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]12.8 1.67 4 9.54 5 0.81 13 4.12 7 23.1 5 2.26 16 3.43 1 11.8 1 1.47 8 2.31 11 15.3 7 0.67 10 18.1 2 27.2 3 8.68 5 12.6 38 27.0 11 6.93 30 0.78 26 1.08 39 3.37 33 11.6 9 25.9 3 16.2 20
MDP-Flow2 [68]14.7 1.76 8 9.93 9 0.86 15 3.26 2 20.6 2 1.44 3 4.04 3 13.6 3 1.26 6 3.09 30 21.8 35 0.88 22 22.4 17 32.2 13 14.3 17 9.15 13 23.6 3 5.83 11 2.18 52 0.32 19 4.78 48 10.8 5 26.3 4 15.0 12
NNF-Local [87]15.2 1.75 7 9.66 6 0.87 16 4.56 14 27.6 16 2.46 20 4.52 4 15.6 7 2.18 18 2.57 19 18.4 19 0.86 19 18.8 5 29.2 5 8.22 3 9.37 16 24.2 6 5.22 8 0.95 29 2.02 76 1.90 19 10.6 4 31.8 26 8.21 2
NN-field [71]17.8 2.01 20 11.0 21 1.10 30 5.74 28 30.7 33 3.21 29 4.57 5 15.7 8 2.22 20 1.81 4 15.7 9 0.54 7 19.0 6 29.4 6 8.42 4 10.5 22 20.3 1 3.83 1 1.43 36 2.03 77 3.72 35 10.1 2 31.1 21 6.81 1
PMMST [114]20.0 1.43 2 8.08 2 0.38 1 6.05 34 28.6 20 4.40 43 6.13 19 19.1 18 4.02 43 2.21 7 11.7 2 1.09 32 21.2 9 30.5 9 13.2 12 9.59 18 23.8 4 5.71 10 2.28 55 1.95 71 4.36 42 11.8 10 29.1 8 13.1 9
WLIF-Flow [93]23.5 1.80 10 9.97 10 0.94 18 6.24 37 28.7 22 4.52 45 5.74 13 18.5 13 3.13 28 3.03 29 19.9 26 1.01 29 21.9 10 32.0 12 14.1 15 12.4 35 27.2 12 6.44 14 3.40 76 0.07 9 8.69 74 11.4 7 26.8 5 15.7 16
ComponentFusion [96]24.2 1.73 6 9.92 8 0.77 10 3.75 5 22.3 4 2.27 17 5.02 9 17.1 10 2.21 19 2.87 23 19.3 24 0.93 23 24.1 22 35.1 25 18.6 40 12.4 35 39.0 77 8.29 61 2.41 56 0.13 17 4.73 47 11.9 12 30.0 17 15.5 15
Correlation Flow [75]25.0 1.96 17 10.9 19 0.66 6 4.21 9 25.5 12 1.35 2 6.69 31 20.7 26 0.94 2 1.68 3 13.3 4 0.48 6 25.4 31 36.9 32 16.3 28 13.5 56 32.5 36 7.88 52 2.82 65 1.63 56 10.8 83 11.3 6 29.7 12 9.89 5
NNF-EAC [103]26.8 1.95 16 10.5 15 1.10 30 4.29 11 25.1 10 2.20 13 5.06 10 16.6 9 1.81 12 3.94 58 23.4 45 1.63 58 22.5 18 32.5 16 14.7 19 11.3 27 25.8 8 6.81 24 2.71 62 2.13 79 4.63 46 12.4 16 30.2 19 16.5 21
Layers++ [37]27.5 1.85 13 10.1 11 1.03 25 6.26 38 27.9 19 4.58 47 4.88 8 15.2 5 3.65 37 2.26 9 14.4 5 0.68 12 17.8 1 25.4 1 12.2 8 13.3 49 28.3 16 6.81 24 4.53 87 2.71 97 7.34 65 13.2 25 29.7 12 19.2 46
LME [70]28.0 1.89 15 10.6 16 0.75 8 3.53 3 21.3 3 1.83 8 7.04 43 18.6 16 8.24 77 3.10 32 23.0 42 0.86 19 24.8 28 35.5 27 17.9 37 10.1 20 30.1 27 6.46 15 2.67 61 1.51 52 5.54 53 12.8 18 30.9 20 17.7 32
RNLOD-Flow [121]30.1 1.68 5 9.49 4 0.75 8 5.76 29 30.6 32 3.18 27 6.58 28 21.1 30 2.92 25 2.61 20 17.5 16 0.74 14 22.0 11 32.8 17 14.9 22 11.5 29 28.0 15 7.37 39 5.53 102 4.17 111 15.2 108 11.8 10 27.7 7 15.1 13
nLayers [57]30.2 1.40 1 7.64 1 0.64 4 8.47 72 30.5 31 7.07 85 6.80 37 20.0 22 5.79 68 2.13 6 14.7 6 0.78 17 18.3 3 26.0 2 12.2 8 12.9 44 25.6 7 6.84 26 1.93 48 2.24 83 3.35 32 14.5 37 32.0 29 20.9 56
HAST [109]31.5 1.57 3 8.65 3 0.60 2 5.82 32 24.9 9 3.84 35 3.85 2 12.5 2 0.41 1 2.82 22 18.8 21 0.58 8 18.7 4 27.9 4 8.00 1 15.9 94 32.6 37 9.69 85 9.89 128 4.87 121 36.9 137 8.55 1 22.0 1 9.33 3
FC-2Layers-FF [74]32.3 1.81 11 9.71 7 1.07 28 6.99 46 33.9 47 4.71 48 4.71 6 15.0 4 3.63 36 2.67 21 18.3 18 0.87 21 20.6 8 29.7 7 14.5 18 13.3 49 28.4 17 7.26 36 5.67 106 1.82 66 14.9 104 12.9 22 29.4 9 18.4 40
ProFlow_ROB [146]32.5 2.91 67 15.3 68 1.30 45 5.38 20 30.3 30 3.10 24 8.14 55 26.3 57 3.45 34 3.50 41 23.3 44 0.98 28 29.0 55 42.5 60 17.0 32 8.52 9 33.1 41 4.71 5 0.00 1 0.02 1 0.00 1 12.1 14 36.2 43 12.3 6
SVFilterOh [111]33.3 2.18 31 11.4 26 0.78 11 5.94 33 29.2 24 3.13 25 4.85 7 15.2 5 2.01 15 2.35 12 17.4 14 0.63 9 20.4 7 30.1 8 8.12 2 14.7 84 29.5 23 8.51 68 10.3 129 3.98 109 31.3 128 12.0 13 26.9 6 13.4 10
TC/T-Flow [76]33.8 2.19 33 11.8 33 1.21 40 5.00 17 29.4 25 1.89 10 5.57 12 18.5 13 1.28 7 3.63 47 23.7 48 1.24 39 24.1 22 35.4 26 15.2 25 7.02 2 25.8 8 5.43 9 3.79 81 2.13 79 19.3 117 14.6 40 36.2 43 17.9 35
AGIF+OF [85]33.9 1.99 19 10.9 19 1.16 35 8.96 77 37.8 69 6.95 80 6.31 22 20.4 23 3.86 41 2.89 24 19.1 22 0.93 23 22.1 12 32.4 14 14.8 20 12.9 44 28.6 19 6.79 23 3.48 79 0.08 14 8.67 73 12.8 18 29.9 15 17.5 28
3DFlow [135]34.7 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 16 32.8 17 13.2 12 19.1 116 42.2 97 12.7 106 11.7 136 1.61 54 31.8 131 11.5 8 29.9 15 9.34 4
TC-Flow [46]35.0 2.04 21 11.0 21 0.94 18 3.69 4 23.4 6 1.68 5 5.96 18 19.9 21 1.06 4 3.73 50 23.6 47 1.24 39 25.7 35 38.0 38 14.8 20 8.99 12 34.6 47 5.03 7 2.82 65 2.47 90 15.9 112 16.0 50 38.1 51 22.0 60
