 23.0 35 32.9 103 65.1 114 34.7 114 49.9 124 65.5 108 77.7 159 3.87 6 10.3 6 3.02 7
Classic++ [32]60.2 27.7 32 51.0 27 28.7 51 21.5 50 45.9 36 24.3 63 18.1 53 44.3 55 19.9 63 10.3 34 37.7 51 7.14 32 33.4 63 44.1 79 27.9 68 24.0 66 57.9 84 21.4 51 46.3 111 55.6 67 49.7 127 8.45 60 20.7 59 9.69 64
HCFN [157]61.2 31.7 41 61.4 57 26.1 37 12.6 4 37.8 5 12.6 3 13.0 11 37.3 29 8.55 2 12.6 63 38.8 59 9.77 76 29.3 42 37.6 42 23.3 37 26.0 79 59.1 91 26.4 83 60.4 145 73.6 133 63.0 148 12.5 92 26.5 83 19.6 106
IIOF-NLDP [129]61.8 33.3 44 59.3 54 24.9 26 24.4 76 53.8 96 22.9 50 18.8 56 46.2 61 15.0 24 13.5 71 39.7 62 9.86 78 32.3 60 41.2 63 23.3 37 29.9 96 60.2 99 29.6 95 28.1 43 60.8 90 27.0 71 7.51 49 17.2 49 7.29 34
MDP-Flow [26]62.2 35.5 57 65.0 65 32.4 64 20.6 44 43.8 23 24.4 65 18.0 52 43.4 53 19.9 63 14.9 86 41.8 73 11.5 88 30.8 51 39.6 50 25.3 54 23.8 63 57.4 82 22.2 57 31.0 56 59.3 84 16.8 27 10.8 84 26.5 83 10.9 70
DeepFlow2 [106]62.8 39.1 71 66.4 72 44.4 89 20.1 40 47.9 50 20.9 43 23.8 80 52.8 76 26.3 88 12.2 50 43.2 80 7.64 41 31.4 55 41.7 67 22.9 32 18.2 23 52.4 49 17.9 15 29.6 49 44.7 10 39.0 93 16.2 111 31.2 108 22.7 115
OFH [38]63.1 41.9 82 61.6 58 48.5 97 14.7 8 42.7 18 14.1 9 17.4 47 47.6 64 12.6 12 10.6 39 38.5 55 8.39 60 34.8 78 43.7 77 34.5 97 27.2 84 61.9 105 29.5 94 21.3 21 57.6 78 21.4 49 12.2 91 29.8 100 16.2 92
SegFlow [156]64.7 35.2 52 67.0 74 25.4 30 25.7 88 53.3 92 28.2 92 25.4 85 58.1 95 27.5 92 12.5 61 48.9 100 8.15 52 34.1 72 44.4 85 27.8 67 17.6 14 52.1 45 19.0 19 21.1 19 51.8 45 22.5 55 9.21 66 25.0 79 11.1 73
CPM-Flow [114]64.8 35.2 52 67.0 74 25.3 28 25.8 89 53.6 93 28.2 92 25.5 86 58.5 99 27.5 92 12.4 55 48.0 96 8.11 51 33.9 68 44.2 80 27.1 61 17.6 14 51.8 43 19.1 21 21.3 21 51.7 43 22.6 58 9.92 75 27.2 89 11.3 74
S2F-IF [121]65.2 35.7 58 69.0 85 26.6 39 24.1 73 54.0 101 26.0 76 25.6 88 60.9 108 25.9 84 12.4 55 46.6 92 8.38 59 34.3 74 44.2 80 27.7 66 18.0 22 53.2 59 19.2 23 21.2 20 51.7 43 22.9 59 8.97 64 24.9 78 9.11 59
PGM-C [118]65.5 35.2 52 67.1 77 25.4 30 25.8 89 53.6 93 28.2 92 25.8 89 59.3 104 27.5 92 12.4 55 48.1 97 8.16 53 33.9 68 44.3 83 27.1 61 17.7 17 52.8 56 19.1 21 20.8 14 50.3 34 22.4 54 9.82 73 27.2 89 11.5 78
BriefMatch [122]66.2 34.1 47 59.4 55 30.2 56 17.1 22 43.6 22 16.1 19 14.8 19 36.3 25 13.4 18 9.41 22 34.3 36 6.26 19 33.4 63 41.2 63 31.8 88 40.3 138 63.5 108 42.7 141 47.2 117 61.1 91 59.1 141 12.7 95 23.4 71 21.6 113
EpicFlow [100]67.8 35.2 52 67.2 78 25.3 28 25.8 89 53.8 96 28.2 92 26.1 91 60.1 105 27.5 92 12.4 55 48.1 97 8.10 50 34.2 73 44.5 86 28.0 70 17.8 19 52.7 54 19.4 28 21.0 17 52.1 48 22.5 55 10.4 80 27.3 91 12.7 81
CostFilter [40]67.9 43.6 90 65.7 69 40.8 82 20.8 45 45.9 36 21.0 44 18.8 56 44.9 58 18.3 42 17.3 98 39.5 61 13.9 100 26.7 19 32.8 13 22.7 30 30.9 100 60.0 97 31.6 100 59.7 142 81.5 157 59.3 143 4.31 14 11.9 20 5.93 14
FlowFields+ [128]68.3 35.8 61 69.2 87 26.0 36 25.6 86 55.3 110 27.7 89 26.7 92 62.9 113 27.7 97 12.7 66 45.9 90 8.84 69 34.0 71 44.2 80 26.6 59 17.6 14 54.9 69 19.0 19 20.6 13 53.9 58 22.3 53 9.31 69 26.5 83 8.79 56
RFlow [88]69.1 44.4 92 75.2 109 50.5 103 16.5 19 42.1 17 17.2 26 21.4 68 52.2 73 16.0 27 11.3 44 36.2 47 7.25 34 35.2 82 44.3 83 32.3 89 24.3 68 55.6 73 22.6 61 38.6 82 55.3 64 41.6 101 13.4 98 29.9 101 16.9 98
FlowFields [108]70.8 35.7 58 68.7 83 25.8 35 25.6 86 55.1 109 27.7 89 26.8 95 62.8 112 27.6 96 13.0 69 46.8 94 9.13 73 34.6 77 44.9 90 28.1 71 17.8 19 54.9 69 19.4 28 21.3 21 54.8 62 24.2 64 9.25 67 26.4 82 8.47 50
CVENG22+RIC [199]70.8 33.1 43 66.3 71 24.4 24 25.1 81 55.0 108 26.2 77 25.1 84 60.2 106 26.3 88 12.2 50 46.7 93 8.20 55 37.5 100 47.7 109 34.4 96 19.3 25 54.8 67 21.5 52 20.8 14 50.5 35 22.5 55 11.0 85 31.4 111 10.9 70
TV-L1-improved [17]71.5 27.7 32 57.9 49 20.5 17 18.2 27 44.9 29 19.1 32 19.4 60 47.7 65 17.0 35 10.1 28 38.5 55 6.75 26 35.9 90 46.0 98 27.3 63 43.7 145 70.2 137 47.5 146 51.4 127 60.5 89 50.3 129 10.3 79 26.8 88 10.8 69
DMF_ROB [135]71.9 43.0 87 71.7 97 45.5 92 22.4 63 48.3 52 24.0 59 28.0 103 62.4 111 26.9 91 12.8 68 45.8 89 7.80 45 33.9 68 43.1 71 30.0 84 20.9 31 56.4 76 21.2 48 22.3 27 42.0 5 27.0 71 12.7 95 27.6 93 17.1 99
Steered-L1 [116]73.8 38.7 70 67.9 79 43.1 87 11.6 1 34.7 1 12.3 2 16.3 39 41.3 46 13.9 19 12.1 48 38.6 57 8.30 57 34.5 76 43.4 74 32.5 91 29.4 94 61.1 104 25.9 80 60.6 146 67.0 115 70.1 155 15.9 108 30.6 104 24.0 117
Sparse Occlusion [54]74.2 38.6 69 61.8 60 32.5 66 26.0 93 48.8 54 29.5 102 20.0 62 45.2 59 19.2 48 14.3 81 38.4 53 9.67 75 34.4 75 42.6 70 26.7 60 25.4 76 52.4 49 22.4 60 67.3 153 75.9 145 48.3 123 8.07 55 19.9 57 7.36 36
MLDP_OF [87]75.5 48.8 103 77.3 112 52.2 105 20.1 40 49.6 64 19.3 37 23.5 79 54.6 81 18.9 45 12.3 54 38.6 57 7.65 42 33.5 66 40.9 60 29.1 82 28.4 90 55.9 74 31.6 100 49.1 121 62.2 98 60.5 145 7.91 54 16.8 45 8.95 57
PWC-Net_RVC [143]75.8 49.3 105 75.1 108 39.6 79 28.7 104 54.0 101 29.4 101 27.2 96 58.7 100 31.5 105 15.6 89 38.4 53 8.76 67 36.5 95 45.6 97 28.3 72 26.2 81 60.3 100 26.4 83 13.0 6 49.3 26 4.98 10 7.79 51 19.4 55 7.36 36
DeepFlow [85]76.2 47.3 99 71.9 98 64.0 123 21.4 48 48.2 51 22.7 49 27.9 100 58.2 96 31.6 106 15.1 87 42.7 76 10.6 84 31.5 57 42.1 68 22.6 28 19.6 26 56.7 78 19.4 28 27.6 41 46.2 16 39.7 95 20.6 122 35.3 127 28.0 126
WRT [146]76.6 38.4 68 61.6 58 26.8 41 31.9 111 58.0 119 32.7 107 28.0 103 56.1 86 21.7 72 14.6 83 41.9 74 9.03 72 30.7 49 37.0 39 24.9 49 35.7 117 62.5 106 31.8 104 34.3 67 63.2 101 37.1 88 7.23 46 15.2 37 7.62 42
TF+OM [98]78.0 39.8 74 55.2 43 30.4 58 20.4 43 41.0 13 23.5 53 19.5 61 39.4 38 28.0 98 18.4 101 37.0 50 18.0 108 35.0 79 41.1 61 39.6 112 29.6 95 52.6 52 29.1 93 49.0 120 66.8 114 43.6 108 14.4 100 29.3 97 18.0 101
CombBMOF [111]79.6 42.4 83 71.5 95 31.3 62 25.2 82 52.9 89 25.1 71 17.9 50 45.8 60 16.1 28 14.2 79 41.7 71 11.4 87 33.5 66 40.2 56 29.6 83 34.5 111 59.9 96 37.3 120 55.2 137 69.9 126 46.5 120 6.78 43 16.8 45 8.62 51
EPPM w/o HM [86]80.1 43.1 88 72.4 100 38.1 77 18.7 30 52.5 83 16.9 24 21.3 67 56.2 87 17.5 36 16.2 93 45.3 87 12.7 96 33.4 63 39.6 50 30.0 84 33.5 105 65.4 116 33.8 109 45.5 107 66.1 112 65.5 152 6.88 44 18.1 52 9.16 61
FF++_ROB [141]80.8 38.0 67 69.4 88 32.4 64 25.8 89 54.8 107 27.6 87 28.3 108 63.7 114 30.3 101 15.7 90 49.6 102 12.9 97 35.0 79 44.9 90 28.9 79 23.0 54 55.4 72 23.0 69 22.1 26 53.1 54 24.0 63 10.1 77 25.5 80 12.8 83
Complementary OF [21]82.7 51.9 112 74.9 107 59.3 115 14.2 6 41.6 15 13.7 6 20.4 63 46.6 62 19.7 57 22.2 109 40.8 66 21.0 113 36.0 92 43.4 74 38.5 110 33.9 109 63.8 109 31.6 100 31.1 57 51.9 46 36.2 86 18.9 119 34.4 124 29.4 128
Aniso. Huber-L1 [22]82.8 33.9 45 65.1 68 32.8 67 34.0 112 54.0 101 40.0 115 27.9 100 55.0 83 38.4 113 15.2 88 49.9 103 12.0 91 35.3 84 44.6 87 28.5 73 23.9 64 55.9 74 20.7 40 50.6 125 62.1 97 39.7 95 8.15 56 20.7 59 8.39 48
