Optical flow evaluation results Statistics:     Average   SD   R0.5   R1.0   R2.0   A50   A75   A95  
Error type:   endpoint   angle   interpolation   normalized interpolation  
Show images: below table   above table        
R0.5
endpoint
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
OFLAF [77]11.2 1.67 4 9.54 5 0.81 12 4.12 7 23.1 5 2.26 16 3.43 1 11.8 1 1.47 8 2.31 10 15.3 6 0.67 9 18.1 2 27.2 3 8.68 5 12.6 35 27.0 11 6.93 29 0.78 17 1.08 29 3.37 24 11.6 9 25.9 3 16.2 17
MDP-Flow2 [68]13.0 1.76 8 9.93 9 0.86 14 3.26 2 20.6 2 1.44 3 4.04 3 13.6 3 1.26 6 3.09 28 21.8 32 0.88 20 22.4 16 32.2 12 14.3 16 9.15 12 23.6 3 5.83 10 2.18 41 0.32 16 4.78 38 10.8 5 26.3 4 15.0 10
NNF-Local [87]13.6 1.75 7 9.66 6 0.87 15 4.56 14 27.6 16 2.46 20 4.52 4 15.6 7 2.18 18 2.57 17 18.4 17 0.86 17 18.8 5 29.2 5 8.22 3 9.37 15 24.2 6 5.22 7 0.95 20 2.02 63 1.90 13 10.6 4 31.8 25 8.21 2
NN-field [71]16.0 2.01 20 11.0 21 1.10 29 5.74 27 30.7 32 3.21 28 4.57 5 15.7 8 2.22 20 1.81 3 15.7 8 0.54 6 19.0 6 29.4 6 8.42 4 10.5 21 20.3 1 3.83 1 1.43 26 2.03 64 3.72 26 10.1 2 31.1 20 6.81 1
PMMST [114]18.0 1.43 2 8.08 2 0.38 1 6.05 33 28.6 20 4.40 42 6.13 18 19.1 17 4.02 41 2.21 6 11.7 2 1.09 29 21.2 9 30.5 9 13.2 12 9.59 17 23.8 4 5.71 9 2.28 44 1.95 58 4.36 32 11.8 10 29.1 8 13.1 7
WLIF-Flow [93]21.7 1.80 10 9.97 10 0.94 17 6.24 36 28.7 22 4.52 44 5.74 13 18.5 12 3.13 27 3.03 27 19.9 24 1.01 26 21.9 10 32.0 11 14.1 14 12.4 32 27.2 12 6.44 13 3.40 65 0.07 7 8.69 63 11.4 7 26.8 5 15.7 14
ComponentFusion [96]22.0 1.73 6 9.92 8 0.77 9 3.75 5 22.3 4 2.27 17 5.02 9 17.1 10 2.21 19 2.87 21 19.3 22 0.93 21 24.1 20 35.1 23 18.6 37 12.4 32 39.0 72 8.29 55 2.41 45 0.13 14 4.73 37 11.9 12 30.0 16 15.5 13
Correlation Flow [75]22.7 1.96 17 10.9 19 0.66 6 4.21 9 25.5 12 1.35 2 6.69 30 20.7 25 0.94 2 1.68 2 13.3 3 0.48 5 25.4 29 36.9 30 16.3 26 13.5 52 32.5 35 7.88 49 2.82 54 1.63 45 10.8 71 11.3 6 29.7 11 9.89 5
NNF-EAC [103]24.3 1.95 16 10.5 15 1.10 29 4.29 11 25.1 10 2.20 13 5.06 10 16.6 9 1.81 12 3.94 54 23.4 41 1.63 54 22.5 17 32.5 15 14.7 18 11.3 25 25.8 8 6.81 23 2.71 51 2.13 66 4.63 36 12.4 15 30.2 18 16.5 18
Layers++ [37]25.0 1.85 13 10.1 11 1.03 24 6.26 37 27.9 19 4.58 46 4.88 8 15.2 5 3.65 35 2.26 8 14.4 4 0.68 10 17.8 1 25.4 1 12.2 8 13.3 45 28.3 16 6.81 23 4.53 74 2.71 83 7.34 54 13.2 23 29.7 11 19.2 42
LME [70]25.4 1.89 15 10.6 16 0.75 7 3.53 3 21.3 3 1.83 8 7.04 42 18.6 15 8.24 73 3.10 30 23.0 39 0.86 17 24.8 26 35.5 25 17.9 34 10.1 19 30.1 26 6.46 14 2.67 50 1.51 41 5.54 42 12.8 17 30.9 19 17.7 29
RNLOD-Flow [121]27.5 1.68 5 9.49 4 0.75 7 5.76 28 30.6 31 3.18 26 6.58 27 21.1 29 2.92 24 2.61 18 17.5 14 0.74 12 22.0 11 32.8 16 14.9 21 11.5 27 28.0 15 7.37 37 5.53 88 4.17 97 15.2 94 11.8 10 27.7 7 15.1 11
nLayers [57]27.5 1.40 1 7.64 1 0.64 4 8.47 69 30.5 30 7.07 80 6.80 36 20.0 21 5.79 65 2.13 5 14.7 5 0.78 15 18.3 3 26.0 2 12.2 8 12.9 40 25.6 7 6.84 25 1.93 37 2.24 70 3.35 23 14.5 35 32.0 28 20.9 51
HAST [109]28.8 1.57 3 8.65 3 0.60 2 5.82 31 24.9 9 3.84 34 3.85 2 12.5 2 0.41 1 2.82 20 18.8 19 0.58 7 18.7 4 27.9 4 8.00 1 15.9 87 32.6 36 9.69 78 9.89 114 4.87 106 36.9 122 8.55 1 22.0 1 9.33 3
FC-2Layers-FF [74]29.5 1.81 11 9.71 7 1.07 27 6.99 45 33.9 46 4.71 47 4.71 6 15.0 4 3.63 34 2.67 19 18.3 16 0.87 19 20.6 8 29.7 7 14.5 17 13.3 45 28.4 17 7.26 34 5.67 92 1.82 53 14.9 90 12.9 20 29.4 9 18.4 36
SVFilterOh [111]30.5 2.18 30 11.4 25 0.78 10 5.94 32 29.2 24 3.13 24 4.85 7 15.2 5 2.01 15 2.35 11 17.4 12 0.63 8 20.4 7 30.1 8 8.12 2 14.7 79 29.5 22 8.51 62 10.3 115 3.98 95 31.3 113 12.0 13 26.9 6 13.4 8
TC/T-Flow [76]30.9 2.19 32 11.8 32 1.21 38 5.00 17 29.4 25 1.89 10 5.57 12 18.5 12 1.28 7 3.63 43 23.7 44 1.24 36 24.1 20 35.4 24 15.2 23 7.02 2 25.8 8 5.43 8 3.79 69 2.13 66 19.3 103 14.6 38 36.2 41 17.9 31
AGIF+OF [85]31.5 1.99 19 10.9 19 1.16 34 8.96 74 37.8 66 6.95 75 6.31 21 20.4 22 3.86 39 2.89 22 19.1 20 0.93 21 22.1 12 32.4 13 14.8 19 12.9 40 28.6 19 6.79 22 3.48 68 0.08 12 8.67 62 12.8 17 29.9 14 17.5 25
3DFlow [135]31.7 1.97 18 10.7 17 0.63 3 5.21 18 29.9 28 1.88 9 5.17 11 17.4 11 1.02 3 1.00 1 9.03 1 0.18 1 22.3 15 32.8 16 13.2 12 19.1 104 42.2 91 12.7 96 11.7 121 1.61 43 31.8 116 11.5 8 29.9 14 9.34 4