HBM-GC [105]35.4 2.10 26 10.8 18 0.94 18 7.69 60 31.9 40 6.10 72 6.21 21 18.5 13 3.82 39 2.22 8 15.5 8 0.78 17 22.1 12 31.8 10 14.2 16 13.3 49 24.1 5 7.49 43 8.91 125 1.87 67 21.4 121 12.7 17 31.1 21 16.7 24
IIOF-NLDP [131]36.8 2.63 54 13.9 54 1.09 29 7.53 57 38.0 72 3.28 30 6.98 42 22.1 39 1.85 13 2.28 10 15.7 9 0.95 26 25.2 29 37.6 37 12.5 10 13.4 54 35.9 56 8.72 71 0.78 26 0.39 24 3.57 34 15.4 47 37.7 48 15.1 13
ALD-Flow [66]37.3 2.22 35 11.8 33 1.02 24 4.33 12 24.7 7 2.04 12 6.35 24 20.9 27 1.56 9 3.67 48 24.0 52 1.10 33 25.8 36 37.5 36 15.8 27 8.24 5 32.7 39 4.68 3 3.06 70 2.62 96 16.6 114 15.6 49 39.3 54 19.8 50
ProbFlowFields [128]38.9 3.29 75 17.1 78 1.88 90 6.54 40 29.8 26 5.50 59 7.69 50 23.8 48 6.90 71 3.09 30 17.1 12 1.28 41 27.8 43 39.5 44 19.2 46 6.56 1 27.2 12 5.00 6 0.09 5 0.03 4 0.86 12 17.1 57 39.4 55 17.5 28
IROF++ [58]39.5 2.18 31 11.5 29 1.33 48 7.91 61 36.5 64 5.96 67 6.71 33 21.7 36 4.85 61 3.62 46 22.8 38 1.63 58 24.2 25 34.9 24 17.1 34 13.3 49 33.4 43 7.82 50 0.55 22 1.09 40 1.01 14 12.8 18 32.9 33 16.7 24
FESL [72]40.5 1.86 14 10.2 12 0.99 21 10.4 95 39.3 81 7.94 93 6.79 36 21.2 32 4.35 50 2.39 14 16.2 11 0.76 16 24.2 25 34.7 22 19.2 46 12.6 38 27.7 14 7.10 35 3.35 74 2.20 82 8.03 69 14.5 37 31.2 23 17.6 31
FMOF [94]41.3 2.09 24 11.2 25 1.44 62 9.20 80 37.9 70 6.96 81 6.14 20 19.5 19 3.82 39 2.52 17 17.4 14 0.73 13 24.1 22 34.8 23 17.7 36 13.5 56 28.4 17 6.99 32 4.64 90 1.63 56 14.5 100 14.5 37 32.7 31 17.2 27
Classic+CPF [83]41.6 2.16 29 11.6 30 1.42 60 8.04 64 36.6 65 5.76 63 6.70 32 21.8 38 3.86 41 3.02 28 21.2 33 1.14 35 23.6 21 34.2 21 17.0 32 13.4 54 29.1 20 7.03 34 4.58 89 1.50 51 13.6 96 12.9 22 29.7 12 17.5 28
MLDP_OF [89]41.8 2.46 47 13.6 51 1.14 34 4.43 13 27.8 18 1.99 11 6.80 37 21.7 36 1.89 14 2.52 17 19.6 25 0.75 15 28.2 44 40.4 47 19.2 46 11.8 31 29.6 24 9.40 80 8.30 123 2.15 81 31.7 130 13.3 26 33.4 36 15.9 17
PH-Flow [101]42.5 2.30 40 12.2 37 1.45 64 7.61 58 35.2 52 5.81 64 5.92 17 19.0 17 4.67 59 3.52 42 22.1 36 1.49 51 23.4 20 33.9 20 16.3 28 12.4 35 29.4 22 6.87 27 4.88 94 2.25 85 14.0 98 12.2 15 30.1 18 16.6 22
Efficient-NL [60]43.6 2.41 45 11.8 33 1.55 75 8.28 68 35.4 55 5.90 65 6.72 34 20.9 27 3.78 38 2.95 27 19.1 22 1.20 37 22.1 12 32.4 14 15.3 26 14.6 82 31.0 31 8.05 56 3.32 72 2.40 89 7.02 61 13.6 30 29.6 10 18.2 37
PMF [73]44.0 2.30 40 12.8 43 1.01 22 5.64 27 31.4 37 2.51 21 6.83 39 22.5 44 1.72 11 3.26 33 21.1 30 0.94 25 24.3 27 36.7 31 9.56 6 14.4 78 40.0 84 8.40 65 7.45 120 8.62 139 24.8 122 10.4 3 25.6 2 12.7 7
OAR-Flow [125]44.8 2.96 68 15.1 67 1.58 77 6.72 43 31.3 36 4.10 40 9.12 63 27.1 61 4.72 60 3.73 50 23.9 50 1.17 36 28.3 46 40.8 49 17.6 35 8.30 6 33.5 45 4.69 4 0.25 13 0.17 18 2.56 27 17.5 61 40.5 57 22.6 63
Aniso-Texture [82]44.9 1.84 12 10.4 14 0.81 13 4.68 15 24.7 7 3.74 33 8.07 54 23.8 48 3.23 31 2.10 5 18.4 19 0.46 3 29.0 55 41.0 52 22.9 62 12.7 41 32.7 39 8.37 64 6.63 115 5.87 130 14.8 103 16.4 51 35.2 40 24.2 71
WRT [150]44.9 2.74 59 13.5 48 0.68 7 10.0 91 40.0 83 5.90 65 9.48 65 24.9 54 2.26 21 1.42 2 12.9 3 0.47 5 22.7 19 33.5 19 13.6 14 16.4 98 36.2 59 9.46 81 4.01 82 0.45 27 10.3 80 15.4 47 35.3 41 13.0 8
Sparse-NonSparse [56]46.0 2.11 27 11.7 31 1.39 54 7.47 56 35.1 51 5.75 62 6.48 26 21.2 32 4.34 48 3.52 42 22.9 39 1.38 46 26.1 39 37.3 35 19.6 53 13.5 56 31.2 33 7.42 40 5.02 98 1.18 44 13.5 95 13.5 28 31.7 24 18.8 44
JOF [140]46.4 2.08 22 11.0 21 1.19 37 7.97 63 35.7 61 6.06 71 5.84 15 18.1 12 4.57 57 3.34 37 21.1 30 1.52 53 22.1 12 31.9 11 15.0 24 14.2 72 29.3 21 8.17 57 10.6 132 4.81 119 30.7 127 12.8 18 29.6 10 17.7 32
OFH [38]46.6 2.82 62 13.9 54 2.01 91 4.91 16 28.6 20 2.33 18 8.97 62 28.0 66 2.88 24 4.00 61 27.0 62 1.43 49 31.0 67 44.5 73 22.7 60 10.5 22 41.8 95 6.88 28 0.03 2 0.02 1 0.27 7 17.1 57 46.4 76 19.2 46
Ramp [62]47.0 2.21 34 12.1 36 1.45 64 7.45 55 35.5 58 5.63 61 6.33 23 20.6 25 4.23 45 3.43 38 22.5 37 1.38 46 25.8 36 37.0 33 19.3 50 13.5 56 30.3 28 7.45 41 4.89 95 1.97 73 15.1 107 13.1 24 31.9 27 18.0 36
NL-TV-NCC [25]47.2 2.25 37 11.7 31 0.78 11 6.94 45 35.5 58 2.54 22 6.48 26 21.1 30 1.08 5 2.48 16 21.5 34 0.46 3 31.5 70 46.7 87 16.7 30 17.3 102 41.0 93 10.2 89 4.41 86 0.10 16 10.1 79 18.4 62 43.2 63 18.2 37
LSM [39]47.2 2.24 36 12.4 39 1.39 54 7.37 53 35.4 55 5.47 58 6.61 29 21.6 35 4.24 46 3.46 40 23.8 49 1.30 43 25.8 36 37.0 33 19.3 50 13.7 62 32.1 35 7.36 38 5.34 101 1.11 42 14.5 100 13.7 33 32.3 30 18.2 37