VCN_RVC [178]84.4 55.6 114 78.9 115 49.0 100 29.1 105 56.1 113 30.0 103 27.5 98 60.4 107 24.8 82 16.3 95 52.8 109 11.6 89 35.0 79 43.2 73 27.9 68 25.3 75 59.4 93 24.6 76 22.3 27 61.9 95 7.73 14 8.49 61 22.2 67 10.5 67
Rannacher [23]84.8 43.1 88 71.0 93 45.2 91 24.1 73 49.4 59 26.4 79 26.0 90 56.9 91 26.0 86 14.2 79 42.7 76 10.5 83 37.1 99 47.9 111 30.7 87 32.3 102 65.2 115 27.0 86 44.0 103 56.0 72 39.7 95 7.83 52 21.2 63 9.19 62
TCOF [69]84.9 45.0 93 70.0 89 51.5 104 25.5 85 53.7 95 26.7 80 26.7 92 56.2 87 32.0 107 21.9 108 43.1 79 22.2 115 37.8 103 48.9 116 25.7 56 18.8 24 44.7 12 20.0 35 52.1 131 67.5 117 25.8 66 10.7 82 26.7 86 11.4 76
ComplOF-FED-GPU [35]86.0 49.5 106 75.7 111 55.3 108 15.3 11 47.0 45 13.8 7 21.1 66 52.7 75 16.1 28 17.1 97 40.6 65 14.2 101 35.7 89 45.1 94 32.5 91 35.3 114 67.5 127 34.4 112 46.5 113 59.0 83 50.8 130 12.8 97 29.6 98 16.6 96
ACK-Prior [27]86.9 55.9 115 72.7 102 59.3 115 17.5 24 43.3 20 16.0 18 17.8 48 42.3 48 16.3 32 17.6 99 41.3 68 12.0 91 35.3 84 41.1 61 35.9 100 37.4 130 59.6 94 34.3 111 59.8 144 61.1 91 74.7 156 17.7 117 29.2 96 27.4 121
F-TV-L1 [15]87.3 66.8 126 84.2 126 77.3 137 27.1 100 52.0 78 29.1 100 27.2 96 57.3 93 24.2 81 24.1 114 52.0 108 19.5 111 39.3 111 47.7 109 39.3 111 24.2 67 56.5 77 24.9 77 33.2 64 53.7 57 20.1 44 6.69 41 18.6 53 5.94 15
ROF-ND [105]88.3 49.2 104 71.5 95 49.4 101 22.5 65 46.2 40 20.6 40 21.4 68 50.0 70 18.1 40 23.1 111 53.7 113 16.0 103 35.9 90 46.1 100 28.6 74 33.5 105 58.5 87 30.3 97 60.7 147 70.5 127 60.4 144 9.67 71 20.9 61 10.2 66
LDOF [28]88.5 41.7 81 70.7 90 47.2 96 24.0 72 53.9 100 24.6 67 26.7 92 58.4 98 25.5 83 15.8 91 57.4 123 10.2 81 36.0 92 45.3 95 34.8 98 22.1 44 58.1 86 21.3 49 30.6 54 56.8 74 23.4 60 22.5 131 38.6 137 30.2 129
MCPFlow_RVC [197]88.9 63.2 121 77.9 113 48.7 99 49.5 132 66.5 136 53.4 129 50.3 134 76.4 130 53.4 132 20.7 105 42.4 75 16.5 105 38.0 106 47.4 107 25.0 50 23.2 55 50.4 39 24.2 74 27.5 40 58.3 81 4.48 9 8.18 57 17.4 50 8.78 55
GMFlow_RVC [196]89.9 76.9 143 79.3 117 73.3 129 35.5 113 53.2 91 40.5 116 33.2 115 54.3 79 34.0 110 27.7 119 41.5 70 23.4 119 35.6 88 42.3 69 28.8 77 33.5 105 54.7 66 32.0 105 46.5 113 76.4 147 23.5 61 2.66 2 8.79 2 0.35 1
SIOF [67]90.1 50.3 109 66.0 70 47.1 95 19.8 35 48.4 53 20.7 41 29.8 110 55.1 84 32.6 109 25.9 117 48.3 99 25.0 120 37.7 101 46.4 102 36.8 103 32.9 103 58.6 88 35.6 117 37.2 78 53.1 54 18.6 36 16.8 113 33.0 114 21.3 112
LocallyOriented [52]90.2 39.4 72 60.5 56 35.7 71 27.9 103 57.8 118 28.5 97 28.1 105 58.3 97 30.6 104 13.9 75 41.3 68 10.1 79 37.8 103 47.3 106 33.0 95 24.8 74 52.5 51 28.1 89 39.4 89 62.4 99 37.5 90 15.7 106 33.0 114 18.2 104
Second-order prior [8]90.4 37.6 65 70.9 92 37.2 75 22.4 63 51.2 71 23.7 55 24.5 83 59.1 103 22.6 75 11.2 43 41.2 67 8.48 64 37.9 105 49.6 124 28.8 77 29.0 92 68.8 131 26.0 81 55.5 138 64.7 106 52.7 135 14.7 103 34.1 122 17.3 100
Brox et al. [5]90.8 43.7 91 74.4 105 56.4 112 27.0 99 52.5 83 30.5 105 23.4 78 54.5 80 23.3 78 13.4 70 50.0 104 8.66 66 39.8 114 46.5 103 47.6 136 21.6 37 59.8 95 22.8 67 30.9 55 59.3 84 7.61 12 23.1 135 37.0 133 33.4 137
FlowNetS+ft+v [110]91.3 36.8 64 67.0 74 39.4 78 25.3 84 52.1 80 27.6 87 27.8 99 57.2 92 35.5 111 13.5 71 50.9 106 9.44 74 40.1 115 49.5 123 36.8 103 20.9 31 57.0 79 20.8 42 46.3 111 66.3 113 41.0 99 17.4 115 34.3 123 24.1 118
NL-TV-NCC [25]91.9 46.1 95 68.3 81 43.4 88 25.2 82 55.3 110 23.5 53 21.8 73 47.2 63 16.9 34 16.9 96 44.1 82 11.9 90 38.5 108 49.1 120 27.3 63 36.5 123 65.7 118 34.9 115 46.2 109 75.7 144 45.7 114 12.6 93 28.8 94 9.10 58
SRR-TVOF-NL [89]92.3 47.6 101 69.1 86 41.9 85 23.3 67 52.7 87 23.3 51 25.5 86 56.8 90 25.9 84 13.5 71 47.9 95 8.09 49 36.9 98 43.8 78 32.9 94 25.8 78 57.7 83 22.6 61 62.8 150 75.2 141 49.1 126 21.0 124 29.7 99 31.6 132
DF-Auto [113]92.4 41.6 80 64.2 63 32.8 67 42.0 122 58.8 122 49.6 124 34.8 118 62.2 110 47.2 123 20.7 105 53.4 112 14.5 102 36.2 94 44.7 88 37.2 107 15.1 6 42.9 10 17.4 12 45.3 105 69.0 122 13.0 19 24.2 139 37.7 134 31.9 133
DPOF [18]93.0 45.3 94 68.9 84 37.6 76 26.7 98 56.9 114 26.9 83 24.3 82 54.6 81 26.2 87 18.6 102 54.6 116 13.6 99 33.3 62 43.1 71 28.9 79 27.6 88 60.8 101 26.3 82 47.2 117 55.3 64 76.0 158 14.3 99 31.0 107 15.3 89
CRTflow [81]93.1 40.9 76 72.5 101 36.2 73 21.3 47 49.4 59 21.8 45 22.9 75 57.5 94 19.0 46 14.0 77 44.7 84 10.3 82 35.4 87 45.0 93 30.4 86 46.6 150 73.4 144 53.8 151 38.8 84 65.5 108 38.2 91 19.5 121 38.5 136 27.6 124
TriangleFlow [30]93.4 41.5 79 63.2 61 42.6 86 21.4 48 52.4 82 20.2 39 21.7 72 53.6 78 16.2 30 14.8 84 44.4 83 10.9 85 43.2 129 52.9 137 43.4 122 36.8 127 65.9 120 38.8 124 42.2 98 65.4 107 41.8 103 15.8 107 35.2 126 22.5 114
Bartels [41]94.8 48.6 102 63.2 61 61.4 121 23.4 69 44.0 24 27.1 85 21.4 68 44.6 56 23.8 80 26.2 118 43.0 78 25.4 121 36.8 96 44.7 88 41.7 119 33.7 108 60.0 97 41.7 138 52.6 132 67.2 116 61.1 146 11.2 87 23.4 71 16.3 93
Dynamic MRF [7]96.0 49.5 106 78.0 114 55.8 111 17.2 23 47.4 47 16.5 22 21.6 71 56.3 89 16.2 30 14.8 84 46.4 91 12.5 94 41.2 121 49.0 118 45.1 128 35.3 114 70.7 138 38.5 123 37.1 77 57.7 79 55.1 136 21.3 126 36.7 132 31.2 131
CBF [12]96.1 41.4 77 74.0 104 48.5 97 40.2 119 51.5 75 51.7 126 22.9 75 50.8 72 28.5 99 14.3 81 44.7 84 11.2 86 38.3 107 46.1 100 36.1 101 26.3 82 55.1 71 24.9 77 61.5 148 71.0 128 52.0 134 11.6 90 26.7 86 14.8 88
CLG-TV [48]96.5 41.4 77 68.0 80 40.8 82 37.0 117 53.1 90 45.3 118 30.9 111 58.7 100 40.2 115 22.8 110 62.0 130 19.3 110 39.0 110 47.6 108 38.2 109 27.2 84 61.0 103 27.1 87 46.2 109 57.8 80 29.3 77 9.74 72 24.6 77 9.11 59
CNN-flow-warp+ref [115]97.0 42.6 85 71.2 94 49.8 102 31.6 110 53.8 96 37.3 112 32.7 113 63.8 115 42.7 119 16.0 92 55.1 117 12.1 93 38.6 109 46.0 98 43.8 126 23.3 58 59.1 91 23.6 71 23.5 31 50.9 40 21.9 52 24.2 139 36.2 129 32.9 135
Local-TV-L1 [65]97.2 56.8 117 79.1 116 74.5 130 39.5 118 53.8 96 46.1 120 38.1 119 66.2 117 43.1 120 23.9 113 52.9 111 21.1 114 32.3 60 41.4 66 27.5 65 23.2 55 54.8 67 22.7 65 25.8 34 47.5 19 33.4 83 26.9 142 40.5 141 40.5 146
HBM-GC [103]99.8 73.5 138 79.7 118 79.4 141 30.0 106 49.7 66 33.6 108 29.3 109 47.8 66 30.4 102 35.4 130 45.2 86 33.3 130 30.5 48 35.1 24 32.6 93 34.6 112 52.0 44 35.4 116 70.9 156 80.1 152 62.6 147 8.83 63 19.1 54 13.0 85
TriFlow [93]103.0 47.1 98 66.5 73 41.1 84 31.2 109 49.6 64 37.3 112 27.9 100 52.3 74 39.4 114 24.7 115 49.3 101 22.3 116 37.7 101 43.5 76 43.1 121 28.4 90 52.7 54 29.0 92 76.7 160 73.7 134 99.5 163 16.2 111 30.5 103 20.1 108
OFRF [132]104.2 50.4 110 64.5 64 55.4 110 41.2 121 57.5 116 46.2 122 34.5 117 58.9 102 40.6 116 29.6 122 45.6 88 28.8 125 30.7 49 40.2 56 22.3 26 31.1 101 57.9 84 30.4 99 43.5 101 62.5 100 51.9 133 29.8 146 39.3 138 49.1 154
p-harmonic [29]105.4 50.4 110 86.6 137 56.5 114 27.1 100 54.5 104 28.9 99 32.9 114 69.3 123 30.4 102 19.8 103 65.1 133 16.2 104 39.6 113 47.2 105 40.3 114 30.4 98 66.5 122 32.2 107 45.6 108 64.4 104 28.9 76 10.2 78 24.1 76 13.2 86