TC-Flow [46]32.0 2.04 21 11.0 21 0.94 17 3.69 4 23.4 6 1.68 5 5.96 17 19.9 20 1.06 4 3.73 46 23.6 43 1.24 36 25.7 33 38.0 36 14.8 19 8.99 11 34.6 45 5.03 6 2.82 54 2.47 76 15.9 98 16.0 46 38.1 48 22.0 55
HBM-GC [105]32.5 2.10 25 10.8 18 0.94 17 7.69 59 31.9 39 6.10 68 6.21 20 18.5 12 3.82 37 2.22 7 15.5 7 0.78 15 22.1 12 31.8 10 14.2 15 13.3 45 24.1 5 7.49 41 8.91 111 1.87 54 21.4 107 12.7 16 31.1 20 16.7 21
ALD-Flow [66]34.2 2.22 34 11.8 32 1.02 23 4.33 12 24.7 7 2.04 12 6.35 23 20.9 26 1.56 9 3.67 44 24.0 48 1.10 30 25.8 34 37.5 34 15.8 25 8.24 5 32.7 38 4.68 3 3.06 59 2.62 82 16.6 100 15.6 45 39.3 50 19.8 46
IIOF-NLDP [131]34.3 2.63 53 13.9 52 1.09 28 7.53 56 38.0 69 3.28 29 6.98 41 22.1 38 1.85 13 2.28 9 15.7 8 0.95 24 25.2 27 37.6 35 12.5 10 13.4 50 35.9 54 8.72 65 0.78 17 0.39 20 3.57 25 15.4 44 37.7 45 15.1 11
IROF++ [58]36.5 2.18 30 11.5 28 1.33 45 7.91 60 36.5 61 5.96 65 6.71 32 21.7 35 4.85 58 3.62 42 22.8 35 1.63 54 24.2 23 34.9 22 17.1 31 13.3 45 33.4 41 7.82 47 0.55 14 1.09 30 1.01 9 12.8 17 32.9 32 16.7 21
ProbFlowFields [128]36.8 3.29 72 17.1 75 1.88 86 6.54 39 29.8 26 5.50 58 7.69 49 23.8 47 6.90 68 3.09 28 17.1 11 1.28 38 27.8 41 39.5 42 19.2 43 6.56 1 27.2 12 5.00 5 0.09 3 0.03 3 0.86 7 17.1 53 39.4 51 17.5 25
FESL [72]37.2 1.86 14 10.2 12 0.99 20 10.4 89 39.3 78 7.94 88 6.79 35 21.2 31 4.35 48 2.39 12 16.2 10 0.76 14 24.2 23 34.7 20 19.2 43 12.6 35 27.7 14 7.10 33 3.35 63 2.20 69 8.03 58 14.5 35 31.2 22 17.6 28
FMOF [94]37.8 2.09 23 11.2 24 1.44 59 9.20 76 37.9 67 6.96 76 6.14 19 19.5 18 3.82 37 2.52 15 17.4 12 0.73 11 24.1 20 34.8 21 17.7 33 13.5 52 28.4 17 6.99 30 4.64 77 1.63 45 14.5 86 14.5 35 32.7 30 17.2 24
Classic+CPF [83]38.3 2.16 28 11.6 29 1.42 57 8.04 62 36.6 62 5.76 62 6.70 31 21.8 37 3.86 39 3.02 26 21.2 30 1.14 32 23.6 19 34.2 19 17.0 30 13.4 50 29.1 20 7.03 32 4.58 76 1.50 40 13.6 83 12.9 20 29.7 11 17.5 25
MLDP_OF [89]38.7 2.46 46 13.6 49 1.14 33 4.43 13 27.8 18 1.99 11 6.80 36 21.7 35 1.89 14 2.52 15 19.6 23 0.75 13 28.2 42 40.4 45 19.2 43 11.8 29 29.6 23 9.40 74 8.30 109 2.15 68 31.7 115 13.3 24 33.4 35 15.9 15
PH-Flow [101]39.2 2.30 39 12.2 36 1.45 61 7.61 57 35.2 51 5.81 63 5.92 16 19.0 16 4.67 56 3.52 38 22.1 33 1.49 48 23.4 18 33.9 18 16.3 26 12.4 32 29.4 21 6.87 26 4.88 81 2.25 72 14.0 84 12.2 14 30.1 17 16.6 19
Efficient-NL [60]40.5 2.41 44 11.8 32 1.55 72 8.28 65 35.4 54 5.90 64 6.72 33 20.9 26 3.78 36 2.95 25 19.1 20 1.20 34 22.1 12 32.4 13 15.3 24 14.6 77 31.0 30 8.05 53 3.32 61 2.40 75 7.02 50 13.6 28 29.6 10 18.2 33
PMF [73]40.8 2.30 39 12.8 42 1.01 21 5.64 26 31.4 36 2.51 21 6.83 38 22.5 43 1.72 11 3.26 31 21.1 28 0.94 23 24.3 25 36.7 29 9.56 6 14.4 73 40.0 78 8.40 59 7.45 106 8.62 124 24.8 108 10.4 3 25.6 2 12.7 6
Aniso-Texture [82]41.5 1.84 12 10.4 14 0.81 12 4.68 15 24.7 7 3.74 32 8.07 53 23.8 47 3.23 30 2.10 4 18.4 17 0.46 3 29.0 53 41.0 50 22.9 58 12.7 37 32.7 38 8.37 58 6.63 101 5.87 115 14.8 89 16.4 47 35.2 39 24.2 65
OAR-Flow [125]41.9 2.96 65 15.1 65 1.58 74 6.72 42 31.3 35 4.10 39 9.12 61 27.1 58 4.72 57 3.73 46 23.9 46 1.17 33 28.3 44 40.8 47 17.6 32 8.30 6 33.5 43 4.69 4 0.25 7 0.17 15 2.56 19 17.5 57 40.5 53 22.6 58
Sparse-NonSparse [56]42.7 2.11 26 11.7 30 1.39 51 7.47 55 35.1 50 5.75 61 6.48 25 21.2 31 4.34 46 3.52 38 22.9 36 1.38 43 26.1 37 37.3 33 19.6 50 13.5 52 31.2 32 7.42 38 5.02 85 1.18 34 13.5 82 13.5 26 31.7 23 18.8 40
Ramp [62]43.5 2.21 33 12.1 35 1.45 61 7.45 54 35.5 56 5.63 60 6.33 22 20.6 24 4.23 43 3.43 35 22.5 34 1.38 43 25.8 34 37.0 31 19.3 47 13.5 52 30.3 27 7.45 39 4.89 82 1.97 60 15.1 93 13.1 22 31.9 26 18.0 32
NL-TV-NCC [25]43.6 2.25 36 11.7 30 0.78 10 6.94 44 35.5 56 2.54 22 6.48 25 21.1 29 1.08 5 2.48 14 21.5 31 0.46 3 31.5 67 46.7 84 16.7 28 17.3 91 41.0 87 10.2 81 4.41 73 0.10 13 10.1 68 18.4 58 43.2 59 18.2 33
LSM [39]43.9 2.24 35 12.4 38 1.39 51 7.37 52 35.4 54 5.47 57 6.61 28 21.6 34 4.24 44 3.46 37 23.8 45 1.30 40 25.8 34 37.0 31 19.3 47 13.7 58 32.1 34 7.36 36 5.34 87 1.11 32 14.5 86 13.7 31 32.3 29 18.2 33
OFH [38]44.1 2.82 60 13.9 52 2.01 87 4.91 16 28.6 20 2.33 18 8.97 60 28.0 63 2.88 23 4.00 57 27.0 58 1.43 46 31.0 64 44.5 70 22.7 56 10.5 21 41.8 89 6.88 27 0.03 1 0.02 1 0.27 3 17.1 53 46.4 72 19.2 42
Sparse Occlusion [54]44.8 2.14 27 11.4 25 1.03 24 7.32 50 31.0 33 6.11 69 7.29 46 22.9 45 2.48 22 3.29 32 22.9 36 1.03 27 26.9 39 39.4 40 14.9 21 13.0 42 33.3 40 7.63 44 7.80 107 8.76 127 12.2 78 14.8 40 34.8 38 16.9 23