Sparse Occlusion [54]48.2 2.14 28 11.4 26 1.03 25 7.32 51 31.0 34 6.11 73 7.29 47 22.9 46 2.48 23 3.29 34 22.9 39 1.03 30 26.9 41 39.4 42 14.9 22 13.0 46 33.3 42 7.63 46 7.80 121 8.76 142 12.2 91 14.8 42 34.8 39 16.9 26
Classic+NL [31]48.4 2.08 22 11.4 26 1.35 50 7.33 52 35.9 62 5.30 55 6.47 25 21.0 29 4.53 55 3.59 44 22.9 39 1.49 51 25.4 31 36.3 29 19.4 52 13.8 65 31.1 32 7.57 44 5.78 108 2.32 88 15.0 105 13.5 28 31.9 27 18.7 43
IROF-TV [53]50.3 2.51 50 13.5 48 1.41 58 8.08 65 38.7 78 6.19 76 6.97 41 22.3 41 4.43 52 4.23 64 28.8 70 1.72 63 28.3 46 39.9 45 22.6 59 13.8 65 40.0 84 8.01 54 0.23 11 0.39 24 0.67 10 13.7 33 33.6 37 17.8 34
RFlow [90]51.3 2.42 46 13.5 48 1.16 35 3.98 6 25.2 11 1.81 7 8.89 61 27.5 63 3.13 28 3.45 39 26.8 60 1.60 56 30.5 65 43.6 64 24.5 70 14.2 72 38.1 71 7.94 53 3.36 75 1.65 59 8.47 72 16.9 56 42.3 59 20.5 55
TV-L1-MCT [64]51.4 2.09 24 11.1 24 1.39 54 9.67 82 39.0 80 7.35 86 7.11 45 22.3 41 4.27 47 2.94 26 20.7 29 1.13 34 28.4 48 39.4 42 25.8 77 16.0 96 35.0 50 9.27 77 1.27 34 0.57 29 7.24 63 14.8 42 33.2 35 23.3 68
S2D-Matching [84]52.0 2.39 43 13.0 44 1.52 72 7.22 49 35.6 60 5.13 53 7.63 49 24.4 51 4.38 51 3.30 35 20.5 28 1.35 45 25.3 30 36.0 28 19.2 46 14.1 69 31.5 34 7.77 49 6.21 112 2.24 83 16.9 115 13.6 30 31.7 24 19.3 48
COFM [59]52.0 2.51 50 13.9 54 1.42 60 5.54 23 28.9 23 3.40 31 7.79 52 23.6 47 4.53 55 2.90 25 18.2 17 0.95 26 29.1 57 40.8 49 25.4 74 15.5 91 30.7 30 9.39 79 4.69 91 1.23 45 15.4 111 16.8 55 37.1 45 21.8 59
Occlusion-TV-L1 [63]53.8 2.47 48 13.1 45 1.12 32 6.32 39 32.2 42 4.45 44 9.86 69 28.3 67 4.44 53 3.86 56 26.7 59 1.43 49 31.9 76 44.3 70 27.1 83 11.3 27 35.3 54 10.4 92 0.47 20 1.16 43 0.67 10 19.8 69 46.6 78 22.9 66
Complementary OF [21]54.0 2.69 58 15.0 65 1.33 48 4.19 8 26.9 14 1.70 6 7.15 46 24.4 51 3.09 27 3.86 56 26.1 56 1.41 48 33.2 82 44.6 75 29.7 96 13.3 49 40.7 92 7.00 33 0.74 25 0.03 4 7.12 62 23.9 93 53.1 100 33.9 103
MDP-Flow [26]54.6 2.33 42 13.4 47 1.20 38 5.61 26 26.9 14 4.88 50 6.76 35 22.6 45 5.72 67 4.13 62 29.5 75 1.92 67 28.7 51 40.8 49 23.2 65 12.8 43 36.7 61 8.04 55 2.54 58 2.96 99 4.43 44 19.4 68 44.6 69 26.0 80
CostFilter [40]54.6 2.65 55 14.9 63 1.01 22 5.51 22 31.6 38 2.23 15 7.39 48 24.1 50 3.06 26 3.82 54 26.1 56 1.08 31 25.4 31 38.9 41 10.2 7 15.1 87 42.7 99 8.52 69 8.99 126 10.3 144 29.5 126 14.4 36 37.2 46 16.1 19
ACK-Prior [27]55.0 2.16 29 12.4 39 0.64 4 4.26 10 25.9 13 1.33 1 5.91 16 20.4 23 1.67 10 2.39 14 20.4 27 0.33 2 30.0 61 41.1 53 24.4 69 19.2 117 40.3 89 12.2 104 14.4 140 6.30 133 40.9 140 21.0 76 43.6 65 27.5 85
PWC-Net_ROB [147]56.6 4.13 98 21.0 98 2.11 93 8.97 78 40.1 84 6.18 75 10.7 74 31.8 77 8.37 78 2.38 13 17.1 12 0.67 10 34.8 95 50.7 107 21.3 55 11.8 31 39.2 79 6.97 31 0.15 7 1.43 48 0.07 3 14.9 44 38.2 52 15.9 17
2DHMM-SAS [92]56.7 2.28 39 12.3 38 1.46 66 8.45 71 38.1 73 6.02 70 8.34 57 24.4 51 5.21 63 3.73 50 23.4 45 1.62 57 25.5 34 36.6 30 18.8 41 14.5 79 33.4 43 8.46 67 5.07 99 2.05 78 15.3 109 13.3 26 32.9 33 18.5 42
SimpleFlow [49]57.0 2.39 43 12.6 42 1.60 79 9.03 79 38.3 74 7.38 87 8.52 59 25.7 56 5.41 64 4.36 69 25.5 55 2.48 76 26.8 40 38.0 38 21.6 56 14.0 68 29.7 25 7.65 47 2.77 64 1.97 73 6.48 58 14.3 35 32.8 32 19.7 49
Steered-L1 [118]58.4 1.78 9 10.2 12 0.92 17 2.76 1 19.0 1 1.44 3 5.78 14 19.7 20 2.10 16 3.99 60 27.5 65 1.53 55 31.3 69 43.3 62 27.6 85 14.6 82 39.2 79 9.88 86 14.6 141 5.70 128 47.1 141 22.4 83 48.1 82 29.3 91
AggregFlow [97]60.0 3.49 83 17.6 82 1.74 81 10.4 95 42.0 94 6.99 82 11.4 80 30.6 72 9.73 86 3.75 53 21.1 30 1.52 53 28.9 54 41.8 57 18.2 38 7.46 3 22.8 2 4.30 2 1.95 49 2.54 92 4.24 40 20.5 71 42.7 62 25.8 78
TF+OM [100]60.4 2.89 66 14.7 61 1.35 50 5.44 21 27.6 16 3.94 36 10.2 70 26.3 57 12.8 98 3.61 45 24.6 54 1.28 41 29.8 60 40.5 48 25.7 75 12.7 41 34.9 49 6.11 12 5.62 105 4.89 122 14.0 98 21.5 78 46.5 77 23.8 70
EPPM w/o HM [88]62.7 3.53 85 16.6 74 1.44 62 5.80 30 35.3 54 2.22 14 8.01 53 26.3 57 2.45 22 4.38 70 28.0 66 1.77 65 27.0 42 40.0 46 13.0 11 18.6 110 44.4 109 10.8 95 10.5 131 2.30 87 37.7 138 13.6 30 35.6 42 13.9 11
DeepFlow2 [108]62.8 3.18 73 16.9 77 1.48 68 6.68 42 33.7 46 4.15 41 10.7 74 31.1 73 7.69 74 5.96 90 31.1 84 3.33 88 28.5 49 41.3 54 19.1 43 9.45 17 34.7 48 6.60 18 1.60 41 1.66 62 10.4 81 23.5 88 47.9 81 30.2 94