Learning Flow [11]106.1 42.9 86 70.7 90 44.8 90 30.2 107 54.7 105 34.7 109 28.2 106 55.9 85 32.3 108 17.6 99 57.1 122 12.6 95 44.0 132 52.6 135 47.8 139 30.5 99 64.6 111 30.3 97 46.9 115 63.3 102 42.8 107 14.7 103 31.6 112 16.3 93
Fusion [6]108.4 40.5 75 75.6 110 45.9 93 20.0 37 50.0 68 22.5 47 20.8 65 52.8 76 22.8 76 16.2 93 52.8 109 13.5 98 43.1 127 49.0 118 47.5 133 39.6 137 67.8 129 43.8 143 63.9 151 75.0 140 46.3 119 35.5 152 42.6 147 53.3 158
Shiralkar [42]111.2 46.1 95 85.6 132 54.3 107 19.7 34 57.7 117 18.2 28 28.2 106 70.8 124 19.3 49 20.5 104 59.0 125 18.4 109 39.5 112 49.7 126 36.3 102 40.4 139 76.1 146 41.2 136 51.9 129 65.8 110 64.2 150 21.0 124 42.4 146 25.3 119
StereoFlow [44]111.4 95.9 163 96.0 162 97.4 163 88.3 163 96.2 163 86.2 159 82.6 160 94.8 161 73.7 157 91.4 162 96.3 162 90.3 161 53.0 152 61.6 157 52.8 145 11.2 2 39.3 6 11.7 3 10.5 3 42.5 6 1.70 2 11.5 88 23.6 73 18.0 101
LiteFlowNet [138]112.9 62.6 119 88.2 144 55.3 108 35.7 114 65.1 133 36.9 111 39.6 120 74.5 127 38.1 112 23.4 112 50.3 105 17.4 106 43.1 127 51.4 132 42.2 120 35.7 117 69.3 133 33.9 110 41.2 94 75.2 141 17.8 33 14.4 100 28.9 95 16.7 97
ContinualFlow_ROB [148]113.1 67.9 129 87.6 141 62.0 122 54.1 138 68.0 138 60.3 137 52.2 138 80.5 137 54.5 135 32.5 125 61.0 129 26.1 124 47.3 144 57.0 144 40.4 115 43.1 144 69.7 135 48.7 147 18.7 11 49.0 24 6.92 11 11.5 88 23.8 75 12.8 83
SegOF [10]115.8 56.3 116 71.9 98 37.1 74 57.3 142 62.9 130 68.3 145 46.0 128 69.0 122 57.2 140 41.0 134 59.5 127 37.2 133 43.5 130 48.3 114 56.4 149 38.2 135 69.6 134 39.1 125 17.9 10 64.5 105 3.40 6 22.7 134 33.0 114 32.0 134
StereoOF-V1MT [117]116.8 49.7 108 86.0 134 56.4 112 21.2 46 68.8 140 16.3 21 32.2 112 80.7 138 20.8 67 21.3 107 66.1 136 17.4 106 47.0 143 57.0 144 47.5 133 41.7 142 81.2 151 40.9 133 38.6 82 68.1 119 48.6 124 23.2 136 42.2 145 27.7 125
Ad-TV-NDC [36]117.8 73.7 139 85.4 130 89.5 157 56.9 140 60.4 126 67.5 143 51.0 135 75.9 129 57.6 142 45.7 137 65.7 134 47.9 141 35.3 84 45.3 95 28.9 79 27.3 87 57.2 81 28.2 90 34.6 69 55.0 63 27.3 73 34.0 149 48.7 153 47.5 151
EAI-Flow [147]118.4 71.2 133 88.2 144 74.6 131 35.9 115 59.6 124 38.0 114 40.3 121 74.4 126 44.4 121 33.3 126 55.4 119 31.8 128 40.7 120 49.7 126 36.9 105 37.2 129 65.8 119 39.3 128 57.5 140 72.5 131 39.3 94 11.1 86 25.5 80 12.7 81
C-RAFT_RVC [181]119.2 78.8 148 92.1 151 75.6 134 53.7 137 68.4 139 58.1 135 57.1 145 82.6 141 61.7 149 28.9 121 55.3 118 22.6 117 46.9 142 55.9 143 43.4 122 35.5 116 65.0 113 40.4 131 45.3 105 69.8 125 17.5 31 10.7 82 22.9 70 8.35 47
WOLF_ROB [144]119.6 56.9 118 87.9 142 59.5 117 35.9 115 66.0 135 35.7 110 42.5 123 78.3 132 44.7 122 24.7 115 59.5 127 22.9 118 41.2 121 49.1 120 43.4 122 37.7 132 72.0 142 35.9 118 34.3 67 61.3 94 27.4 74 22.5 131 40.1 140 33.0 136
Modified CLG [34]119.9 68.7 130 80.5 121 76.1 135 52.0 135 61.0 127 63.6 139 51.9 136 79.4 133 55.6 137 47.4 140 72.1 144 46.7 139 41.2 121 49.7 126 46.0 130 26.0 79 64.7 112 26.7 85 31.4 60 55.6 67 19.9 43 29.0 145 43.8 149 39.9 145
CompactFlow_ROB [155]120.1 75.4 141 80.3 120 60.2 119 56.9 140 71.3 145 64.0 140 59.4 149 86.4 147 66.2 153 34.8 129 57.0 121 30.4 127 47.8 145 55.5 142 46.3 131 37.0 128 71.2 139 39.2 126 20.9 16 58.5 82 3.99 8 17.4 115 34.7 125 16.5 95
IAOF2 [51]121.1 54.9 113 73.7 103 53.9 106 42.6 123 58.3 120 50.7 125 33.9 116 61.9 109 42.1 118 64.4 150 75.7 147 74.3 152 41.5 124 49.9 130 37.1 106 36.4 122 64.0 110 34.4 112 59.7 142 69.6 124 41.3 100 19.4 120 33.4 119 23.0 116
Filter Flow [19]124.2 62.9 120 74.4 105 60.8 120 42.8 124 60.1 125 49.4 123 42.5 123 66.0 116 51.2 128 52.1 146 69.5 141 50.2 142 44.8 135 49.7 126 54.4 147 41.9 143 66.7 123 43.6 142 74.3 159 88.9 161 42.6 106 10.6 81 21.6 66 12.6 80
AugFNG_ROB [139]124.8 72.6 137 79.9 119 59.6 118 59.5 143 72.0 147 68.5 146 55.6 143 83.3 142 56.1 138 34.1 128 59.3 126 30.3 126 49.8 148 58.3 148 47.4 132 37.9 134 71.3 140 39.6 129 35.5 72 73.9 135 8.00 15 15.9 108 33.2 117 18.4 105
LSM_FLOW_RVC [182]125.6 80.5 153 95.3 160 79.1 140 50.6 134 71.0 144 54.5 132 53.9 140 89.5 153 47.9 125 31.9 124 66.2 137 25.4 121 46.8 141 54.4 141 45.7 129 37.7 132 72.5 143 41.2 136 27.8 42 68.3 121 13.4 21 16.8 113 36.2 129 18.1 103
SPSA-learn [13]126.5 65.1 122 87.4 140 72.7 128 45.7 129 59.3 123 53.4 129 45.2 127 74.7 128 52.2 130 41.6 135 69.9 143 42.5 135 42.7 126 48.9 116 48.7 141 38.8 136 69.0 132 42.5 140 39.1 87 61.9 95 19.3 38 36.0 153 45.6 150 48.3 152
GroupFlow [9]127.0 66.4 124 85.2 129 80.8 144 61.6 147 75.4 151 69.0 147 51.9 136 83.6 143 57.0 139 33.5 127 63.9 131 32.5 129 49.6 147 61.0 152 39.9 113 51.3 155 81.7 152 59.4 155 22.8 30 51.1 41 16.5 25 28.0 144 41.9 144 37.9 143
IAOF [50]127.1 66.3 123 81.3 123 77.8 138 50.1 133 58.4 121 59.7 136 45.0 126 74.1 125 49.6 127 50.8 143 68.2 138 58.0 148 40.2 116 48.7 115 37.8 108 36.7 124 66.9 124 33.5 108 54.9 135 63.5 103 40.8 98 30.1 148 41.3 143 43.5 147
2D-CLG [1]127.1 77.2 144 82.3 124 75.4 133 61.5 146 65.9 134 73.7 151 63.2 151 89.6 154 60.8 147 82.8 159 88.3 156 86.8 159 43.5 130 49.3 122 54.8 148 35.1 113 67.5 127 36.1 119 21.3 21 50.8 39 15.5 23 34.4 151 46.3 152 46.0 148
TVL1_RVC [175]127.3 88.5 158 92.7 152 96.4 161 69.8 155 66.8 137 83.8 157 67.8 153 90.2 156 70.7 155 77.3 155 89.0 158 80.7 155 40.2 116 49.6 124 40.8 116 23.9 64 65.6 117 27.6 88 21.6 25 57.0 77 10.3 17 36.2 154 51.0 155 47.2 150
BlockOverlap [61]127.3 77.2 144 86.0 134 82.8 147 48.2 130 55.8 112 57.6 134 46.9 130 66.9 118 51.9 129 49.1 142 54.1 114 51.2 143 36.8 96 41.3 65 47.5 133 40.5 140 59.0 90 39.6 129 68.9 155 80.2 153 65.1 151 20.8 123 30.8 105 34.9 139
HBpMotionGpu [43]127.6 67.0 127 80.7 122 72.3 127 55.3 139 57.3 115 66.7 142 44.7 125 67.2 120 54.1 134 39.5 133 57.8 124 38.4 134 42.0 125 48.2 113 48.3 140 35.9 119 60.9 102 39.2 126 65.1 152 72.0 130 50.1 128 22.6 133 32.5 113 36.9 140
LFNet_ROB [145]128.6 72.3 134 93.8 156 65.3 124 45.6 128 78.1 156 45.9 119 48.8 133 87.7 150 41.8 117 31.5 123 66.0 135 25.6 123 47.8 145 57.1 146 47.6 136 37.6 131 71.5 141 38.0 121 49.3 122 74.5 138 26.4 70 15.9 108 33.5 120 20.9 110
GraphCuts [14]129.4 66.6 125 87.0 138 80.0 143 43.1 125 63.0 131 46.1 120 41.8 122 67.0 119 53.4 132 28.5 120 64.0 132 20.8 112 40.2 116 48.1 112 43.5 125 46.5 148 63.4 107 40.5 132 62.7 149 75.4 143 69.5 154 23.8 138 33.3 118 38.5 144
Black & Anandan [4]130.0 70.3 132 88.0 143 84.1 148 45.5 127 61.4 128 52.0 127 47.4 131 77.3 131 52.9 131 42.3 136 77.5 148 42.8 136 44.0 132 51.8 133 45.0 127 35.9 119 75.9 145 38.3 122 50.8 126 71.3 129 17.8 33 29.8 146 42.7 148 37.6 142
IRR-PWC_RVC [180]131.8 78.7 147 85.7 133 72.0 126 59.5 143 68.9 141 67.8 144 64.7 152 85.8 146 65.7 152 38.6 131 69.2 139 34.2 131 46.6 140 52.9 137 49.0 142 33.9 109 69.8 136 32.1 106 49.7 123 81.6 158 21.1 47 21.9 129 36.6 131 26.0 120
EPMNet [131]133.0 78.2 146 91.5 149 78.0 139 61.6 147 75.7 152 69.6 148 55.3 142 79.5 134 57.3 141 48.1 141 56.6 120 47.7 140 45.3 136 54.0 139 41.1 117 36.7 124 67.3 125 41.0 134 56.4 139 81.4 156 26.3 68 18.6 118 36.0 128 20.7 109