Classic+NL [31]44.8 2.08 22 11.4 25 1.35 47 7.33 51 35.9 59 5.30 54 6.47 24 21.0 28 4.53 53 3.59 40 22.9 36 1.49 48 25.4 29 36.3 27 19.4 49 13.8 61 31.1 31 7.57 42 5.78 94 2.32 74 15.0 91 13.5 26 31.9 26 18.7 39
IROF-TV [53]47.3 2.51 49 13.5 47 1.41 55 8.08 63 38.7 75 6.19 71 6.97 40 22.3 40 4.43 50 4.23 60 28.8 66 1.72 59 28.3 44 39.9 43 22.6 55 13.8 61 40.0 78 8.01 51 0.23 6 0.39 20 0.67 5 13.7 31 33.6 36 17.8 30
RFlow [90]47.6 2.42 45 13.5 47 1.16 34 3.98 6 25.2 11 1.81 7 8.89 59 27.5 60 3.13 27 3.45 36 26.8 56 1.60 52 30.5 62 43.6 61 24.5 66 14.2 68 38.1 66 7.94 50 3.36 64 1.65 48 8.47 61 16.9 52 42.3 55 20.5 50
TV-L1-MCT [64]47.8 2.09 23 11.1 23 1.39 51 9.67 78 39.0 77 7.35 81 7.11 44 22.3 40 4.27 45 2.94 24 20.7 27 1.13 31 28.4 46 39.4 40 25.8 73 16.0 89 35.0 48 9.27 71 1.27 24 0.57 23 7.24 52 14.8 40 33.2 34 23.3 62
COFM [59]48.3 2.51 49 13.9 52 1.42 57 5.54 22 28.9 23 3.40 30 7.79 51 23.6 46 4.53 53 2.90 23 18.2 15 0.95 24 29.1 54 40.8 47 25.4 70 15.5 85 30.7 29 9.39 73 4.69 78 1.23 35 15.4 97 16.8 51 37.1 42 21.8 54
S2D-Matching [84]48.5 2.39 42 13.0 43 1.52 69 7.22 48 35.6 58 5.13 52 7.63 48 24.4 50 4.38 49 3.30 33 20.5 26 1.35 42 25.3 28 36.0 26 19.2 43 14.1 65 31.5 33 7.77 46 6.21 98 2.24 70 16.9 101 13.6 28 31.7 23 19.3 44
Complementary OF [21]50.2 2.69 57 15.0 63 1.33 45 4.19 8 26.9 14 1.70 6 7.15 45 24.4 50 3.09 26 3.86 52 26.1 52 1.41 45 33.2 79 44.6 72 29.7 89 13.3 45 40.7 86 7.00 31 0.74 16 0.03 3 7.12 51 23.9 86 53.1 92 33.9 93
Occlusion-TV-L1 [63]50.3 2.47 47 13.1 44 1.12 31 6.32 38 32.2 41 4.45 43 9.86 66 28.3 64 4.44 51 3.86 52 26.7 55 1.43 46 31.9 73 44.3 67 27.1 79 11.3 25 35.3 52 10.4 84 0.47 13 1.16 33 0.67 5 19.8 65 46.6 74 22.9 60
ACK-Prior [27]50.6 2.16 28 12.4 38 0.64 4 4.26 10 25.9 13 1.33 1 5.91 15 20.4 22 1.67 10 2.39 12 20.4 25 0.33 2 30.0 58 41.1 51 24.4 65 19.2 105 40.3 83 12.2 95 14.4 125 6.30 118 40.9 125 21.0 70 43.6 61 27.5 78
MDP-Flow [26]50.8 2.33 41 13.4 46 1.20 36 5.61 25 26.9 14 4.88 49 6.76 34 22.6 44 5.72 64 4.13 58 29.5 71 1.92 63 28.7 49 40.8 47 23.2 61 12.8 39 36.7 58 8.04 52 2.54 47 2.96 85 4.43 34 19.4 64 44.6 65 26.0 73
CostFilter [40]50.8 2.65 54 14.9 61 1.01 21 5.51 21 31.6 37 2.23 15 7.39 47 24.1 49 3.06 25 3.82 50 26.1 52 1.08 28 25.4 29 38.9 39 10.2 7 15.1 82 42.7 93 8.52 63 8.99 112 10.3 129 29.5 112 14.4 34 37.2 43 16.1 16
2DHMM-SAS [92]52.6 2.28 38 12.3 37 1.46 63 8.45 68 38.1 70 6.02 67 8.34 55 24.4 50 5.21 60 3.73 46 23.4 41 1.62 53 25.5 32 36.6 28 18.8 38 14.5 74 33.4 41 8.46 61 5.07 86 2.05 65 15.3 95 13.3 24 32.9 32 18.5 38
SimpleFlow [49]53.1 2.39 42 12.6 41 1.60 76 9.03 75 38.3 71 7.38 82 8.52 57 25.7 54 5.41 61 4.36 65 25.5 51 2.48 71 26.8 38 38.0 36 21.6 52 14.0 64 29.7 24 7.65 45 2.77 53 1.97 60 6.48 47 14.3 33 32.8 31 19.7 45
Steered-L1 [118]54.0 1.78 9 10.2 12 0.92 16 2.76 1 19.0 1 1.44 3 5.78 14 19.7 19 2.10 16 3.99 56 27.5 61 1.53 51 31.3 66 43.3 59 27.6 81 14.6 77 39.2 74 9.88 79 14.6 126 5.70 113 47.1 126 22.4 77 48.1 77 29.3 83
AggregFlow [97]55.7 3.49 80 17.6 79 1.74 78 10.4 89 42.0 89 6.99 77 11.4 76 30.6 69 9.73 81 3.75 49 21.1 28 1.52 50 28.9 52 41.8 55 18.2 35 7.46 3 22.8 2 4.30 2 1.95 38 2.54 78 4.24 30 20.5 67 42.7 58 25.8 71
TF+OM [100]56.0 2.89 64 14.7 59 1.35 47 5.44 20 27.6 16 3.94 35 10.2 67 26.3 55 12.8 91 3.61 41 24.6 50 1.28 38 29.8 57 40.5 46 25.7 71 12.7 37 34.9 47 6.11 11 5.62 91 4.89 107 14.0 84 21.5 72 46.5 73 23.8 64
EPPM w/o HM [88]58.2 3.53 82 16.6 71 1.44 59 5.80 29 35.3 53 2.22 14 8.01 52 26.3 55 2.45 21 4.38 66 28.0 62 1.77 61 27.0 40 40.0 44 13.0 11 18.6 98 44.4 103 10.8 87 10.5 117 2.30 73 37.7 123 13.6 28 35.6 40 13.9 9
DeepFlow2 [108]58.4 3.18 70 16.9 74 1.48 65 6.68 41 33.7 45 4.15 40 10.7 71 31.1 70 7.69 71 5.96 83 31.1 79 3.33 82 28.5 47 41.3 52 19.1 40 9.45 16 34.7 46 6.60 17 1.60 30 1.66 50 10.4 69 23.5 81 47.9 76 30.2 86
CombBMOF [113]58.8 2.67 55 14.4 56 1.05 26 7.17 46 33.9 46 4.00 36 6.89 39 21.4 33 4.18 42 5.20 76 28.8 66 3.04 80 28.2 42 41.7 54 18.5 36 21.8 109 39.5 75 20.1 113 4.02 70 4.61 104 6.08 44 17.1 53 37.5 44 24.5 67
Adaptive [20]59.0 2.49 48 13.2 45 1.13 32 7.17 46 34.5 49 4.97 50 10.2 67 28.7 66 4.34 46 4.31 64 28.2 63 1.66 56 34.5 86 48.1 90 28.2 83 14.3 71 36.1 55 8.24 54 4.04 71 4.49 103 7.32 53 14.7 39 34.7 37 18.9 41