Adaptive [20]62.9 2.49 49 13.2 46 1.13 33 7.17 47 34.5 50 4.97 51 10.2 70 28.7 69 4.34 48 4.31 68 28.2 67 1.66 60 34.5 90 48.1 94 28.2 87 14.3 76 36.1 57 8.24 58 4.04 84 4.49 117 7.32 64 14.7 41 34.7 38 18.9 45
CombBMOF [113]63.8 2.67 56 14.4 58 1.05 27 7.17 47 33.9 47 4.00 37 6.89 40 21.4 34 4.18 44 5.20 82 28.8 70 3.04 86 28.2 44 41.7 56 18.5 39 21.8 123 39.5 81 20.1 127 4.02 83 4.61 118 6.08 55 17.1 57 37.5 47 24.5 73
ComplOF-FED-GPU [35]66.1 2.87 65 15.6 70 1.35 50 6.14 35 33.6 45 3.15 26 8.26 56 27.4 62 3.30 32 4.29 65 28.2 67 1.71 62 33.1 81 47.9 93 24.1 68 14.7 84 45.7 112 9.19 76 3.33 73 1.48 50 15.0 105 18.8 65 48.4 84 22.0 60
TCOF [69]67.3 3.05 70 15.4 69 1.75 82 8.12 67 38.6 76 5.20 54 13.8 93 34.5 88 13.2 100 8.75 114 29.0 72 8.90 119 33.8 86 47.3 90 23.1 64 9.33 15 25.9 10 6.64 20 2.59 59 1.95 71 6.38 57 15.3 46 39.1 53 18.4 40
ROF-ND [107]67.9 3.29 75 14.7 61 1.29 44 7.42 54 31.8 39 2.42 19 7.10 44 22.1 39 2.13 17 3.68 49 23.2 43 2.87 83 31.1 68 43.7 65 23.6 67 19.3 120 38.5 73 10.7 94 8.90 124 2.99 100 24.8 122 21.9 80 48.6 85 22.7 65
DeepFlow [86]68.2 3.36 78 17.3 79 1.54 74 7.91 61 35.2 52 5.35 56 12.1 85 33.0 82 10.5 93 6.24 92 32.1 87 3.55 91 28.8 52 42.3 58 18.8 41 9.77 19 37.4 66 6.90 29 1.30 35 0.37 21 9.70 78 27.4 106 52.7 96 35.8 106
Classic++ [32]68.3 2.59 53 13.9 54 1.51 71 6.79 44 32.3 43 5.37 57 9.15 64 27.8 65 5.54 65 4.29 65 29.0 72 1.77 65 30.2 63 43.9 66 22.8 61 14.8 86 40.0 84 8.36 63 6.82 116 4.17 111 16.5 113 16.5 52 39.5 56 19.8 50
BriefMatch [124]68.5 2.27 38 12.5 41 1.23 42 6.23 36 32.1 41 3.54 32 6.68 30 22.3 41 3.16 30 3.32 36 23.9 50 1.23 38 30.8 66 43.3 62 26.8 80 23.9 126 43.6 103 21.0 129 11.0 135 4.44 116 33.1 134 21.5 78 44.8 70 29.2 90
TV-L1-improved [17]70.0 2.56 52 13.6 51 1.20 38 5.80 30 30.0 29 4.04 38 9.84 68 28.4 68 4.60 58 4.16 63 27.0 62 1.66 60 31.5 70 45.4 81 23.0 63 17.5 103 45.5 111 13.7 113 7.01 118 4.32 115 20.5 119 17.1 57 42.5 61 20.4 53
S2F-IF [123]71.0 4.50 101 23.8 106 2.14 97 8.86 74 42.8 98 6.52 77 11.0 76 34.0 87 9.17 81 4.86 74 29.2 74 2.39 74 35.6 97 51.0 109 26.9 81 8.49 8 36.6 60 6.30 13 0.60 23 0.03 4 2.49 26 23.6 89 52.7 96 25.9 79
Bartels [41]71.1 3.26 74 16.7 76 1.37 53 5.33 19 29.8 26 3.18 27 8.40 58 26.9 60 4.45 54 4.40 71 26.9 61 2.16 70 32.7 78 45.4 81 28.4 91 14.3 76 38.1 71 12.9 107 8.20 122 3.82 107 31.3 128 18.4 62 43.7 67 23.3 68
SIOF [67]72.0 2.67 56 13.6 51 1.23 42 7.65 59 37.9 70 4.78 49 14.2 96 32.9 81 15.4 102 6.36 93 34.7 94 3.84 94 34.0 87 45.8 84 33.2 101 13.5 56 35.7 55 10.5 93 1.99 50 0.99 37 4.21 39 20.5 71 45.6 72 30.7 97
DMF_ROB [139]73.2 3.59 90 19.4 92 1.80 86 8.09 66 35.4 55 5.96 67 11.6 81 33.7 85 7.90 76 5.84 88 32.4 88 3.42 90 33.7 84 47.0 88 28.7 93 12.6 38 37.5 68 8.25 60 0.50 21 0.35 20 2.46 25 26.5 99 52.6 95 32.2 101
F-TV-L1 [15]73.2 3.34 77 17.3 79 1.80 86 9.99 90 38.6 76 7.03 83 13.2 91 32.6 80 7.82 75 5.85 89 32.9 89 2.91 85 31.5 70 45.0 78 25.2 72 15.1 87 38.7 74 8.99 74 2.19 53 3.29 103 3.03 30 15.1 45 38.0 50 16.6 22
PGM-C [120]74.1 4.80 106 24.9 112 2.34 107 9.79 83 42.4 95 7.86 91 11.3 79 34.5 88 9.49 82 5.28 85 34.6 93 2.54 79 34.5 90 49.1 100 26.5 78 9.26 14 37.2 63 6.72 22 0.42 18 0.07 9 1.85 18 23.7 90 53.0 99 25.6 77
CRTflow [80]74.5 3.53 85 18.6 86 1.79 84 6.54 40 34.0 49 4.08 39 10.5 72 31.6 76 5.02 62 4.95 78 30.6 80 2.31 71 30.1 62 44.2 69 19.1 43 24.2 127 50.1 122 26.0 133 1.80 46 0.92 35 6.63 59 22.7 85 52.1 92 30.0 93
FlowFields [110]75.5 4.67 102 24.4 108 2.22 100 9.80 84 44.3 102 7.67 89 11.8 83 36.4 96 10.1 90 4.90 76 30.5 79 2.63 81 36.4 101 51.6 112 28.9 94 8.76 11 38.7 74 6.48 16 0.85 28 0.03 4 2.71 28 23.3 87 53.7 105 22.3 62
FlowFields+ [130]75.5 4.68 103 24.5 109 2.22 100 9.86 87 44.7 105 7.63 88 12.1 85 37.3 99 10.3 92 4.92 77 30.3 78 2.61 80 36.3 99 51.6 112 28.3 90 8.62 10 38.7 74 6.57 17 0.41 16 0.02 1 1.92 21 23.7 90 53.6 104 25.5 76
CPM-Flow [116]76.2 4.79 105 24.9 112 2.32 105 9.83 85 42.4 95 7.89 92 11.2 78 33.9 86 9.50 83 5.25 83 34.3 91 2.50 78 34.7 93 49.3 103 26.7 79 10.3 21 37.5 68 7.62 45 0.42 18 0.07 9 1.82 17 24.5 95 54.2 106 26.8 83
TriangleFlow [30]76.6 2.81 61 14.9 63 1.22 41 7.27 50 37.1 67 3.76 34 9.83 67 30.2 71 3.34 33 3.84 55 27.1 64 1.72 63 39.4 114 53.7 117 34.8 107 21.8 123 43.5 101 16.0 118 4.72 93 7.40 136 8.30 71 18.5 64 44.3 68 21.5 58