FlowNet2 [120]133.1 78.8 148 86.2 136 79.4 141 63.5 152 70.2 143 72.8 150 57.2 147 82.0 139 59.7 146 46.2 138 51.4 107 45.6 138 45.3 136 54.0 139 41.1 117 36.7 124 67.3 125 41.0 134 67.6 154 80.8 154 55.1 136 14.5 102 30.0 102 13.9 87
ResPWCR_ROB [140]133.8 78.9 150 92.8 154 75.1 132 40.4 120 63.5 132 43.5 117 48.1 132 80.2 135 48.8 126 39.2 132 69.2 139 35.6 132 44.0 132 50.5 131 49.2 143 44.6 147 76.7 147 47.0 145 54.6 134 78.7 149 31.4 80 23.4 137 38.0 135 30.8 130
2bit-BM-tele [96]134.9 82.4 154 87.2 139 91.8 158 44.4 126 54.7 105 52.9 128 46.0 128 68.3 121 47.4 124 51.5 145 54.4 115 53.4 146 40.5 119 47.1 104 47.7 138 47.9 151 66.4 121 53.1 149 71.7 157 83.6 159 75.1 157 21.9 129 39.3 138 29.2 127
Nguyen [33]135.6 75.6 142 85.4 130 85.8 150 67.0 153 61.6 129 83.0 156 57.1 145 80.2 135 64.1 151 70.8 151 80.2 150 77.4 154 45.9 139 52.2 134 56.4 149 36.3 121 68.1 130 42.0 139 41.4 95 66.0 111 19.7 41 34.1 150 45.6 150 46.1 149
SILK [80]137.4 72.5 135 85.1 128 88.3 154 61.9 149 71.8 146 73.7 151 54.9 141 85.3 144 58.0 144 53.6 147 69.8 142 54.6 147 52.8 150 57.9 147 61.8 153 46.5 148 77.6 148 48.9 148 31.3 58 54.3 61 38.9 92 37.8 155 50.6 154 49.7 155
UnFlow [127]140.1 89.6 160 94.1 157 86.4 151 72.2 156 83.9 159 77.9 154 71.4 157 93.2 158 69.8 154 54.8 148 74.4 145 51.4 144 62.0 158 66.9 159 69.1 160 50.0 153 80.9 149 57.1 152 53.2 133 69.0 122 7.68 13 15.6 105 30.8 105 21.0 111
Periodicity [79]140.4 68.9 131 83.5 125 65.5 125 52.2 136 69.8 142 57.0 133 78.4 159 82.5 140 87.2 161 47.2 139 74.7 146 45.5 137 69.7 163 81.9 163 65.6 157 59.5 158 84.9 159 60.7 156 36.3 76 79.8 151 19.2 37 40.7 157 66.5 162 53.1 157
Horn & Schunck [3]141.1 74.1 140 93.2 155 86.9 152 49.1 131 73.8 148 53.9 131 53.1 139 89.0 152 54.6 136 50.9 144 81.4 151 52.4 145 51.3 149 58.8 149 54.3 146 41.2 141 82.3 153 44.6 144 55.0 136 74.3 137 19.6 40 40.7 157 56.8 157 48.8 153
Heeger++ [102]144.5 86.1 156 91.0 148 77.1 136 67.6 154 91.6 162 65.1 141 85.6 162 94.6 160 83.6 160 71.0 152 88.2 155 68.8 150 62.9 159 69.8 161 67.3 158 69.4 162 91.0 162 70.8 160 40.2 92 80.9 155 26.3 68 21.7 127 31.2 108 27.4 121
SLK [47]145.2 67.5 128 90.3 146 82.1 145 72.2 156 84.7 160 84.8 158 58.4 148 94.0 159 58.1 145 78.1 156 82.5 152 84.6 158 55.4 155 61.5 155 68.1 159 49.4 152 83.7 157 57.7 153 36.2 75 68.1 119 26.2 67 50.3 160 60.0 159 65.2 162
FFV1MT [104]147.4 85.0 155 92.0 150 84.4 149 60.6 145 83.8 158 60.8 138 85.4 161 92.2 157 88.2 162 71.2 153 89.9 159 69.1 151 64.0 161 69.3 160 78.0 162 69.2 161 91.5 163 73.2 162 51.7 128 73.9 135 45.3 111 21.7 127 31.2 108 27.4 121
FOLKI [16]147.6 72.5 135 84.5 127 87.5 153 62.3 150 74.9 150 74.0 153 56.9 144 87.2 148 57.7 143 59.8 149 78.1 149 65.4 149 53.3 153 61.2 154 62.7 154 50.9 154 81.0 150 62.7 157 47.3 119 73.3 132 56.8 140 49.0 159 62.9 160 64.3 161
TI-DOFE [24]148.2 90.7 161 94.6 159 97.1 162 76.9 161 79.5 157 89.4 162 73.1 158 96.1 162 74.4 158 84.6 160 93.6 161 88.3 160 52.9 151 59.9 150 63.9 155 44.5 146 83.6 156 53.5 150 42.9 99 68.0 118 17.0 30 50.5 161 65.5 161 62.4 160
H+S_RVC [176]148.3 79.6 152 90.3 146 82.3 146 75.7 159 90.8 161 80.5 155 71.1 156 96.2 163 61.0 148 89.4 161 88.1 154 91.6 162 56.7 156 60.0 151 70.2 161 57.2 156 86.6 161 64.3 158 31.7 62 78.0 148 25.0 65 55.9 162 57.2 158 62.3 159
PGAM+LK [55]154.5 79.4 151 92.7 152 88.7 155 62.9 151 76.8 155 71.9 149 59.9 150 88.3 151 62.8 150 74.9 154 90.6 160 75.6 153 54.4 154 61.0 152 64.6 156 58.1 157 82.7 154 58.6 154 77.6 161 85.6 160 78.1 160 38.8 156 52.7 156 50.7 156
Adaptive flow [45]155.3 91.3 162 95.7 161 96.2 159 75.8 160 75.9 153 86.2 159 68.9 154 85.6 145 72.4 156 80.6 158 85.2 153 83.9 157 57.3 157 61.5 155 60.2 152 66.7 159 84.1 158 70.4 159 90.2 162 92.7 162 95.0 161 27.7 143 40.5 141 37.0 141
HCIC-L [97]156.1 88.6 159 96.7 163 89.3 156 80.8 162 74.4 149 93.1 163 86.6 163 87.2 148 95.2 163 95.8 163 97.4 163 96.9 163 63.4 160 66.7 158 57.8 151 68.9 160 82.7 154 73.1 161 96.0 163 95.9 163 98.6 162 25.3 141 33.9 121 34.7 138
Pyramid LK [2]158.6 86.7 157 94.5 158 96.2 159 73.1 158 76.5 154 86.4 161 70.8 155 89.6 154 78.5 159 78.1 156 88.6 157 82.7 156 68.8 162 76.4 162 80.4 163 75.7 163 85.1 160 78.1 163 73.1 158 79.6 150 69.3 153 60.8 163 74.5 163 79.9 163
AdaConv-v1 [124]164.3 100.0 164 100.0 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 165 99.9 165 99.9 165 99.9 165 100.0 165 99.7 165 99.9 165 99.9 164 99.9 164 99.9 164
SepConv-v1 [125]164.3 100.0 164 100.0 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 165 99.9 165 99.9 165 99.9 165 100.0 165 99.7 165 99.9 165 99.9 164 99.9 164 99.9 164
SuperSlomo [130]164.3 100.0 164 100.0 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 165 99.9 165 99.9 165 99.9 165 100.0 165 99.7 165 99.9 165 99.9 164 99.9 164 99.9 164
CtxSyn [134]164.3 100.0 164 100.0 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 165 99.9 165 99.9 165 99.9 165 100.0 165 99.7 165 99.9 165 99.9 164 99.9 164 99.9 164
CyclicGen [149]164.3 100.0 164 100.0 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 165 99.9 165 99.9 165 99.9 165 100.0 165 99.7 165 99.9 165 99.9 164 99.9 164 99.9 164
TOF-M [150]164.3 100.0 164 100.0 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 165 99.9 165 99.9 165 99.9 165 100.0 165 99.7 165 99.9 165 99.9 164 99.9 164 99.9 164
MPRN [151]164.3 100.0 164 100.0 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 165 99.9 165 99.9 165 99.9 165 100.0 165 99.7 165 99.9 165 99.9 164 99.9 164 99.9 164
DAIN [152]164.3 100.0 164 100.0 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 165 99.9 165 99.9 165 99.9 165 100.0 165 99.7 165 99.9 165 99.9 164 99.9 164 99.9 164
FRUCnet [153]164.3 100.0 164 100.0 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 165 99.9 165 99.9 165 99.9 165 100.0 165 99.7 165 99.9 165 99.9 164 99.9 164 99.9 164
OFRI [154]164.3 100.0 164 100.0 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 165 99.9 165 99.9 165 99.9 165 100.0 165 99.7 165 99.9 165 99.9 164 99.9 164 99.9 164
FGME [158]164.3 100.0 164 100.0 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 165 99.9 165 99.9 165 99.9 165 100.0 165 99.7 165 99.9 165 99.9 164 99.9 164 99.9 164
MS-PFT [159]164.3 100.0 164 100.0 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 165 99.9 165 99.9 165 99.9 165 100.0 165 99.7 165 99.9 165 99.9 164 99.9 164 99.9 164
MEMC-Net+ [160]164.3 100.0 164 100.0 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 165 99.9 165 99.9 165 99.9 165 100.0 165 99.7 165 99.9 165 99.9 164 99.9 164 99.9 164
ADC [161]164.3 100.0 164 100.0 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 165 99.9 165 99.9 165 99.9 165 100.0 165 99.7 165 99.9 165 99.9 164 99.9 164 99.9 164
DSepConv [162]164.3 100.0 164 100.0 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 165 99.9 165 99.9 165 99.9 165 100.0 165 99.7 165 99.9 165 99.9 164 99.9 164 99.9 164