ComplOF-FED-GPU [35]61.6 2.87 63 15.6 67 1.35 47 6.14 34 33.6 44 3.15 25 8.26 54 27.4 59 3.30 31 4.29 61 28.2 63 1.71 58 33.1 78 47.9 89 24.1 64 14.7 79 45.7 106 9.19 70 3.33 62 1.48 39 15.0 91 18.8 61 48.4 79 22.0 55
TCOF [69]62.1 3.05 67 15.4 66 1.75 79 8.12 64 38.6 73 5.20 53 13.8 87 34.5 83 13.2 93 8.75 101 29.0 68 8.90 106 33.8 82 47.3 86 23.1 60 9.33 14 25.9 10 6.64 19 2.59 48 1.95 58 6.38 46 15.3 43 39.1 49 18.4 36
ROF-ND [107]63.0 3.29 72 14.7 59 1.29 42 7.42 53 31.8 38 2.42 19 7.10 43 22.1 38 2.13 17 3.68 45 23.2 40 2.87 78 31.1 65 43.7 62 23.6 63 19.3 107 38.5 68 10.7 86 8.90 110 2.99 86 24.8 108 21.9 74 48.6 80 22.7 59
BriefMatch [124]63.3 2.27 37 12.5 40 1.23 40 6.23 35 32.1 40 3.54 31 6.68 29 22.3 40 3.16 29 3.32 34 23.9 46 1.23 35 30.8 63 43.3 59 26.8 76 23.9 112 43.6 97 21.0 115 11.0 120 4.44 102 33.1 119 21.5 72 44.8 66 29.2 82
DeepFlow [86]63.5 3.36 75 17.3 76 1.54 71 7.91 60 35.2 51 5.35 55 12.1 80 33.0 78 10.5 87 6.24 85 32.1 81 3.55 84 28.8 50 42.3 56 18.8 38 9.77 18 37.4 62 6.90 28 1.30 25 0.37 17 9.70 67 27.4 96 52.7 88 35.8 95
Classic++ [32]63.7 2.59 52 13.9 52 1.51 68 6.79 43 32.3 42 5.37 56 9.15 62 27.8 62 5.54 62 4.29 61 29.0 68 1.77 61 30.2 60 43.9 63 22.8 57 14.8 81 40.0 78 8.36 57 6.82 102 4.17 97 16.5 99 16.5 48 39.5 52 19.8 46
TV-L1-improved [17]65.0 2.56 51 13.6 49 1.20 36 5.80 29 30.0 29 4.04 37 9.84 65 28.4 65 4.60 55 4.16 59 27.0 58 1.66 56 31.5 67 45.4 78 23.0 59 17.5 92 45.5 105 13.7 102 7.01 104 4.32 101 20.5 105 17.1 53 42.5 57 20.4 49
Bartels [41]66.2 3.26 71 16.7 73 1.37 50 5.33 19 29.8 26 3.18 26 8.40 56 26.9 57 4.45 52 4.40 67 26.9 57 2.16 65 32.7 75 45.4 78 28.4 86 14.3 71 38.1 66 12.9 97 8.20 108 3.82 93 31.3 113 18.4 58 43.7 63 23.3 62
S2F-IF [123]66.3 4.50 96 23.8 101 2.14 92 8.86 71 42.8 93 6.52 72 11.0 72 34.0 82 9.17 76 4.86 70 29.2 70 2.39 69 35.6 92 51.0 103 26.9 77 8.49 8 36.6 57 6.30 12 0.60 15 0.03 3 2.49 18 23.6 82 52.7 88 25.9 72
SIOF [67]66.8 2.67 55 13.6 49 1.23 40 7.65 58 37.9 67 4.78 48 14.2 90 32.9 77 15.4 95 6.36 86 34.7 87 3.84 87 34.0 83 45.8 81 33.2 93 13.5 52 35.7 53 10.5 85 1.99 39 0.99 27 4.21 29 20.5 67 45.6 68 30.7 88
F-TV-L1 [15]68.1 3.34 74 17.3 76 1.80 83 9.99 86 38.6 73 7.03 78 13.2 85 32.6 76 7.82 72 5.85 82 32.9 82 2.91 79 31.5 67 45.0 75 25.2 68 15.1 82 38.7 69 8.99 68 2.19 42 3.29 89 3.03 21 15.1 42 38.0 47 16.6 19
CRTflow [80]69.0 3.53 82 18.6 83 1.79 81 6.54 39 34.0 48 4.08 38 10.5 69 31.6 73 5.02 59 4.95 74 30.6 76 2.31 66 30.1 59 44.2 66 19.1 40 24.2 113 50.1 112 26.0 119 1.80 35 0.92 26 6.63 48 22.7 78 52.1 86 30.0 85
PGM-C [120]69.2 4.80 101 24.9 107 2.34 100 9.79 79 42.4 90 7.86 86 11.3 75 34.5 83 9.49 77 5.28 79 34.6 86 2.54 74 34.5 86 49.1 96 26.5 74 9.26 13 37.2 59 6.72 21 0.42 11 0.07 7 1.85 12 23.7 83 53.0 91 25.6 70
FlowFields [110]70.4 4.67 97 24.4 103 2.22 94 9.80 80 44.3 97 7.67 84 11.8 78 36.4 91 10.1 84 4.90 72 30.5 75 2.63 76 36.4 95 51.6 106 28.9 88 8.76 10 38.7 69 6.48 15 0.85 19 0.03 3 2.71 20 23.3 80 53.7 97 22.3 57
FlowFields+ [130]70.6 4.68 98 24.5 104 2.22 94 9.86 83 44.7 99 7.63 83 12.1 80 37.3 94 10.3 86 4.92 73 30.3 74 2.61 75 36.3 94 51.6 106 28.3 85 8.62 9 38.7 69 6.57 16 0.41 9 0.02 1 1.92 14 23.7 83 53.6 96 25.5 69
TriangleFlow [30]70.9 2.81 59 14.9 61 1.22 39 7.27 49 37.1 64 3.76 33 9.83 64 30.2 68 3.34 32 3.84 51 27.1 60 1.72 59 39.4 108 53.7 110 34.8 98 21.8 109 43.5 95 16.0 105 4.72 80 7.40 121 8.30 60 18.5 60 44.3 64 21.5 53
CPM-Flow [116]71.3 4.79 100 24.9 107 2.32 98 9.83 81 42.4 90 7.89 87 11.2 74 33.9 81 9.50 78 5.25 77 34.3 84 2.50 73 34.7 89 49.3 99 26.7 75 10.3 20 37.5 64 7.62 43 0.42 11 0.07 7 1.82 11 24.5 88 54.2 98 26.8 76
Rannacher [23]71.5 3.03 66 16.1 69 1.59 75 8.35 66 36.9 63 6.87 74 11.1 73 31.8 74 6.71 67 4.88 71 29.7 72 2.34 67 31.7 72 45.9 82 23.3 62 16.8 90 44.0 99 10.3 83 4.89 82 2.57 80 12.1 77 16.7 50 41.9 54 19.9 48
SRR-TVOF-NL [91]71.5 3.16 69 16.2 70 1.49 66 8.87 72 38.5 72 5.57 59 12.3 82 33.4 79 8.53 74 3.96 55 26.6 54 1.34 41 32.8 76 44.6 72 27.2 80 13.8 61 39.0 72 8.34 56 5.55 90 5.38 111 17.8 102 22.0 75 43.3 60 25.2 68