SRR-TVOF-NL [91]76.8 3.16 72 16.2 73 1.49 69 8.87 75 38.5 75 5.57 60 12.3 87 33.4 83 8.53 79 3.96 59 26.6 58 1.34 44 32.8 79 44.6 75 27.2 84 13.8 65 39.0 77 8.34 62 5.55 104 5.38 126 17.8 116 22.0 81 43.3 64 25.2 75
EpicFlow [102]76.8 4.80 106 24.9 112 2.33 106 9.90 88 42.9 99 7.95 94 11.8 83 35.7 94 9.56 84 5.26 84 34.4 92 2.49 77 34.6 92 49.2 102 27.0 82 10.8 25 37.5 68 7.33 37 0.41 16 0.07 9 1.80 16 24.1 94 53.5 102 26.4 81
Rannacher [23]76.8 3.03 69 16.1 72 1.59 78 8.35 69 36.9 66 6.87 79 11.1 77 31.8 77 6.71 70 4.88 75 29.7 76 2.34 72 31.7 75 45.9 85 23.3 66 16.8 99 44.0 105 10.3 91 4.89 95 2.57 94 12.1 90 16.7 54 41.9 58 19.9 52
LocallyOriented [52]76.9 4.06 94 20.2 95 1.87 89 12.1 99 47.6 108 8.49 97 15.9 101 39.1 106 11.1 95 5.10 80 28.6 69 2.84 82 34.0 87 47.4 91 25.7 75 11.8 31 32.6 37 7.84 51 1.10 30 1.51 52 6.95 60 20.3 70 46.8 80 23.1 67
Aniso. Huber-L1 [22]77.8 2.84 64 14.5 59 1.46 66 14.0 102 42.6 97 12.9 101 13.4 92 31.3 74 13.0 99 6.50 94 35.2 96 4.19 97 29.7 59 42.4 59 21.8 58 14.5 79 35.0 50 8.43 66 5.54 103 3.18 102 12.8 93 16.6 53 37.7 48 20.9 56
Dynamic MRF [7]79.5 3.39 79 18.9 89 1.30 45 5.60 25 33.5 44 2.81 23 9.67 66 31.3 74 3.54 35 4.64 73 33.7 90 2.39 74 38.0 107 51.2 110 34.9 108 19.2 117 51.8 126 15.2 116 3.41 77 0.37 21 20.9 120 25.1 97 52.2 93 31.7 99
FF++_ROB [145]80.5 4.95 109 25.8 118 2.27 102 10.3 94 44.5 103 7.95 94 13.1 90 37.6 103 12.4 97 5.12 81 31.4 85 2.87 83 36.3 99 52.0 116 28.2 87 10.9 26 36.9 62 7.65 47 1.46 37 0.96 36 4.19 38 20.8 75 49.0 86 22.6 63
DPOF [18]81.5 4.03 92 21.8 100 2.11 93 9.50 81 40.4 86 5.97 69 8.88 60 27.5 63 6.05 69 4.29 65 30.8 81 2.08 69 31.5 70 45.1 79 21.6 56 15.9 94 37.3 65 9.53 83 15.3 142 1.61 54 47.3 142 22.1 82 46.3 75 28.5 87
CBF [12]84.3 2.82 62 15.0 65 1.32 47 18.0 109 40.4 86 21.6 114 10.6 73 29.2 70 9.72 85 6.57 95 34.8 95 4.55 100 31.5 70 44.0 68 24.5 70 14.5 79 35.0 50 8.92 73 10.9 134 6.02 131 26.2 125 20.7 74 43.6 65 27.2 84
Brox et al. [5]84.5 3.55 88 18.8 88 1.64 80 10.1 93 39.6 82 8.97 98 11.7 82 33.4 83 8.96 80 6.57 95 36.4 98 3.41 89 38.2 109 47.6 92 45.3 129 13.5 56 42.4 98 9.63 84 0.27 14 0.99 37 0.47 9 31.0 113 56.4 112 43.3 120
Fusion [6]84.6 3.40 80 19.1 90 2.16 99 5.57 24 31.1 35 4.53 46 7.70 51 25.2 55 7.53 73 5.78 87 35.6 97 4.10 96 36.6 102 47.1 89 38.8 116 14.2 72 41.9 96 13.2 108 6.84 117 5.31 124 11.7 88 24.8 96 51.1 91 31.6 98
CLG-TV [48]87.0 2.80 60 14.6 60 1.41 58 14.0 102 40.7 89 14.1 105 12.7 88 32.0 79 11.0 94 8.13 107 47.7 120 5.99 112 32.0 77 45.2 80 25.2 72 14.1 69 40.1 88 10.9 96 6.45 113 5.82 129 10.4 81 19.0 66 42.4 60 26.6 82
Local-TV-L1 [65]87.0 4.05 93 19.4 92 2.51 111 17.1 108 43.6 101 15.9 108 19.8 110 37.3 99 23.3 110 9.20 117 43.3 111 6.89 116 28.6 50 41.3 54 20.2 54 14.1 69 35.1 53 8.67 70 1.24 32 0.62 30 3.94 36 33.5 122 57.2 114 49.6 127
LiteFlowNet [142]87.6 6.03 119 30.6 122 2.46 110 12.8 100 48.7 109 9.20 99 14.4 97 42.4 111 9.92 89 5.00 79 30.8 81 2.05 68 43.8 122 61.4 126 32.8 99 16.3 97 47.6 118 8.24 58 0.10 6 0.87 34 0.32 8 22.5 84 52.4 94 24.5 73
p-harmonic [29]89.0 3.47 82 19.1 90 2.29 103 8.40 70 35.9 62 6.80 78 12.8 89 34.6 90 9.84 88 9.04 115 47.6 119 6.72 114 37.1 104 48.7 98 39.6 117 13.1 47 44.0 105 11.2 98 3.43 78 2.50 91 6.33 56 21.2 77 45.2 71 30.5 95
LDOF [28]89.1 4.09 96 20.0 94 2.31 104 9.96 89 41.8 92 7.06 84 14.1 94 37.0 97 10.1 90 8.41 109 43.3 111 4.97 102 34.4 89 46.2 86 32.5 98 12.2 34 41.0 93 8.88 72 1.63 43 2.00 75 5.79 54 29.9 108 56.0 110 38.8 115
DF-Auto [115]89.5 4.71 104 22.2 101 2.11 93 21.1 114 49.4 111 21.6 114 20.3 111 39.8 108 31.0 116 7.62 103 37.5 100 5.08 105 33.6 83 43.9 66 33.3 102 8.36 7 29.8 26 7.48 42 2.60 60 5.21 123 2.22 22 32.4 117 53.1 100 43.2 119
TriFlow [95]90.4 3.53 85 17.9 83 1.77 83 11.0 98 37.3 68 10.6 100 16.7 104 35.8 95 25.3 112 4.44 72 30.9 83 2.34 72 35.0 96 44.3 70 35.7 109 10.7 24 30.4 29 6.68 21 33.4 145 9.63 143 90.0 147 30.3 111 55.2 109 36.8 110
FlowNetS+ft+v [112]93.0 3.75 91 18.5 85 2.13 96 10.0 91 38.8 79 8.25 96 16.3 102 37.5 102 20.0 103 7.89 105 37.0 99 5.17 106 36.9 103 48.2 95 35.7 109 11.6 30 40.0 84 9.13 75 4.56 88 4.02 110 14.6 102 23.8 92 51.0 89 31.9 100
Second-order prior [8]94.3 3.49 83 18.6 86 1.79 84 9.83 85 40.6 88 7.83 90 14.1 94 39.0 105 9.82 87 6.20 91 31.4 85 3.83 93 34.7 93 49.4 104 27.6 85 18.7 112 52.1 127 11.4 100 9.18 127 3.60 105 20.1 118 19.1 67 48.2 83 24.4 72