MAF-net [163]164.3 100.0 164 100.0 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 165 99.9 165 99.9 165 99.9 165 100.0 165 99.7 165 99.9 165 99.9 164 99.9 164 99.9 164
STAR-Net [164]164.3 100.0 164 100.0 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 165 99.9 165 99.9 165 99.9 165 100.0 165 99.7 165 99.9 165 99.9 164 99.9 164 99.9 164
AdaCoF [165]164.3 100.0 164 100.0 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 165 99.9 165 99.9 165 99.9 165 100.0 165 99.7 165 99.9 165 99.9 164 99.9 164 99.9 164
TC-GAN [166]164.3 100.0 164 100.0 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 165 99.9 165 99.9 165 99.9 165 100.0 165 99.7 165 99.9 165 99.9 164 99.9 164 99.9 164
FeFlow [167]164.3 100.0 164 100.0 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 165 99.9 165 99.9 165 99.9 165 100.0 165 99.7 165 99.9 165 99.9 164 99.9 164 99.9 164
DAI [168]164.3 100.0 164 100.0 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 165 99.9 165 99.9 165 99.9 165 100.0 165 99.7 165 99.9 165 99.9 164 99.9 164 99.9 164
SoftSplat [169]164.3 100.0 164 100.0 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 165 99.9 165 99.9 165 99.9 165 100.0 165 99.7 165 99.9 165 99.9 164 99.9 164 99.9 164
STSR [170]164.3 100.0 164 100.0 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 165 99.9 165 99.9 165 99.9 165 100.0 165 99.7 165 99.9 165 99.9 164 99.9 164 99.9 164
BMBC [171]164.3 100.0 164 100.0 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 165 99.9 165 99.9 165 99.9 165 100.0 165 99.7 165 99.9 165 99.9 164 99.9 164 99.9 164
GDCN [172]164.3 100.0 164 100.0 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 165 99.9 165 99.9 165 99.9 165 100.0 165 99.7 165 99.9 165 99.9 164 99.9 164 99.9 164
EDSC [173]164.3 100.0 164 100.0 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 165 99.9 165 99.9 165 99.9 165 100.0 165 99.7 165 99.9 165 99.9 164 99.9 164 99.9 164
MV_VFI [183]164.3 100.0 164 100.0 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 165 99.9 165 99.9 165 99.9 165 100.0 165 99.7 165 99.9 165 99.9 164 99.9 164 99.9 164
DistillNet [184]164.3 100.0 164 100.0 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 165 99.9 165 99.9 165 99.9 165 100.0 165 99.7 165 99.9 165 99.9 164 99.9 164 99.9 164
SepConv++ [185]164.3 100.0 164 100.0 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 165 99.9 165 99.9 165 99.9 165 100.0 165 99.7 165 99.9 165 99.9 164 99.9 164 99.9 164
EAFI [186]164.3 100.0 164 100.0 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 165 99.9 165 99.9 165 99.9 165 100.0 165 99.7 165 99.9 165 99.9 164 99.9 164 99.9 164
FLAVR [188]164.3 100.0 164 100.0 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 165 99.9 165 99.9 165 99.9 165 100.0 165 99.7 165 99.9 165 99.9 164 99.9 164 99.9 164
SoftsplatAug [190]164.3 100.0 164 100.0 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 165 99.9 165 99.9 165 99.9 165 100.0 165 99.7 165 99.9 165 99.9 164 99.9 164 99.9 164
ProBoost-Net [191]164.3 100.0 164 100.0 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 165 99.9 165 99.9 165 99.9 165 100.0 165 99.7 165 99.9 165 99.9 164 99.9 164 99.9 164
IDIAL [192]164.3 100.0 164 100.0 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 165 99.9 165 99.9 165 99.9 165 100.0 165 99.7 165 99.9 165 99.9 164 99.9 164 99.9 164
IFRNet [193]164.3 100.0 164 100.0 165 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 164 99.9 165 99.9 165 99.9 165 99.9 165 100.0 165 99.7 165 99.9 165 99.9 164 99.9 164 99.9 164
AVG_FLOW_ROB [137]168.4 100.0 164 99.9 164 100.0 164 100.0 164 100.0 164 100.0 164 99.9 164 99.9 164 99.9 164 100.0 199 99.9 164 100.0 199 99.9 164 100.0 199 99.8 164 99.2 164 99.5 164 98.3 164 99.6 164 97.0 164 99.7 164 99.9 164 99.9 164 99.9 164
Move the mouse over the numbers in the table to see the corresponding images. Click to compare with the ground truth.

References

Methodtime*framescolor Reference and notes
[1] 2D-CLG 844 2 gray The 2D-CLG method by Bruhn et al. as implemented by Stefan Roth. [A. Bruhn, J. Weickert, and C. Schnörr. Lucas/Kanade meets Horn/Schunck: combining local and global optic flow methods. IJCV 63(3), 2005.] Parameters were set to match the published performance on Yosemite sequence, which may not be optimal for other sequences.
[2] Pyramid LK 12 2 color A modification of Bouguet's pyramidal implementation of Lucas-Kanade.
[3] Horn & Schunck 49 2 gray A modern Matlab implementation of the Horn & Schunck method by Deqing Sun. Parameters set to optimize AAE on all training data.
[4] Black & Anandan 328 2 gray A modern Matlab implementation of the Black & Anandan method by Deqing Sun.
[5] Brox et al. 18 2 color T. Brox, A. Bruhn, N. Papenberg, and J. Weickert. High accuracy optical flow estimation based on a theory for warping. ECCV 2004. (Improved using separate robust functions as proposed in A. Bruhn and J. Weickert, Towards ultimate motion estimation, ICCV 2005; improved by training on the training set.)
[6] Fusion 2,666 2 color V. Lempitsky, S. Roth, and C. Rother. Discrete-continuous optimization for optical flow estimation. CVPR 2008.
[7] Dynamic MRF 366 2 gray B. Glocker, N. Paragios, N. Komodakis, G. Tziritas, and N. Navab. Optical flow estimation with uncertainties through dynamic MRFs. CVPR 2008. (Method improved since publication.)
[8] Second-order prior 14 2 gray W. Trobin, T. Pock, D. Cremers, and H. Bischof. An unbiased second-order prior for high-accuracy motion estimation. DAGM 2008. (Method improved since publication; for details see W. Trobin, Ph.D. thesis, 2009.)
[9] GroupFlow 600 2 gray X. Ren. Local Grouping for Optical Flow. CVPR 2008.
[10] SegOF 60 2 color L. Xu, J. Chen, and J. Jia. Segmentation based variational model for accurate optical flow estimation. ECCV 2008. Code available.
[11] Learning Flow 825 2 gray D. Sun, S. Roth, J.P. Lewis, and M. Black. Learning optical flow (SRF-LFC). ECCV 2008.
[12] CBF 69 2 color W. Trobin, T. Pock, D. Cremers, and H. Bischof. Continuous energy minimization via repeated binary fusion. ECCV 2008. (Method improved since publication; for details see W. Trobin, Ph.D. thesis, 2009.)
[13] SPSA-learn 200 2 color Y. Li and D. Huttenlocher. Learning for optical flow using stochastic optimization. ECCV 2008.
[14] GraphCuts 1,200 2 color T. Cooke. Two applications of graph-cuts to image processing. DICTA 2008.
[15] F-TV-L1 8 2 gray A. Wedel, T. Pock, J. Braun, U. Franke, and D. Cremers. Duality TV-L1 flow with fundamental matrix prior. IVCNZ 2008.
[16] FOLKI 1.4 2 gray G. Le Besnerais and F. Champagnat. Dense optical flow by iterative local window registration. ICIP 2005.
[17] TV-L1-improved 2.9 2 gray A. Wedel, T. Pock, C. Zach, H. Bischof, and D. Cremers. An improved algorithm for TV-L1 optical flow computation. Proceedings of the Dagstuhl Visual Motion Analysis Workshop 2008. Code at GPU4Vision.