LocallyOriented [52]71.6 4.06 90 20.2 91 1.87 85 12.1 93 47.6 102 8.49 91 15.9 94 39.1 100 11.1 89 5.10 75 28.6 65 2.84 77 34.0 83 47.4 87 25.7 71 11.8 29 32.6 36 7.84 48 1.10 21 1.51 41 6.95 49 20.3 66 46.8 75 23.1 61
EpicFlow [102]71.8 4.80 101 24.9 107 2.33 99 9.90 84 42.9 94 7.95 89 11.8 78 35.7 89 9.56 79 5.26 78 34.4 85 2.49 72 34.6 88 49.2 98 27.0 78 10.8 24 37.5 64 7.33 35 0.41 9 0.07 7 1.80 10 24.1 87 53.5 94 26.4 74
Aniso. Huber-L1 [22]72.0 2.84 62 14.5 57 1.46 63 14.0 95 42.6 92 12.9 94 13.4 86 31.3 71 13.0 92 6.50 87 35.2 89 4.19 90 29.7 56 42.4 57 21.8 54 14.5 74 35.0 48 8.43 60 5.54 89 3.18 88 12.8 80 16.6 49 37.7 45 20.9 51
Dynamic MRF [7]73.6 3.39 76 18.9 86 1.30 43 5.60 24 33.5 43 2.81 23 9.67 63 31.3 71 3.54 33 4.64 69 33.7 83 2.39 69 38.0 101 51.2 104 34.9 99 19.2 105 51.8 115 15.2 104 3.41 66 0.37 17 20.9 106 25.1 90 52.2 87 31.7 90
DPOF [18]76.0 4.03 88 21.8 95 2.11 89 9.50 77 40.4 81 5.97 66 8.88 58 27.5 60 6.05 66 4.29 61 30.8 77 2.08 64 31.5 67 45.1 76 21.6 52 15.9 87 37.3 61 9.53 76 15.3 127 1.61 43 47.3 127 22.1 76 46.3 71 28.5 79
CBF [12]78.2 2.82 60 15.0 63 1.32 44 18.0 100 40.4 81 21.6 103 10.6 70 29.2 67 9.72 80 6.57 88 34.8 88 4.55 92 31.5 67 44.0 65 24.5 66 14.5 74 35.0 48 8.92 67 10.9 119 6.02 116 26.2 111 20.7 69 43.6 61 27.2 77
Brox et al. [5]78.3 3.55 85 18.8 85 1.64 77 10.1 88 39.6 79 8.97 92 11.7 77 33.4 79 8.96 75 6.57 88 36.4 91 3.41 83 38.2 103 47.6 88 45.3 116 13.5 52 42.4 92 9.63 77 0.27 8 0.99 27 0.47 4 31.0 102 56.4 104 43.3 107
Fusion [6]78.5 3.40 77 19.1 87 2.16 93 5.57 23 31.1 34 4.53 45 7.70 50 25.2 53 7.53 70 5.78 81 35.6 90 4.10 89 36.6 96 47.1 85 38.8 105 14.2 68 41.9 90 13.2 98 6.84 103 5.31 109 11.7 75 24.8 89 51.1 85 31.6 89
Local-TV-L1 [65]79.5 4.05 89 19.4 89 2.51 103 17.1 99 43.6 96 15.9 97 19.8 102 37.3 94 23.3 99 9.20 104 43.3 100 6.89 103 28.6 48 41.3 52 20.2 51 14.1 65 35.1 51 8.67 64 1.24 22 0.62 24 3.94 27 33.5 110 57.2 105 49.6 114
CLG-TV [48]80.2 2.80 58 14.6 58 1.41 55 14.0 95 40.7 84 14.1 96 12.7 83 32.0 75 11.0 88 8.13 97 47.7 108 5.99 99 32.0 74 45.2 77 25.2 68 14.1 65 40.1 82 10.9 88 6.45 99 5.82 114 10.4 69 19.0 62 42.4 56 26.6 75
LDOF [28]81.9 4.09 92 20.0 90 2.31 97 9.96 85 41.8 87 7.06 79 14.1 88 37.0 92 10.1 84 8.41 98 43.3 100 4.97 93 34.4 85 46.2 83 32.5 91 12.2 31 41.0 87 8.88 66 1.63 32 2.00 62 5.79 43 29.9 97 56.0 102 38.8 102
p-harmonic [29]81.9 3.47 79 19.1 87 2.29 96 8.40 67 35.9 59 6.80 73 12.8 84 34.6 85 9.84 83 9.04 102 47.6 107 6.72 101 37.1 98 48.7 94 39.6 106 13.1 43 44.0 99 11.2 89 3.43 67 2.50 77 6.33 45 21.2 71 45.2 67 30.5 87
DF-Auto [115]82.1 4.71 99 22.2 96 2.11 89 21.1 103 49.4 104 21.6 103 20.3 103 39.8 102 31.0 105 7.62 94 37.5 93 5.08 95 33.6 80 43.9 63 33.3 94 8.36 7 29.8 25 7.48 40 2.60 49 5.21 108 2.22 15 32.4 105 53.1 92 43.2 106
TriFlow [95]83.8 3.53 82 17.9 80 1.77 80 11.0 92 37.3 65 10.6 93 16.7 97 35.8 90 25.3 101 4.44 68 30.9 78 2.34 67 35.0 91 44.3 67 35.7 100 10.7 23 30.4 28 6.68 20 33.4 130 9.63 128 90.0 132 30.3 100 55.2 101 36.8 98
FlowNetS+ft+v [112]86.0 3.75 87 18.5 82 2.13 91 10.0 87 38.8 76 8.25 90 16.3 95 37.5 97 20.0 96 7.89 95 37.0 92 5.17 96 36.9 97 48.2 91 35.7 100 11.6 28 40.0 78 9.13 69 4.56 75 4.02 96 14.6 88 23.8 85 51.0 83 31.9 91
SuperFlow [81]86.4 3.40 77 16.6 71 1.81 84 15.3 97 41.5 85 15.9 97 17.0 98 35.2 88 27.6 102 10.0 106 43.1 99 8.60 105 36.1 93 44.3 67 46.7 117 13.1 43 39.8 77 11.3 90 2.49 46 4.24 100 4.26 31 30.0 98 54.7 99 40.8 104
OFRF [134]87.5 3.10 68 15.9 68 1.40 54 21.2 104 45.4 100 20.7 102 18.7 101 34.6 85 22.6 98 7.09 90 30.2 73 5.59 97 30.2 60 44.8 74 16.7 28 18.6 98 43.5 95 10.2 81 6.14 97 3.78 92 25.5 110 34.2 111 53.5 94 54.4 119
Second-order prior [8]87.7 3.49 80 18.6 83 1.79 81 9.83 81 40.6 83 7.83 85 14.1 88 39.0 99 9.82 82 6.20 84 31.4 80 3.83 86 34.7 89 49.4 100 27.6 81 18.7 100 52.1 116 11.4 91 9.18 113 3.60 91 20.1 104 19.1 63 48.2 78 24.4 66
Learning Flow [11]87.9 3.56 86 18.2 81 1.56 73 8.71 70 41.5 85 6.17 70 14.5 91 37.8 98 11.8 90 7.92 96 41.1 98 5.02 94 40.9 111 51.7 108 42.4 108 15.4 84 47.2 108 11.4 91 2.73 52 6.19 117 7.64 57 23.0 79 49.9 81 28.9 81
Ad-TV-NDC [36]89.8 10.3 118 20.2 91 18.1 127 38.1 116 53.0 110 43.3 119 28.0 113 45.6 108 35.7 109 20.6 113 48.9 111 23.8 114 29.1 54 42.5 58 19.1 40 13.7 58 36.1 55 9.46 75 2.03 40 1.43 38 4.38 33 41.4 119 65.3 116 57.0 121