SuperFlow [81]94.8 3.40 80 16.6 74 1.81 88 15.3 104 41.5 90 15.9 108 17.0 105 35.2 93 27.6 113 10.0 119 43.1 110 8.60 118 36.1 98 44.3 70 46.7 131 13.1 47 39.8 83 11.3 99 2.49 57 4.24 114 4.26 41 30.0 109 54.7 107 40.8 117
Learning Flow [11]95.2 3.56 89 18.2 84 1.56 76 8.71 73 41.5 90 6.17 74 14.5 98 37.8 104 11.8 96 7.92 106 41.1 107 5.02 103 40.9 118 51.7 114 42.4 120 15.4 90 47.2 117 11.4 100 2.73 63 6.19 132 7.64 68 23.0 86 49.9 87 28.9 89
OFRF [134]95.5 3.10 71 15.9 71 1.40 57 21.2 115 45.4 106 20.7 113 18.7 108 34.6 90 22.6 109 7.09 97 30.2 77 5.59 109 30.2 63 44.8 77 16.7 30 18.6 110 43.5 101 10.2 89 6.14 111 3.78 106 25.5 124 34.2 123 53.5 102 54.4 132
CNN-flow-warp+ref [117]98.6 4.85 108 24.6 110 2.62 113 13.2 101 41.8 92 12.9 101 17.7 107 39.6 107 25.0 111 8.67 113 44.8 114 5.78 111 38.1 108 48.2 95 43.5 124 13.7 62 40.4 90 9.32 78 1.80 46 1.29 47 9.16 75 33.2 119 57.7 116 42.9 118
Ad-TV-NDC [36]99.1 10.3 131 20.2 95 18.1 141 38.1 128 53.0 119 43.3 132 28.0 125 45.6 115 35.7 121 20.6 126 48.9 123 23.8 127 29.1 57 42.5 60 19.1 43 13.7 62 36.1 57 9.46 81 2.03 51 1.43 48 4.38 43 41.4 132 65.3 128 57.0 134
ContinualFlow_ROB [152]99.3 8.33 126 33.5 127 3.16 118 25.9 120 54.7 121 25.7 119 24.1 117 50.5 125 32.1 117 7.50 102 42.2 108 4.65 101 48.0 129 67.8 136 28.9 94 21.7 122 56.2 130 19.3 126 0.08 4 0.79 33 0.10 4 20.6 73 46.6 78 20.4 53
WOLF_ROB [148]101.0 5.72 117 29.1 119 2.14 97 18.8 111 56.5 125 14.1 105 22.4 115 48.9 123 20.6 105 8.21 108 40.5 106 5.30 107 41.7 120 56.1 122 40.9 118 17.2 101 46.4 114 10.1 88 0.70 24 0.40 26 2.78 29 29.8 107 62.4 124 38.0 114
StereoOF-V1MT [119]101.2 4.08 95 23.0 102 1.49 69 10.4 95 53.3 120 4.35 42 16.3 102 49.5 124 5.71 66 7.37 100 48.5 121 4.03 95 46.7 126 62.9 129 42.9 123 21.9 125 64.7 136 17.0 119 1.58 40 1.87 67 9.43 77 33.2 119 66.2 129 36.5 108
BlockOverlap [61]103.0 4.14 100 17.3 79 3.50 119 23.3 116 43.1 100 25.5 118 21.0 112 37.2 98 27.8 114 13.1 120 39.0 103 13.7 122 28.8 52 38.6 40 28.2 87 18.7 112 37.2 63 13.3 109 12.6 138 6.40 135 40.8 139 26.8 104 45.8 73 43.3 120
Shiralkar [42]103.9 4.11 97 23.3 103 1.52 72 8.88 76 44.5 103 5.07 52 14.5 98 41.9 110 6.96 72 7.32 99 44.7 113 4.37 98 38.8 113 55.2 120 33.1 100 26.7 132 60.7 131 18.5 124 10.4 130 3.38 104 32.9 133 26.7 102 61.6 120 29.5 92
EAI-Flow [151]104.0 6.63 121 29.9 121 2.74 115 16.6 107 49.7 113 13.0 103 19.1 109 46.0 117 20.3 104 7.88 104 42.2 108 5.06 104 43.3 121 60.6 124 34.1 104 15.3 89 46.8 115 10.9 96 5.09 100 0.08 14 13.8 97 26.7 102 57.1 113 30.6 96
LFNet_ROB [149]104.7 8.75 128 41.6 138 3.69 123 18.9 112 59.4 126 15.2 107 24.3 118 60.8 136 21.2 106 8.64 112 49.0 124 5.67 110 50.3 132 66.9 134 46.2 130 17.8 104 52.5 128 12.5 105 0.17 8 0.05 8 1.03 15 26.6 100 61.9 122 27.8 86
SegOF [10]106.1 6.07 120 25.2 115 3.62 121 36.7 126 55.3 122 41.7 129 26.1 120 43.8 113 39.2 125 15.2 122 45.4 115 12.3 120 46.5 125 56.0 121 57.5 135 18.2 109 49.9 121 14.9 115 0.19 9 0.71 32 0.86 12 31.1 114 52.9 98 35.9 107
HBpMotionGpu [43]106.6 5.00 110 21.6 99 2.81 116 31.1 123 49.5 112 35.0 123 26.3 122 45.3 114 37.1 123 9.18 116 39.3 104 7.65 117 33.7 84 45.6 83 32.2 97 15.7 93 37.4 66 9.89 87 5.71 107 4.19 113 12.5 92 33.4 121 56.3 111 47.8 125
ResPWCR_ROB [144]106.8 5.84 118 29.6 120 2.83 117 15.8 105 51.1 115 13.4 104 21.2 113 48.5 122 21.2 106 8.43 110 47.3 118 5.39 108 41.2 119 57.0 123 37.4 114 19.2 117 53.0 129 15.6 117 1.16 31 1.66 62 5.49 52 31.6 115 62.2 123 34.6 105
StereoFlow [44]107.7 28.4 146 55.1 147 37.7 146 81.1 147 92.6 147 77.8 146 65.0 145 82.9 147 51.1 141 69.6 146 90.7 147 65.5 143 52.7 137 67.5 135 44.9 128 8.13 4 33.5 45 6.60 18 0.05 3 0.37 21 0.17 5 32.2 116 54.8 108 40.4 116
2bit-BM-tele [98]107.8 5.17 112 23.4 104 3.54 120 16.3 106 40.3 85 16.7 110 15.2 100 34.6 90 14.2 101 8.49 111 37.6 101 6.75 115 32.8 79 44.5 73 28.6 92 24.3 128 43.9 104 22.5 131 15.6 143 8.72 141 50.0 144 26.2 98 50.8 88 37.5 112
SPSA-learn [13]108.5 5.52 114 25.3 117 4.12 124 25.2 119 50.0 114 26.8 120 25.1 119 45.7 116 36.7 122 19.0 123 54.2 126 20.8 124 38.6 110 48.4 97 44.4 126 17.9 107 45.3 110 17.6 121 1.60 41 0.54 28 5.27 51 39.6 129 57.9 117 53.3 130
FlowNet2 [122]109.6 7.84 124 30.7 123 2.58 112 41.4 132 65.2 132 44.4 133 29.6 128 48.0 120 46.8 134 5.31 86 24.0 52 3.06 87 47.8 127 64.8 132 36.3 112 17.8 104 44.3 107 13.4 110 2.93 68 8.71 140 5.22 49 30.2 110 61.7 121 28.8 88