[18] DPOF 287 2 color C. Lei and Y.-H. Yang. Optical flow estimation on coarse-to-fine region-trees using discrete optimization. ICCV 2009. (Method improved since publication.)
[19] Filter Flow 34,000 2 color S. Seitz and S. Baker. Filter flow. ICCV 2009.
[20] Adaptive 9.2 2 gray A. Wedel, D. Cremers, T. Pock, and H. Bischof. Structure- and motion-adaptive regularization for high accuracy optic flow. ICCV 2009.
[21] Complementary OF 44 2 color H. Zimmer, A. Bruhn, J. Weickert, L. Valgaerts, A. Salgado, B. Rosenhahn, and H.-P. Seidel. Complementary optic flow. EMMCVPR 2009.
[22] Aniso. Huber-L1 2 2 gray M. Werlberger, W. Trobin, T. Pock, A. Wedel, D. Cremers, and H. Bischof. Anisotropic Huber-L1 optical flow. BMVC 2009. Code at GPU4Vision.
[23] Rannacher 0.12 2 gray J. Rannacher. Realtime 3D motion estimation on graphics hardware. Bachelor thesis, Heidelberg University, 2009.
[24] TI-DOFE 260 2 gray C. Cassisa, S. Simoens, and V. Prinet. Two-frame optical flow formulation in an unwarped multiresolution scheme. CIARP 2009.
[25] NL-TV-NCC 20 2 color M. Werlberger, T. Pock, and H. Bischof. Motion estimation with non-local total variation regularization. CVPR 2010.
[26] MDP-Flow 188 2 color L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. CVPR 2010.
[27] ACK-Prior 5872 2 color K. Lee, D. Kwon, I. Yun, and S. Lee. Optical flow estimation with adaptive convolution kernel prior on discrete framework. CVPR 2010.
[28] LDOF 122 2 color T. Brox and J. Malik. Large displacement optical flow: descriptor matching in variational motion estimation. PAMI 33(3):500-513, 2011.
[29] p-harmonic 565 2 gray J. Gai and R. Stevenson. Optical flow estimation with p-harmonic regularization. ICIP 2010.
[30] TriangleFlow 4200 2 gray B. Glocker, H. Heibel, N. Navab, P. Kohli, and C. Rother. TriangleFlow: Optical flow with triangulation-based higher-order likelihoods. ECCV 2010.
[31] Classic+NL 972 2 color D. Sun, S. Roth, and M. Black. Secrets of optical flow estimation and their principles. CVPR 2010. Matlab code.
[32] Classic++ 486 2 gray A modern implementation of the classical formulation descended from Horn & Schunck and Black & Anandan; see D. Sun, S. Roth, and M. Black, Secrets of optical flow estimation and their principles, CVPR 2010.
[33] Nguyen 33 2 gray D. Nguyen. Tuning optical flow estimation with image-driven functions. ICRA 2011.
[34] Modified CLG 133 2 gray R. Fezzani, F. Champagnat, and G. Le Besnerais. Combined local global method for optic flow computation. EUSIPCO 2010.
[35] ComplOF-FED-GPU 0.97 2 color P. Gwosdek, H. Zimmer, S. Grewenig, A. Bruhn, and J. Weickert. A highly efficient GPU implementation for variational optic flow based on the Euler-Lagrange framework. CVGPU Workshop 2010.
[36] Ad-TV-NDC 35 2 gray M. Nawaz. Motion estimation with adaptive regularization and neighborhood dependent constraint. DICTA 2010.
[37] Layers++ 18206 2 color D. Sun, E. Sudderth, and M. Black. Layered image motion with explicit occlusions, temporal consistency, and depth ordering. NIPS 2010.
[38] OFH 620 3 color H. Zimmer, A. Bruhn, J. Weickert. Optic flow in harmony. IJCV 93(3) 2011.
[39] LSM 1615 2 color K. Jia, X. Wang, and X. Tang. Optical flow estimation using learned sparse model. ICCV 2011.
[40] CostFilter 55 2 color C. Rhemann, A. Hosni, M. Bleyer, C. Rother, and M. Gelautz. Fast cost-volume filtering for visual correspondence and beyond. CVPR 2011.
[41] Bartels 0.15 2 gray C. Bartels and G. de Haan. Smoothness constraints in recursive search motion estimation for picture rate conversion. IEEE TCSVT 2010. Version improved since publication: mapped on GPU.
[42] Shiralkar 600 2 gray M. Shiralkar and R. Schalkoff. A self organization-based optical flow estimator with GPU implementation. MVA 23(6):1229-1242.
[43] HBpMotionGpu 1000 5 gray S. Grauer-Gray and C. Kambhamettu. Hierarchical belief propagation to reduce search space using CUDA for stereo and motion estimation. WACV 2009. (Method improved since publication.)
[44] StereoFlow 7200 2 color G. Rosman, S. Shem-Tov, D. Bitton, T. Nir, G. Adiv, R. Kimmel, A. Feuer, and A. Bruckstein. Over-parameterized optical flow using a stereoscopic constraint. SSVM 2011:761-772.
[45] Adaptive flow 121 2 gray Tarik Arici and Vural Aksakalli. Energy minimization based motion estimation using adaptive smoothness priors. VISAPP 2012.
[46] TC-Flow 2500 5 color S. Volz, A. Bruhn, L. Valgaerts, and H. Zimmer. Modeling temporal coherence for optical flow. ICCV 2011.
[47] SLK 300 2 gray T. Corpetti and E. Mémin. Stochastic uncertainty models for the luminance consistency assumption. IEEE TIP 2011.
[48] CLG-TV 29 2 gray M. Drulea. Total variation regularization of local-global optical flow. ITSC 2011. Matlab code.
[49] SimpleFlow 1.7 2 color M. Tao, J. Bai, P. Kohli, S. Paris. SimpleFlow: a non-iterative, sublinear optical flow algorithm. EUROGRAPHICS 2012.
[50] IAOF 57 2 gray D. Nguyen. Improving motion estimation using image-driven functions and hybrid scheme. PSIVT 2011.
[51] IAOF2 56 2 gray Duc Dung Nguyen and Jae Wook Jeon. Enhancing accuracy and sharpness of motion field with adaptive scheme and occlusion-aware filter. IET Image Processing 7.2 (2013): 144-153.
[52] LocallyOriented 9541 2 gray Y.Niu, A. Dick, and M. Brooks. Locally oriented optical flow computation. To appear in TIP 2012.
[53] IROF-TV 261 2 color H. Rashwan, D. Puig, and M. Garcia. On improving the robustness of differential optical flow. ICCV 2011 Artemis workshop.
[54] Sparse Occlusion 2312 2 color Alper Ayvaci, Michalis Raptis, and Stefano Soatto. Sparse occlusion detection with optical flow. IJCV 97(3):322-338, 2012.
[55] PGAM+LK 0.37 2 gray A. Alba, E. Arce-Santana, and M. Rivera. Optical flow estimation with prior models obtained from phase correlation. ISVC 2010.
[56] Sparse-NonSparse 713 2 color Zhuoyuan Chen, Jiang Wang, and Ying Wu. Decomposing and regularizing sparse/non-sparse components for motion field estimation. CVPR 2012.
[57] nLayers 36150 4 color D. Sun, E. Sudderth, and M. Black. Layered segmentation and optical flow estimation over time. CVPR 2012.
[58] IROF++ 187 2 color H. Rashwan, D. Puig, and M. Garcia. Variational optical flow estimation based on stick tensor voting. IEEE TIP 2013.
[59] COFM 600 3 color M. Mozerov. Constrained optical flow estimation as a matching problem. IEEE TIP 2013.
[60] Efficient-NL 400 2 color P. Krähenbühl and V. Koltun. Efficient nonlocal regularization for optical flow. ECCV 2012.
[61] BlockOverlap 2 2 gray Michael Santoro, Ghassan AlRegib, and Yucel Altunbasak. Motion estimation using block overlap minimization. MMSP 2012.
[62] Ramp 1200 2 color A. Singh and N. Ahuja. Exploiting ramp structures for improving optical flow estimation. ICPR 2012.
[63] Occlusion-TV-L1 538 3 gray C. Ballester, L. Garrido, V. Lazcano, and V. Caselles. A TV-L1 optical flow method with occlusion detection. DAGM-OAGM 2012.
[64] TV-L1-MCT 90 2 color M. Mohamed and B. Mertsching. TV-L1 optical flow estimation with image details recovering based on modified census transform. ISVC 2012.
[65] Local-TV-L1 500 2 gray L. Raket. Local smoothness for global optical flow. ICIP 2012.
[66] ALD-Flow 61 2 color M. Stoll, A. Bruhn, and S. Volz. Adaptive integration of feature matches into variational optic flow methods. ACCV 2012.
[67] SIOF 234 2 color L. Xu, Z. Dai, and J. Jia. Scale invariant optical flow. ECCV 2012.
[68] MDP-Flow2 342 2 color L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. PAMI 34(9):1744-1757, 2012. Code available.
[69] TCOF 1421 all gray J. Sanchez, A. Salgado, and N. Monzon. Optical flow estimation with consistent spatio-temporal coherence models. VISAPP 2013.
[70] LME 476 2 color W. Li, D. Cosker, M. Brown, and R. Tang. Optical flow estimation using Laplacian mesh energy. CVPR 2013.
[71] NN-field 362 2 color L. Chen, H. Jin, Z. Lin, S. Cohen, and Y. Wu. Large displacement optical flow from nearest neighbor fields. CVPR 2013.
[72] FESL 3310 2 color Weisheng Dong, Guangming Shi, Xiaocheng Hu, and Yi Ma. Nonlocal sparse and low-rank regularization for optical flow estimation. IEEE TIP 23(10):4527-4538, 2014.
[73] PMF 35 2 color J. Lu, H. Yang, D. Min, and M. Do. PatchMatch filter: efficient edge-aware filtering meets randomized search for fast correspondence field estimation. CVPR 2013.
[74] FC-2Layers-FF 2662 4 color D. Sun, J. Wulff, E. Sudderth, H. Pfister, and M. Black. A fully-connected layered model of foreground and background flow. CVPR 2013.
[75] NNF-Local 673 2 color Zhuoyuan Chen, Hailin Jin, Zhe Lin, Scott Cohen, and Ying Wu. Large displacement optical flow from nearest neighbor fields. CVPR 2013.
[76] Correlation Flow 290 2 color M. Drulea and S. Nedevschi. Motion estimation using the correlation transform. TIP 2013. Matlab code.
[77] TC/T-Flow 341 5 color M. Stoll, S. Volz, and A. Bruhn. Joint trilateral filtering for multiframe optical flow. ICIP 2013.