CNN-flow-warp+ref [117]90.1 4.85 103 24.6 105 2.62 105 13.2 94 41.8 87 12.9 94 17.7 100 39.6 101 25.0 100 8.67 100 44.8 103 5.78 98 38.1 102 48.2 91 43.5 111 13.7 58 40.4 84 9.32 72 1.80 35 1.29 37 9.16 64 33.2 107 57.7 107 42.9 105
StereoOF-V1MT [119]92.0 4.08 91 23.0 97 1.49 66 10.4 89 53.3 111 4.35 41 16.3 95 49.5 114 5.71 63 7.37 93 48.5 109 4.03 88 46.7 115 62.9 118 42.9 110 21.9 111 64.7 122 17.0 106 1.58 29 1.87 54 9.43 66 33.2 107 66.2 117 36.5 97
BlockOverlap [61]94.3 4.14 95 17.3 76 3.50 108 23.3 105 43.1 95 25.5 107 21.0 104 37.2 93 27.8 103 13.1 107 39.0 96 13.7 109 28.8 50 38.6 38 28.2 83 18.7 100 37.2 59 13.3 99 12.6 123 6.40 120 40.8 124 26.8 94 45.8 69 43.3 107
Shiralkar [42]95.9 4.11 93 23.3 98 1.52 69 8.88 73 44.5 98 5.07 51 14.5 91 41.9 104 6.96 69 7.32 92 44.7 102 4.37 91 38.8 107 55.2 113 33.1 92 26.7 118 60.7 117 18.5 111 10.4 116 3.38 90 32.9 118 26.7 93 61.6 111 29.5 84
SegOF [10]96.0 6.07 111 25.2 110 3.62 110 36.7 114 55.3 112 41.7 117 26.1 108 43.8 106 39.2 112 15.2 109 45.4 104 12.3 107 46.5 114 56.0 114 57.5 121 18.2 97 49.9 111 14.9 103 0.19 4 0.71 25 0.86 7 31.1 103 52.9 90 35.9 96
StereoFlow [44]96.8 28.4 131 55.1 132 37.7 131 81.1 132 92.6 132 77.8 131 65.0 130 82.9 132 51.1 126 69.6 132 90.7 132 65.5 129 52.7 123 67.5 123 44.9 115 8.13 4 33.5 43 6.60 17 0.05 2 0.37 17 0.17 2 32.2 104 54.8 100 40.4 103
HBpMotionGpu [43]97.4 5.00 104 21.6 94 2.81 107 31.1 111 49.5 105 35.0 111 26.3 110 45.3 107 37.1 111 9.18 103 39.3 97 7.65 104 33.7 81 45.6 80 32.2 90 15.7 86 37.4 62 9.89 80 5.71 93 4.19 99 12.5 79 33.4 109 56.3 103 47.8 112
SPSA-learn [13]98.5 5.52 108 25.3 112 4.12 112 25.2 108 50.0 106 26.8 108 25.1 107 45.7 109 36.7 110 19.0 110 54.2 113 20.8 111 38.6 104 48.4 93 44.4 113 17.9 95 45.3 104 17.6 108 1.60 30 0.54 22 5.27 41 39.6 116 57.9 108 53.3 117
2bit-BM-tele [98]99.0 5.17 106 23.4 99 3.54 109 16.3 98 40.3 80 16.7 99 15.2 93 34.6 85 14.2 94 8.49 99 37.6 94 6.75 102 32.8 76 44.5 70 28.6 87 24.3 114 43.9 98 22.5 117 15.6 128 8.72 126 50.0 129 26.2 91 50.8 82 37.5 100
FlowNet2 [122]99.6 7.84 114 30.7 113 2.58 104 41.4 119 65.2 118 44.4 120 29.6 115 48.0 112 46.8 121 5.31 80 24.0 48 3.06 81 47.8 116 64.8 121 36.3 103 17.8 93 44.3 101 13.4 100 2.93 57 8.71 125 5.22 39 30.2 99 61.7 112 28.8 80
IAOF2 [51]100.4 4.13 94 20.4 93 2.02 88 18.0 100 45.9 101 18.0 100 17.1 99 37.3 94 21.4 97 46.4 123 57.8 115 56.1 126 37.4 100 48.8 95 35.9 102 25.5 115 42.7 93 20.4 114 6.62 100 3.04 87 15.3 95 26.8 94 51.0 83 37.9 101
EPMNet [133]100.5 7.68 113 33.7 117 2.38 101 39.6 117 72.0 127 40.0 116 27.9 112 46.4 110 44.6 119 7.12 91 38.7 95 3.78 85 47.8 116 64.8 121 36.3 103 17.8 93 44.3 101 13.4 100 1.56 28 5.60 112 2.27 16 33.0 106 70.0 122 32.3 92
Filter Flow [19]101.1 5.13 105 23.5 100 2.40 102 20.5 102 51.3 107 19.6 101 23.3 106 42.6 105 35.3 108 27.2 116 48.8 110 28.3 116 39.4 108 49.1 96 44.6 114 17.9 95 40.5 85 11.8 94 7.39 105 7.67 123 11.5 74 26.6 92 46.0 70 33.9 93
Black & Anandan [4]101.2 5.52 108 25.2 110 4.71 114 24.4 107 52.8 108 24.4 106 26.8 111 48.3 113 34.4 107 20.9 114 60.4 116 22.4 113 38.7 106 49.7 101 42.8 109 18.9 102 49.4 109 17.1 107 1.78 34 2.57 80 3.30 22 36.0 112 57.3 106 49.5 113
Modified CLG [34]103.3 7.42 112 31.9 115 5.50 115 31.7 112 52.9 109 37.6 114 28.4 114 50.8 115 40.4 114 20.3 112 60.5 117 21.3 112 39.5 110 51.2 104 42.2 107 14.2 68 45.8 107 11.5 93 3.24 60 1.70 52 9.31 65 40.3 117 65.1 115 54.7 120
IAOF [50]104.5 5.70 110 24.0 102 3.65 111 30.0 110 48.7 103 33.9 110 26.2 109 47.8 111 29.5 104 28.0 117 51.3 112 32.9 117 37.3 99 50.2 102 34.4 97 26.2 116 50.9 114 18.0 110 5.85 95 1.63 45 11.7 75 36.3 113 59.4 110 51.9 115
GraphCuts [14]106.3 5.45 107 24.7 106 2.64 106 24.3 106 55.8 114 21.9 105 21.4 105 40.8 103 32.4 106 9.25 105 46.4 105 6.31 100 38.6 104 51.7 108 33.8 95 28.8 121 39.7 76 18.7 112 12.1 122 2.87 84 35.1 121 38.5 114 58.4 109 53.9 118
2D-CLG [1]107.0 14.0 122 40.7 123 8.09 120 45.8 121 59.5 115 54.5 124 36.8 121 60.4 122 47.3 122 48.9 125 75.1 126 54.2 125 44.9 112 54.8 111 52.5 118 19.0 103 50.3 113 17.8 109 1.26 23 0.07 7 4.43 34 47.4 124 71.2 124 59.9 125
GroupFlow [9]107.4 8.95 117 33.2 116 7.07 117 43.6 120 70.7 123 45.5 121 32.7 117 59.8 121 42.4 117 13.2 108 46.6 106 12.4 108 51.1 120 70.0 125 34.2 96 30.8 123 62.8 119 33.8 124 1.54 27 2.56 79 4.14 28 39.0 115 67.0 119 47.4 111