IAOF2 [51]109.8 4.13 98 20.4 97 2.02 92 18.0 109 45.9 107 18.0 111 17.1 106 37.3 99 21.4 108 46.4 137 57.8 128 56.1 140 37.4 106 48.8 99 35.9 111 25.5 129 42.7 99 20.4 128 6.62 114 3.04 101 15.3 109 26.8 104 51.0 89 37.9 113
AugFNG_ROB [143]110.6 9.81 130 36.9 134 4.29 125 38.3 129 64.3 130 42.6 131 29.2 127 57.1 129 38.5 124 7.41 101 39.4 105 4.51 99 50.9 133 70.1 139 37.7 115 17.0 100 50.1 122 13.6 112 0.23 11 2.25 85 0.17 5 36.5 126 68.9 134 36.5 108
Filter Flow [19]110.7 5.13 111 23.5 105 2.40 109 20.5 113 51.3 116 19.6 112 23.3 116 42.6 112 35.3 120 27.2 129 48.8 122 28.3 129 39.4 114 49.1 100 44.6 127 17.9 107 40.5 91 11.8 103 7.39 119 7.67 138 11.5 87 26.6 100 46.0 74 33.9 103
EPMNet [133]110.8 7.68 123 33.7 128 2.38 108 39.6 130 72.0 141 40.0 128 27.9 124 46.4 118 44.6 132 7.12 98 38.7 102 3.78 92 47.8 127 64.8 132 36.3 112 17.8 104 44.3 107 13.4 110 1.56 39 5.60 127 2.27 23 33.0 118 70.0 135 32.3 102
Black & Anandan [4]111.7 5.52 114 25.2 115 4.71 127 24.4 118 52.8 117 24.4 117 26.8 123 48.3 121 34.4 119 20.9 127 60.4 129 22.4 126 38.7 112 49.7 105 42.8 122 18.9 114 49.4 119 17.1 120 1.78 45 2.57 94 3.30 31 36.0 124 57.3 115 49.5 126
Modified CLG [34]114.0 7.42 122 31.9 125 5.50 128 31.7 124 52.9 118 37.6 126 28.4 126 50.8 126 40.4 127 20.3 125 60.5 130 21.3 125 39.5 116 51.2 110 42.2 119 14.2 72 45.8 113 11.5 102 3.24 71 1.70 65 9.31 76 40.3 130 65.1 127 54.7 133
IAOF [50]114.9 5.70 116 24.0 107 3.65 122 30.0 122 48.7 109 33.9 122 26.2 121 47.8 119 29.5 115 28.0 130 51.3 125 32.9 130 37.3 105 50.2 106 34.4 106 26.2 130 50.9 125 18.0 123 5.85 109 1.63 56 11.7 88 36.3 125 59.4 119 51.9 128
TVL1_ROB [138]115.4 16.9 137 35.6 130 25.2 143 53.5 139 60.5 128 64.0 140 36.2 133 58.7 130 48.0 137 44.6 136 72.3 136 52.0 137 39.5 116 50.7 107 42.5 121 15.5 91 47.0 116 14.1 114 0.40 15 0.66 31 1.90 19 47.4 137 71.1 137 60.2 139
GraphCuts [14]116.6 5.45 113 24.7 111 2.64 114 24.3 117 55.8 124 21.9 116 21.4 114 40.8 109 32.4 118 9.25 118 46.4 116 6.31 113 38.6 110 51.7 114 33.8 103 28.8 135 39.7 82 18.7 125 12.1 137 2.87 98 35.1 136 38.5 127 58.4 118 53.9 131
2D-CLG [1]119.1 14.0 135 40.7 136 8.09 133 45.8 134 59.5 127 54.5 137 36.8 135 60.4 135 47.3 135 48.9 139 75.1 140 54.2 139 44.9 123 54.8 118 52.5 132 19.0 115 50.3 124 17.8 122 1.26 33 0.07 9 4.43 44 47.4 137 71.2 138 59.9 138
GroupFlow [9]119.9 8.95 129 33.2 126 7.07 130 43.6 133 70.7 137 45.5 134 32.7 130 59.8 134 42.4 130 13.2 121 46.6 117 12.4 121 51.1 134 70.0 138 34.2 105 30.8 137 62.8 133 33.8 138 1.54 38 2.56 93 4.14 37 39.0 128 67.0 131 47.4 124
UnFlow [129]121.0 22.1 144 43.6 140 7.44 132 52.6 138 73.8 142 54.3 136 47.7 141 74.9 144 47.5 136 26.4 128 68.7 134 24.7 128 64.5 142 75.5 144 65.6 142 28.5 134 67.0 140 27.1 135 0.19 9 1.87 67 0.05 2 30.4 112 62.4 124 36.8 110
Nguyen [33]121.5 8.19 125 31.4 124 4.40 126 54.9 140 55.7 123 70.2 142 33.6 132 54.6 127 43.3 131 43.5 135 60.9 131 50.5 136 45.1 124 54.9 119 54.2 133 21.1 121 49.4 119 21.0 129 2.92 67 1.87 67 7.39 66 44.7 135 66.2 129 58.5 136
Horn & Schunck [3]123.5 8.56 127 35.5 129 7.11 131 29.4 121 65.4 133 28.1 121 33.4 131 64.4 138 41.2 129 30.6 131 67.2 133 33.6 131 49.1 131 61.3 125 55.5 134 26.4 131 64.7 136 26.1 134 3.02 69 3.95 108 2.44 24 48.8 139 75.0 140 58.8 137
SILK [79]125.9 10.7 132 35.7 131 14.6 138 37.7 127 64.2 129 42.5 130 32.3 129 59.3 132 40.6 128 19.9 124 56.8 127 20.4 123 51.6 136 62.6 128 59.6 138 27.2 133 63.0 134 23.2 132 4.92 97 1.68 64 13.1 94 46.9 136 71.6 139 61.7 141
TI-DOFE [24]130.0 21.2 142 43.7 141 34.5 145 64.6 145 71.9 140 76.5 145 47.1 140 75.6 145 53.7 142 57.3 141 76.4 141 65.6 144 51.5 135 63.9 130 60.0 139 30.4 136 65.8 139 33.2 136 2.24 54 1.65 59 5.22 49 59.1 143 82.1 145 71.2 144
Periodicity [78]130.1 11.0 133 41.5 137 5.85 129 35.3 125 64.5 131 36.8 125 51.0 142 55.5 128 61.7 144 49.6 140 81.4 143 48.4 135 66.0 144 83.6 147 59.0 136 46.1 142 76.4 144 43.0 142 1.67 44 5.33 125 8.13 70 48.8 139 78.9 142 57.5 135
Heeger++ [104]131.2 24.4 145 45.8 142 9.72 135 47.8 136 85.9 146 37.8 127 66.2 146 69.8 141 75.2 145 59.7 143 88.6 146 56.9 141 66.6 145 80.3 146 62.4 141 65.6 147 87.3 147 67.1 147 4.14 85 1.26 46 7.39 66 41.9 133 68.8 132 43.4 122