[78] OFLAF 1530 2 color T. Kim, H. Lee, and K. Lee. Optical flow via locally adaptive fusion of complementary data costs. ICCV 2013.
[79] Periodicity 8000 4 color Georgii Khachaturov, Silvia Gonzalez-Brambila, and Jesus Gonzalez-Trejo. Periodicity-based computation of optical flow. Computacion y Sistemas (CyS) 2014.
[80] SILK 572 2 gray Pascal Zille, Thomas Corpetti, Liang Shao, and Xu Chen. Observation model based on scale interactions for optical flow estimation. IEEE TIP 23(8):3281-3293, 2014.
[81] CRTflow 13 3 color O. Demetz, D. Hafner, and J. Weickert. The complete rank transform: a tool for accurate and morphologically invariant matching of structures. BMVC 2013.
[82] Classic+CPF 640 2 gray Zhigang Tu, Nico van der Aa, Coert Van Gemeren, and Remco Veltkamp. A combined post-filtering method to improve accuracy of variational optical flow estimation. Pattern Recognition 47(5):1926-1940, 2014.
[83] S2D-Matching 1200 2 color Marius Leordeanu, Andrei Zanfir, and Cristian Sminchisescu. Locally affine sparse-to-dense matching for motion and occlusion estimation. ICCV 2013.
[84] AGIF+OF 438 2 gray Zhigang Tu, Ronald Poppe, and Remco Veltkamp. Adaptive guided image filter for warping in variational optical flow computation. Signal Processing 127:253-265, 2016.
[85] DeepFlow 13 2 color P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013.
[86] EPPM w/o HM 2.5 2 color L. Bao, Q. Yang, and H. Jin. Fast edge-preserving PatchMatch for large displacement optical flow. CVPR 2014.
[87] MLDP_OF 165 2 gray M. Mohamed, H. Rashwan, B. Mertsching, M. Garcia, and D. Puig. Illumination-robust optical flow approach using local directional pattern. IEEE TCSVT 24(9):1499-1508, 2014.
[88] RFlow 20 2 gray S. Ali, C. Daul, and W. Blondel. Robust and accurate optical flow estimation for weak texture and varying illumination condition: Application to cystoscopy. IPTA 2014.
[89] SRR-TVOF-NL 32 all color P. Pohl, M. Sirotenko, E. Tolstaya, and V. Bucha. Edge preserving motion estimation with occlusions correction for assisted 2D to 3D conversion. IS&T/SPIE Electronic Imaging 2014.
[90] 2DHMM-SAS 157 2 color M.-C. Shih, R. Shenoy, and K. Rose. A two-dimensional hidden Markov model with spatially-adaptive states with application of optical flow. ICIP 2014 submission.
[91] WLIF-Flow 700 2 color Z. Tu, R. Veltkamp, N. van der Aa, and C. Van Gemeren. Weighted local intensity fusion method for variational optical flow estimation. Submitted to TIP 2014.
[92] FMOF 215 2 color N. Jith, A. Ramakanth, and V. Babu. Optical flow estimation using approximate nearest neighbor field fusion. ICASSP 2014.
[93] TriFlow 150 2 color TriFlow. Optical flow with geometric occlusion estimation and fusion of multiple frames. ECCV 2014 submission 914.
[94] ComponentFusion 6.5 2 color Anonymous. Fast optical flow by component fusion. ECCV 2014 submission 941.
[95] AggregFlow 1642 2 color D. Fortun, P. Bouthemy, and C. Kervrann. Aggregation of local parametric candidates and exemplar-based occlusion handling for optical flow. Preprint arXiv:1407.5759.
[96] 2bit-BM-tele 124 2 gray R. Xu and D. Taubman. Robust dense block-based motion estimation using a two-bit transform on a Laplacian pyramid. ICIP 2013.
[97] HCIC-L 330 2 color Anonymous. Globally-optimal image correspondence using a hierarchical graphical model. NIPS 2014 submission 114.
[98] TF+OM 600 2 color R. Kennedy and C. Taylor. Optical flow with geometric occlusion estimation and fusion of multiple frames. EMMCVPR 2015.
[99] PH-Flow 800 2 color J. Yang and H. Li. Dense, accurate optical flow estimation with piecewise parametric model. CVPR 2015.
[100] EpicFlow 16 2 color J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. EpicFlow: edge-preserving interpolation of correspondences for optical flow. CVPR 2015.
[101] NNF-EAC 380 2 color Anonymous. Variational method for joint optical flow estimation and edge-aware image restoration. CVPR 2015 submission 2336.
[102] Heeger++ 6600 5 gray Anonymous. A context aware biologically inspired algorithm for optical flow (updated results). CVPR 2015 submission 2238.
[103] HBM-GC 330 2 color A. Zheng and Y. Yuan. Motion estimation via hierarchical block matching and graph cut. Submitted to ICIP 2015.
[104] FFV1MT 358 5 gray F. Solari, M. Chessa, N. Medathati, and P. Kornprobst. What can we expect from a V1-MT feedforward architecture for optical flow estimation? Submitted to Signal Processing: Image Communication 2015.
[105] ROF-ND 4 2 color S. Ali, C. Daul, E. Galbrun, and W. Blondel. Illumination invariant large displacement optical flow using robust neighbourhood descriptors. Submitted to CVIU 2015.
[106] DeepFlow2 16 2 color J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. Deep convolutional matching. Submitted to IJCV, 2015.
[107] HAST 2667 2 color Anonymous. Highly accurate optical flow estimation on superpixel tree. ICCV 2015 submission 2221.
[108] FlowFields 15 2 color C. Bailer, B. Taetz, and D. Stricker. Flow Fields: Dense unregularized correspondence fields for highly accurate large displacement optical flow estimation. ICCV 2015.
[109] SVFilterOh 1.56 2 color Anonymous. Fast estimation of large displacement optical flow using PatchMatch and dominant motion patterns. CVPR 2016 submission 1788.
[110] FlowNetS+ft+v 0.5 2 color Anonymous. Learning optical flow with convolutional neural networks. ICCV 2015 submission 235.
[111] CombBMOF 51 2 color M. Brüggemann, R. Kays, P. Springer, and O. Erdler. Combined block-matching and adaptive differential motion estimation in a hierarchical multi-scale framework. ICGIP 2014. (Method improved since publication.)
[112] PMMST 182 2 color F. Zhang, S. Xu, and X. Zhang. High accuracy correspondence field estimation via MST based patch matching. Submitted to TIP 2015.
[113] DF-Auto 70 2 color N. Monzon, A. Salgado, and J. Sanchez. Regularization strategies for discontinuity-preserving optical flow methods. Submitted to TIP 2015.
[114] CPM-Flow 3 2 color Anonymous. Efficient coarse-to-fine PatchMatch for large displacement optical flow. CVPR 2016 submission 241.
[115] CNN-flow-warp+ref 1.4 3 color D. Teney and M. Hebert. Learning to extract motion from videos in convolutional neural networks. ArXiv 1601.07532, 2016.
[116] Steered-L1 804 2 color Anonymous. Optical flow estimation via steered-L1 norm. Submitted to WSCG 2016.
[117] StereoOF-V1MT 343 2 gray Anonymous. Visual features for action-oriented tasks: a cortical-like model for disparity and optic flow computation. BMVC 2016 submission 132.
[118] PGM-C 5 2 color Y. Li. Pyramidal gradient matching for optical flow estimation. Submitted to PAMI 2016.
[119] RNLOD-Flow 1040 2 gray C. Zhang, Z. Chen, M. Wang, M. Li, and S. Jiang. Robust non-local TV-L1 optical flow estimation with occlusion detection. IEEE TIP 26(8):4055-4067, 2017.
[120] FlowNet2 0.091 2 color Anonymous. FlowNet 2.0: Evolution of optical flow estimation with deep networks. CVPR 2017 submission 900.
[121] S2F-IF 20 2 color Anonymous. S2F-IF: Slow-to-fast interpolator flow. CVPR 2017 submission 765.
[122] BriefMatch 0.068 2 gray G. Eilertsen, P.-E. Forssen, and J. Unger. Dense binary feature matching for real-time optical flow estimation. SCIA 2017 submission 62.
[123] OAR-Flow 60 2 color Anonymous. Order-adaptive regularisation for variational optical flow: global, local and in between. SSVM 2017 submission 20.
[124] AdaConv-v1 2.8 2 color Simon Niklaus, Long Mai, and Feng Liu. (Interpolation results only.) Video frame interpolation via adaptive convolution. CVPR 2017.
[125] SepConv-v1 0.2 2 color Simon Niklaus, Long Mai, and Feng Liu. (Interpolation results only.) Video frame interpolation via adaptive separable convolution. ICCV 2017.
[126] ProbFlowFields 37 2 color A. Wannenwetsch, M. Keuper, and S. Roth. ProbFlow: joint optical flow and uncertainty estimation. ICCV 2017.
[127] UnFlow 0.12 2 color Anonymous. UnFlow: Unsupervised learning of optical flow with a bidirectional census loss. Submitted to AAAI 2018.
[128] FlowFields+ 10.5 2 color C. Bailer, B. Taetz, and D. Stricker. Flow fields: Dense correspondence fields for highly accurate large displacement optical flow estimation. Submitted to PAMI 2017.
[129] IIOF-NLDP 150 2 color D.-H. Trinh, W. Blondel, and C. Daul. A general form of illumination-invariant descriptors in variational optical flow estimation. ICIP 2017.
[130] SuperSlomo 0.5 2 color Anonymous. (Interpolation results only.) Super SloMo: High quality estimation of multiple intermediate frames for video interpolation. CVPR 2018 submission 325.
[131] EPMNet 0.061 2 color Anonymous. EPM-convolution multilayer-network for optical flow estimation. ICME 2018 submission 1119.
[132] OFRF 90 2 color Tan Khoa Mai, Michele Gouiffes, and Samia Bouchafa. Optical flow refinement using iterative propagation under colour, proximity and flow reliability constraints. IET Image Processing 2020.
[133] 3DFlow 328 2 color J. Chen, Z. Cai, J. Lai, and X. Xie. A filtering based framework for optical flow estimation. IEEE TCSVT 2018.
[134] CtxSyn 0.07 2 color Simon Niklaus and Feng Liu. (Interpolation results only.) Context-aware synthesis for video frame interpolation. CVPR 2018.
[135] DMF_ROB 10 2 color ROB 2018 baseline submission, based on: P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013.
[136] JOF 657 2 gray C. Zhang, L. Ge, Z. Chen, M. Li, W. Liu, and H. Chen. Refined TV-L1 optical flow estimation using joint filtering. Submitted to IEEE TMM, 2018.
[137] AVG_FLOW_ROB N/A 2 N/A Average flow field of ROB 2018 training set.
[138] LiteFlowNet 0.06 2 color T.-W. Hui, X. Tang, and C. C. Loy. LiteFlowNet: A lightweight convolutional neural network for optical flow estimation. CVPR 2018.