UnFlow [129]108.5 22.1 129 43.6 126 7.44 119 52.6 125 73.8 128 54.3 123 47.7 127 74.9 130 47.5 123 26.4 115 68.7 121 24.7 115 64.5 128 75.5 129 65.6 128 28.5 120 67.0 126 27.1 121 0.19 4 1.87 54 0.05 1 30.4 101 62.4 113 36.8 98
Nguyen [33]109.5 8.19 115 31.4 114 4.40 113 54.9 126 55.7 113 70.2 127 33.6 119 54.6 116 43.3 118 43.5 122 60.9 118 50.5 123 45.1 113 54.9 112 54.2 119 21.1 108 49.4 109 21.0 115 2.92 56 1.87 54 7.39 55 44.7 122 66.2 117 58.5 123
Horn & Schunck [3]110.8 8.56 116 35.5 118 7.11 118 29.4 109 65.4 119 28.1 109 33.4 118 64.4 124 41.2 116 30.6 118 67.2 120 33.6 118 49.1 119 61.3 115 55.5 120 26.4 117 64.7 122 26.1 120 3.02 58 3.95 94 2.44 17 48.8 125 75.0 126 58.8 124
SILK [79]112.8 10.7 119 35.7 119 14.6 124 37.7 115 64.2 116 42.5 118 32.3 116 59.3 119 40.6 115 19.9 111 56.8 114 20.4 110 51.6 122 62.6 117 59.6 124 27.2 119 63.0 120 23.2 118 4.92 84 1.68 51 13.1 81 46.9 123 71.6 125 61.7 127
TI-DOFE [24]116.3 21.2 127 43.7 127 34.5 130 64.6 130 71.9 126 76.5 130 47.1 126 75.6 131 53.7 127 57.3 127 76.4 127 65.6 130 51.5 121 63.9 119 60.0 125 30.4 122 65.8 125 33.2 122 2.24 43 1.65 48 5.22 39 59.1 129 82.1 131 71.2 130
Periodicity [78]116.7 11.0 120 41.5 124 5.85 116 35.3 113 64.5 117 36.8 113 51.0 128 55.5 117 61.7 129 49.6 126 81.4 129 48.4 122 66.0 130 83.6 132 59.0 122 46.1 128 76.4 130 43.0 128 1.67 33 5.33 110 8.13 59 48.8 125 78.9 128 57.5 122
Heeger++ [104]117.5 24.4 130 45.8 128 9.72 122 47.8 123 85.9 131 37.8 115 66.2 131 69.8 127 75.2 130 59.7 129 88.6 131 56.9 127 66.6 131 80.3 131 62.4 127 65.6 132 87.3 132 67.1 132 4.14 72 1.26 36 7.39 55 41.9 120 68.8 120 43.4 109
SLK [47]120.3 17.8 125 50.1 131 21.7 128 62.2 129 77.8 130 74.7 129 40.4 124 72.7 129 48.1 124 66.2 130 73.9 124 76.1 132 60.9 126 71.2 126 72.9 132 33.1 124 68.3 128 35.4 126 5.99 96 1.09 30 11.4 73 60.5 131 81.9 130 75.0 131
FFV1MT [106]120.8 22.0 128 42.2 125 9.20 121 41.0 118 76.9 129 36.1 112 66.5 132 71.9 128 79.2 131 58.5 128 87.7 130 57.1 128 64.8 129 76.5 130 70.3 131 64.8 131 85.8 131 65.3 131 4.70 79 4.86 105 11.3 72 41.9 120 68.8 120 43.4 109
Adaptive flow [45]121.9 16.0 123 36.3 120 17.5 126 57.9 127 67.3 120 64.2 126 38.7 123 59.2 118 48.8 125 39.9 120 69.2 122 44.2 121 49.0 118 62.0 116 43.6 112 39.1 127 62.2 118 34.3 125 34.2 131 23.4 131 82.8 130 40.6 118 64.9 114 51.9 115
FOLKI [16]123.2 13.4 121 45.9 129 16.0 125 48.5 124 67.4 121 57.8 125 36.6 120 66.2 125 40.3 113 32.2 119 66.9 119 37.2 119 52.9 124 64.2 120 60.1 126 34.7 125 65.7 124 40.2 127 12.9 124 7.56 122 33.8 120 55.3 128 78.0 127 70.7 129
PGAM+LK [55]125.2 17.6 124 48.4 130 26.7 129 45.8 121 71.8 125 49.9 122 38.3 122 67.6 126 44.6 119 42.8 121 79.5 128 42.6 120 56.5 125 69.9 124 59.0 122 37.8 126 70.5 129 33.6 123 23.5 129 15.0 130 48.8 128 54.6 127 80.9 129 61.1 126
Pyramid LK [2]125.7 19.8 126 36.7 121 40.3 132 61.8 128 68.8 122 74.6 128 43.5 125 63.7 123 58.2 128 46.9 124 72.7 123 54.1 124 61.5 127 74.5 128 65.8 129 51.3 129 64.1 121 50.1 129 10.8 118 6.30 118 31.9 117 68.2 132 84.9 132 84.8 132
HCIC-L [99]128.5 29.6 132 37.7 122 11.4 123 77.3 131 71.7 124 90.9 132 63.0 129 59.4 120 83.6 132 66.9 131 74.8 125 69.8 131 68.1 132 74.1 127 66.1 130 54.4 130 67.4 127 52.5 130 58.9 132 43.5 132 89.4 131 59.4 130 70.0 122 67.4 128
AdaConv-v1 [126]133.0 82.5 133 78.4 133 94.0 133 98.6 133 99.3 133 97.9 133 99.9 133 99.9 133 99.9 133 97.4 133 96.9 133 99.7 133 100.0 133 99.9 133 99.8 133 93.4 133 95.5 133 93.4 133 86.5 133 85.7 133 99.4 133 99.9 133 99.9 133 99.9 133
SepConv-v1 [127]133.0 82.5 133 78.4 133 94.0 133 98.6 133 99.3 133 97.9 133 99.9 133 99.9 133 99.9 133 97.4 133 96.9 133 99.7 133 100.0 133 99.9 133 99.8 133 93.4 133 95.5 133 93.4 133 86.5 133 85.7 133 99.4 133 99.9 133 99.9 133 99.9 133
SuperSlomo [132]133.0 82.5 133 78.4 133 94.0 133 98.6 133 99.3 133 97.9 133 99.9 133 99.9 133 99.9 133 97.4 133 96.9 133 99.7 133 100.0 133 99.9 133 99.8 133 93.4 133 95.5 133 93.4 133 86.5 133 85.7 133 99.4 133 99.9 133 99.9 133 99.9 133
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 T. Arici. Energy minimization based motion estimation using adaptive smoothness priors. Submitted to IEEE TIP 2011.
[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 D. Nguyen. Enhancing the sharpness of flow field using image-driven functions with occlusion-aware filter. Submitted to TIP 2011.
[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 A. Ayvaci, M. Raptis, and S. Soatto. Sparse occlusion detection with optical flow. Submitted to IJCV 2011.
[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 L. Chen, J. Wang, and Y. Wu. Decomposing and regularizing sparse/non-sparse components for motion field estimation. Submitted to PAMI 2013.
[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 M. Santoro, G. AlRegib, and Y. Altunbasak. Motion estimation using block overlap minimization. Submitted to 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 W. Dong, G. Shi, X. Hu, and Y. Ma. Nonlocal sparse and low-rank regularization for optical flow estimation. Submitted to IEEE TIP 2013.
[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] Correlation Flow 290 2 color M. Drulea and S. Nedevschi. Motion estimation using the correlation transform. TIP 2013. Matlab code.
[76] TC/T-Flow 341 5 color M. Stoll, S. Volz, and A. Bruhn. Joint trilateral filtering for multiframe optical flow. ICIP 2013.
[77] OFLAF 1530 2 color T. Kim, H. Lee, and K. Lee. Optical flow via locally adaptive fusion of complementary data costs. ICCV 2013.
[78] Periodicity 8000 4 color G. Khachaturov, S. Gonzalez-Brambila, and J. Gonzalez-Trejo. Periodicity-based computation of optical flow. Submitted to Computacion y Sistemas (CyS) 2013.
[79] SILK 572 2 gray P. Zille, C. Xu, T. Corpetti, L. Shao. Observation models based on scale interactions for optical flow estimation. Submitted to IEEE TIP.
[80] 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.
[81] SuperFlow 178 2 color Anonymous. Superpixel based optical flow estimation. ICCV 2013 submission 507.
[82] Aniso-Texture 300 2 color Anonymous. Texture information-based optical flow estimation using an incremental multi-resolution approach. ITC-CSCC 2013 submission 267.
[83] Classic+CPF 640 2 gray Z. Tu, R. Veltkamp, and N. van der Aa. A combined post-filtering method to improve accuracy of variational optical flow estimation. Submitted to Pattern Recognition 2013.
[84] S2D-Matching 1200 2 color Anonymous. Locally affine sparse-to-dense matching for motion and occlusion estimation. ICCV 2013 submission 1479.
[85] AGIF+OF 438 2 gray Z. Tu, R. Poppe, and R. Veltkamp. Adaptive guided image filter to warped interpolation image for variational optical flow computation. Submitted to Signal Processing 2015.
[86] DeepFlow 13 2 color P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013.
[87] NNF-Local 673 2 color Z. Chen, H. Jin, Z. Lin, S. Cohen, and Y. Wu. Large displacement optical flow with nearest neighbor field. Submitted to PAMI 2014.
[88] 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.
[89] 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.
[90] 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.
[91] 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.
[92] 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.
[93] 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.
[94] FMOF 215 2 color N. Jith, A. Ramakanth, and V. Babu. Optical flow estimation using approximate nearest neighbor field fusion. ICASSP 2014.
[95] TriFlow 150 2 color TriFlow. Optical flow with geometric occlusion estimation and fusion of multiple frames. ECCV 2014 submission 914.
[96] ComponentFusion 6.5 2 color Anonymous. Fast optical flow by component fusion. ECCV 2014 submission 941.
[97] 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.
[98] 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.
[99] HCIC-L 330 2 color Anonymous. Globally-optimal image correspondence using a hierarchical graphical model. NIPS 2014 submission 114.
[100] TF+OM 600 2 color R. Kennedy and C. Taylor. Optical flow with geometric occlusion estimation and fusion of multiple frames. EMMCVPR 2015.
[101] PH-Flow 800 2 color J. Yang and H. Li. Dense, accurate optical flow estimation with piecewise parametric model. CVPR 2015.
[102] EpicFlow 16 2 color J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. EpicFlow: edge-preserving interpolation of correspondences for optical flow. CVPR 2015.
[103] NNF-EAC 380 2 color Anonymous. Variational method for joint optical flow estimation and edge-aware image restoration. CVPR 2015 submission 2336.
[104] Heeger++ 6600 5 gray Anonymous. A context aware biologically inspired algorithm for optical flow (updated results). CVPR 2015 submission 2238.
[105] HBM-GC 330 2 color A. Zheng and Y. Yuan. Motion estimation via hierarchical block matching and graph cut. Submitted to ICIP 2015.
[106] 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.
[107] 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.
[108] DeepFlow2 16 2 color J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. Deep convolutional matching. Submitted to IJCV, 2015.
[109] HAST 2667 2 color Anonymous. Highly accurate optical flow estimation on superpixel tree. ICCV 2015 submission 2221.
[110] 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.
[111] SVFilterOh 1.56 2 color Anonymous. Fast estimation of large displacement optical flow using PatchMatch and dominant motion patterns. CVPR 2016 submission 1788.
[112] FlowNetS+ft+v 0.5 2 color Anonymous. Learning optical flow with convolutional neural networks. ICCV 2015 submission 235.
[113] 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.)
[114] 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.
[115] DF-Auto 70 2 color N. Monzon, A. Salgado, and J. Sanchez. Regularization strategies for discontinuity-preserving optical flow methods. Submitted to TIP 2015.
[116] CPM-Flow 3 2 color Anonymous. Efficient coarse-to-fine PatchMatch for large displacement optical flow. CVPR 2016 submission 241.
[117] 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.
[118] Steered-L1 804 2 color Anonymous. Optical flow estimation via steered-L1 norm. Submitted to WSCG 2016.
[119] 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.
[120] PGM-C 5 2 color Y. Li. Pyramidal gradient matching for optical flow estimation. Submitted to PAMI 2016.
[121] 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. Submitted to TIP 2016.
[122] FlowNet2 0.091 2 color Anonymous. FlowNet 2.0: Evolution of optical flow estimation with deep networks. CVPR 2017 submission 900.
[123] S2F-IF 20 2 color Anonymous. S2F-IF: Slow-to-fast interpolator flow. CVPR 2017 submission 765.
[124] 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.
[125] OAR-Flow 60 2 color Anonymous. Order-adaptive regularisation for variational optical flow: global, local and in between. SSVM 2017 submission 20.
[126] AdaConv-v1 2.8 2 color S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive convolution. CVPR 2017.
[127] SepConv-v1 0.2 2 color S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive separable convolution. ICCV 2017.
[128] ProbFlowFields 37 2 color A. Wannenwetsch, M. Keuper, and S. Roth. ProbFlow: joint optical flow and uncertainty estimation. ICCV 2017.
[129] UnFlow 0.12 2 color Anonymous. UnFlow: Unsupervised learning of optical flow with a bidirectional census loss. Submitted to AAAI 2018.
[130] 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.
[131] 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.
[132] 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.
[133] EPMNet 0.061 2 color Anonymous. EPM-convolution multilayer-network for optical flow estimation. ICME 2018 submission 1119.
[134] OFRF 90 2 color T. Mai, M. Gouiffes, and S. Bouchafa. Optical Flow refinement using iterative propagation under color, proximity and flow reliability constraints. Submitted to Signal, Image and Video Processing 2017.
[135] 3DFlow 328 2 color J. Chen, Z. Cai, J. Lai, and X. Xie. A filtering based framework for optical flow estimation. IEEE TCSVT 2018.
* 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.