[139] AugFNG_ROB 0.10 all color Anonymous. FusionNet and AugmentedFlowNet: Selective proxy ground truth for training on unlabeled images. ECCV 2018 submission 2834.
[140] ResPWCR_ROB 0.2 2 color Anonymous. Learning optical flow with residual connections. ROB 2018 submission.
[141] FF++_ROB 17.43 2 color R. Schuster, C. Bailer, O. Wasenmueller, D. Stricker. FlowFields++: Accurate optical flow correspondences meet robust interpolation. ICIP 2018. Submitted to ROB 2018.
[142] ProFlow_ROB 76 3 color Anonymous. ProFlow: Learning to predict optical flow. BMVC 2018 submission 277.
[143] PWC-Net_RVC 0.069 2 color D. Sun, X. Yang, M.-Y. Liu, and J. Kautz. PWC-Net: CNNs for optical flow using pyramid, warping, and cost volume. CVPR 2018. Also RVC 2020 baseline submission.
[144] WOLF_ROB 0.02 2 color Anonymous. Reversed deep neural network for optical flow. ROB 2018 submission.
[145] LFNet_ROB 0.068 2 color Anonymous. Learning a flow network. ROB 2018 submission.
[146] WRT 9 2 color L. Mei, J. Lai, X. Xie, J. Zhu, and J. Chen. Illumination-invariance optical flow estimation using weighted regularization transform. Submitted to IEEE TCSVT 2018.
[147] EAI-Flow 2.1 2 color Anonymous. Hierarchical coherency sensitive hashing and interpolation with RANSAC for large displacement optical flow. CVIU 2018 submission 17-678.
[148] ContinualFlow_ROB 0.5 all color Michal Neoral, Jan Sochman, and Jiri Matas. Continual occlusions and optical flow estimation. ACCV 2018.
[149] CyclicGen 0.088 2 color Anonymous. (Interpolation results only.) Deep video frame interpolation using cyclic frame generation. AAAI 2019 submission 323.
[150] TOF-M 0.393 2 color Tianfan Xue, Baian Chen, Jiajun Wu, Donglai Wei, and William Freeman. Video enhancement with task-oriented flow. arXiv 1711.09078, 2017.
[151] MPRN 0.32 4 color Anonymous. (Interpolation results only.) Multi-frame pyramid refinement network for video frame interpolation. CVPR 2019 submission 1361.
[152] DAIN 0.13 2 color Wenbo Bao, Wei-Sheng Lai, Chao Ma, Xiaoyun Zhang, Zhiyong Gao, and Ming-Hsuan Yang. (Interpolation results only.) DAIN: Depth-aware video frame interpolation. CVPR 2019.
[153] FRUCnet 0.65 2 color Van Thang Nguyen, Kyujoong Lee, and Hyuk-Jae Lee. (Interpolation results only.) A stacked deep MEMC network for frame rate up conversion and its application to HEVC. Submitted to IEEE TCSVT 2019.
[154] OFRI 0.31 2 color Anonymous. (Interpolation results only.) Efficient video frame interpolation via optical flow refinement. CVPR 2019 submission 6743.
[155] CompactFlow_ROB 0.05 2 color Anonymous. CompactFlow: spatially shiftable window revisited. CVPR 2019 submission 1387.
[156] SegFlow 3.2 2 color Jun Chen, Zemin Cai, Jianhuang Lai, and Xiaohua Xie. Efficient segmentation-based PatchMatch for large displacement optical flow estimation. IEEE TCSVT 2018.
[157] HCFN 0.18 2 color Anonymous. Practical coarse-to-fine optical flow with deep networks. ICCV 2019 submission 116.
[158] FGME 0.23 2 color Bo Yan, Weimin Tan, Chuming Lin, and Liquan Shen. (Interpolation results only.) Fine-grained motion estimation for video frame interpolation. IEEE Transactions on Broadcasting, 2020.
[159] MS-PFT 0.44 2 color Xianhang Cheng and Zhenzhong Chen. (Interpolation results only.) A multi-scale position feature transform network for video frame interpolation. IEEE TCSVT 2020.
[160] MEMC-Net+ 0.12 2 color Wenbo Bao, Wei-Sheng Lai, Xiaoyun Zhang, Zhiyong Gao, and Ming-Hsuan Yang. (Interpolation results only.) MEMC-Net: Motion estimation and motion compensation driven neural network for video interpolation and enhancement. Submitted to PAMI 2018.
[161] ADC 0.01 2 color Anonymous. (Interpolation results only.) Learning spatial transform for video frame interpolation. ICCV 2019 submission 5424.
[162] DSepConv 0.3 2 color Xianhang Cheng and Zhenzhong Chen. (Interpolation results only.) Video frame interpolation via deformable separable convolution. AAAI 2020.
[163] MAF-net 0.3 2 color Mengshun Hu, Jing Xiao, Liang Liao, Zheng Wang, Chia-Wen Lin, Mi Wang, and Shinichi Satoh. Capturing small, fast-moving objects: Frame interpolation via recurrent motion enhancement. IEEE TCSVT 2021.
[164] STAR-Net 0.049 2 color Anonymous. (Interpolation results only.) Space-time-aware multiple resolution for video enhancement. CPVR 2020 submission 430.
[165] AdaCoF 0.03 2 color Hyeongmin Lee, Taeoh Kim, Tae-young Chung, Daehyun Pak, Yuseok Ban, and Sangyoun Lee. (Interpolation results only.) AdaCoF: Adaptive collaboration of flows for video frame interpolation. CVPR 2020. Code available.
[166] TC-GAN 0.13 2 color Anonymous. (Interpolation results only.) A temporal and contextual generative adversarial network for video frame interpolation. CVPR 2020 submission 111.
[167] FeFlow 0.52 2 color Shurui Gui, Chaoyue Wang, Qihua Chen, and Dacheng Tao. (Interpolation results only.) FeatureFlow: Robust video interpolation via structure-to-texture generation. CVPR 2020. Code available.
[168] DAI 0.23 2 color Anonymous. (Interpolation results only.) Deep animation inbetweening. CVPR 2020 submission 6404.
[169] SoftSplat 0.1 2 color Simon Niklaus and Feng Liu. (Interpolation results only.) Softmax splatting for video frame interpolation. CVPR 2020.
[170] STSR 5.35 2 color Anonymous. (Interpolation results only.) Spatial and temporal video super-resolution with a frequency domain loss. ECCV 2020 submission 2340.
[171] BMBC 0.77 2 color Anonymous. (Interpolation results only.) BMBC: Bilateral motion estimation with bilateral cost volume for video interpolation. ECCV 2020 submission 2095.
[172] GDCN 1.0 2 color Anonymous. (Interpolation results only.) Video interpolation via generalized deformable convolution. ECCV 2020 submission 4347.
[173] EDSC 0.56 2 color Xianhang Cheng and Zhenzhong Chen. (Interpolation results only.) Multiple video frame interpolation via enhanced deformable separable convolution. Submitted to PAMI 2020.
[174] CoT-AMFlow 0.04 2 color Anonymous. CoT-AMFlow: Adaptive modulation network with co-teaching strategy for unsupervised optical flow estimation. CoRL 2020 submission 36.
[175] TVL1_RVC 11.6 2 color RVC 2020 baseline submission by Toby Weed, based on: Javier Sanchez, Enric Meinhardt-Llopis, and Gabriele Facciolo. TV-L1 optical flow estimation. IPOL 3:137-150, 2013.
[176] H+S_RVC 44.7 2 color RVC 2020 baseline submission by Toby Weed, based on: Enric Meinhardt-Llopis, Javier Sanchez, and Daniel Kondermann. Horn-Schunck optical flow with a multi-scale strategy. IPOL 3:151–172, 2013.
[177] PRAFlow_RVC 0.34 2 color Zhexiong Wan, Yuxin Mao, and Yuchao Dai. Pyramid recurrent all-pairs flow. RVC 2020 submission.
[178] VCN_RVC 0.84 2 color Gengshan Yang and Deva Ramanan. Volumetric correspondence networks for optical flow. NeurIPS 2019. RVC 2020 submission.
[179] RAFT-TF_RVC 1.51 2 color Deqing Sun, Charles Herrmann, Varun Jampani, Mike Krainin, Forrester Cole, Austin Stone, Rico Jonschkowski, Ramin Zabih, William Freeman, and Ce Liu. A TensorFlow implementation of RAFT (Zachary Teed and Jia Deng. RAFT: Recurrent all-pairs field transforms for optical flow. ECCV 2020.) RVC 2020 submission.
[180] IRR-PWC_RVC 0.18 2 color Junhwa Hur and Stefan Roth. Iterative residual refinement for joint optical flow and occlusion estimation. CVPR 2019. RVC 2020 submission.
[181] C-RAFT_RVC 0.60 2 color Henrique Morimitsu and Xiangyang Ji. Classification RAFT. RVC 2020 submission.
[182] LSM_FLOW_RVC 0.2 2 color Chengzhou Tang, Lu Yuan, and Ping Tan. LSM: Learning subspace minimization for low-level vision. CVPR 2020. RVC 2020 submission.
[183] MV_VFI 0.23 2 color Zhenfang Wang, Yanjiang Wang, and Baodi Liu. (Interpolation results only.) Multi-view based video interpolation algorithm. ICASSP 2021 submission.
[184] DistillNet 0.12 2 color Anonymous. (Interpolation results only.) A teacher-student optical-flow distillation framework for video frame interpolation. CVPR 2021 submission 7534.
[185] SepConv++ 0.1 2 color Simon Niklaus, Long Mai, and Oliver Wang. (Interpolation results only.) Revisiting adaptive convolutions for video frame interpolation. WACV 2021.
[186] EAFI 0.18 2 color Anonymous. (Interpolation results only.) Error-aware spatial ensembles for video frame interpolation. ICCV 2021 submission 8020.
[187] UnDAF 0.04 2 color Anonymous. UnDAF: A general unsupervised domain adaptation framework for disparity, optical flow or scene flow estimation. CVPR 2021 submission 236.
[188] FLAVR 0.029 all color Anonymous. (Interpolation results only.) FLAVR frame interpolation. NeurIPS 2021 submission 1300.
[189] PBOFVI 150 2 color Zemin Cai, Jianhuang Lai, Xiaoxin Liao, and Xucong Chen. Physics-based optical flow under varying illumination. Submitted to IEEE TCSVT 2021.
[190] SoftsplatAug 0.17 2 color Anonymous. (Interpolation results only.) Transformation data augmentation for sports video frame interpolation. ICCV 2021 submission 3245.
* The "time" column lists the reported runtime in seconds on the "Urban" sequence. Note that these runtimes are not normalized by processor speed or type.