SLK [47]134.2 17.8 139 50.1 145 21.7 142 62.2 144 77.8 144 74.7 144 40.4 138 72.7 143 48.1 138 66.2 144 73.9 138 76.1 146 60.9 140 71.2 140 72.9 146 33.1 138 68.3 142 35.4 140 5.99 110 1.09 40 11.4 86 60.5 145 81.9 144 75.0 145
FFV1MT [106]134.7 22.0 143 42.2 139 9.20 134 41.0 131 76.9 143 36.1 124 66.5 147 71.9 142 79.2 146 58.5 142 87.7 145 57.1 142 64.8 143 76.5 145 70.3 145 64.8 146 85.8 146 65.3 146 4.70 92 4.86 120 11.3 85 41.9 133 68.8 132 43.4 122
H+S_ROB [137]135.2 19.8 140 52.3 146 11.9 137 59.1 142 81.5 145 63.0 139 52.7 143 80.5 146 49.7 140 77.0 147 84.8 144 83.9 147 68.5 147 73.1 141 94.1 147 47.1 143 76.6 145 51.9 144 3.54 80 1.65 59 10.8 83 74.4 147 85.4 147 76.7 146
Adaptive flow [45]135.4 16.0 136 36.3 132 17.5 140 57.9 141 67.3 134 64.2 141 38.7 137 59.2 131 48.8 139 39.9 133 69.2 135 44.2 134 49.0 130 62.0 127 43.6 125 39.1 141 62.2 132 34.3 139 34.2 146 23.4 146 82.8 145 40.6 131 64.9 126 51.9 128
FOLKI [16]136.9 13.4 134 45.9 143 16.0 139 48.5 137 67.4 135 57.8 138 36.6 134 66.2 139 40.3 126 32.2 132 66.9 132 37.2 132 52.9 138 64.2 131 60.1 140 34.7 139 65.7 138 40.2 141 12.9 139 7.56 137 33.8 135 55.3 142 78.0 141 70.7 143
PGAM+LK [55]139.1 17.6 138 48.4 144 26.7 144 45.8 134 71.8 139 49.9 135 38.3 136 67.6 140 44.6 132 42.8 134 79.5 142 42.6 133 56.5 139 69.9 137 59.0 136 37.8 140 70.5 143 33.6 137 23.5 144 15.0 145 48.8 143 54.6 141 80.9 143 61.1 140
Pyramid LK [2]140.0 19.8 140 36.7 133 40.3 147 61.8 143 68.8 136 74.6 143 43.5 139 63.7 137 58.2 143 46.9 138 72.7 137 54.1 138 61.5 141 74.5 143 65.8 143 51.3 144 64.1 135 50.1 143 10.8 133 6.30 133 31.9 132 68.2 146 84.9 146 84.8 147
HCIC-L [99]142.8 29.6 147 37.7 135 11.4 136 77.3 146 71.7 138 90.9 147 63.0 144 59.4 133 83.6 147 66.9 145 74.8 139 69.8 145 68.1 146 74.1 142 66.1 144 54.4 145 67.4 141 52.5 145 58.9 147 43.5 147 89.4 146 59.4 144 70.0 135 67.4 142
AdaConv-v1 [126]148.5 82.5 148 78.4 148 94.0 149 98.6 148 99.3 148 97.9 148 99.9 148 99.9 148 99.9 148 97.4 149 96.9 149 99.7 149 100.0 149 99.9 149 99.8 149 93.4 148 95.5 149 93.4 148 86.5 149 85.7 149 99.4 149 99.9 148 99.9 148 99.9 148
SepConv-v1 [127]148.5 82.5 148 78.4 148 94.0 149 98.6 148 99.3 148 97.9 148 99.9 148 99.9 148 99.9 148 97.4 149 96.9 149 99.7 149 100.0 149 99.9 149 99.8 149 93.4 148 95.5 149 93.4 148 86.5 149 85.7 149 99.4 149 99.9 148 99.9 148 99.9 148
SuperSlomo [132]148.5 82.5 148 78.4 148 94.0 149 98.6 148 99.3 148 97.9 148 99.9 148 99.9 148 99.9 148 97.4 149 96.9 149 99.7 149 100.0 149 99.9 149 99.8 149 93.4 148 95.5 149 93.4 148 86.5 149 85.7 149 99.4 149 99.9 148 99.9 148 99.9 148
CtxSyn [136]148.5 82.5 148 78.4 148 94.0 149 98.6 148 99.3 148 97.9 148 99.9 148 99.9 148 99.9 148 97.4 149 96.9 149 99.7 149 100.0 149 99.9 149 99.8 149 93.4 148 95.5 149 93.4 148 86.5 149 85.7 149 99.4 149 99.9 148 99.9 148 99.9 148
CyclicGen [153]148.5 82.5 148 78.4 148 94.0 149 98.6 148 99.3 148 97.9 148 99.9 148 99.9 148 99.9 148 97.4 149 96.9 149 99.7 149 100.0 149 99.9 149 99.8 149 93.4 148 95.5 149 93.4 148 86.5 149 85.7 149 99.4 149 99.9 148 99.9 148 99.9 148
TOF-M [154]148.5 82.5 148 78.4 148 94.0 149 98.6 148 99.3 148 97.9 148 99.9 148 99.9 148 99.9 148 97.4 149 96.9 149 99.7 149 100.0 149 99.9 149 99.8 149 93.4 148 95.5 149 93.4 148 86.5 149 85.7 149 99.4 149 99.9 148 99.9 148 99.9 148
MEMC-Net+ [155]148.5 82.5 148 78.4 148 94.0 149 98.6 148 99.3 148 97.9 148 99.9 148 99.9 148 99.9 148 97.4 149 96.9 149 99.7 149 100.0 149 99.9 149 99.8 149 93.4 148 95.5 149 93.4 148 86.5 149 85.7 149 99.4 149 99.9 148 99.9 148 99.9 148
CFRF [156]148.5 82.5 148 78.4 148 94.0 149 98.6 148 99.3 148 97.9 148 99.9 148 99.9 148 99.9 148 97.4 149 96.9 149 99.7 149 100.0 149 99.9 149 99.8 149 93.4 148 95.5 149 93.4 148 86.5 149 85.7 149 99.4 149 99.9 148 99.9 148 99.9 148
MPRN [157]148.5 82.5 148 78.4 148 94.0 149 98.6 148 99.3 148 97.9 148 99.9 148 99.9 148 99.9 148 97.4 149 96.9 149 99.7 149 100.0 149 99.9 149 99.8 149 93.4 148 95.5 149 93.4 148 86.5 149 85.7 149 99.4 149 99.9 148 99.9 148 99.9 148
DAIN [158]148.5 82.5 148 78.4 148 94.0 149 98.6 148 99.3 148 97.9 148 99.9 148 99.9 148 99.9 148 97.4 149 96.9 149 99.7 149 100.0 149 99.9 149 99.8 149 93.4 148 95.5 149 93.4 148 86.5 149 85.7 149 99.4 149 99.9 148 99.9 148 99.9 148
PyrWarp [159]148.5 82.5 148 78.4 148 94.0 149 98.6 148 99.3 148 97.9 148 99.9 148 99.9 148 99.9 148 97.4 149 96.9 149 99.7 149 100.0 149 99.9 149 99.8 149 93.4 148 95.5 149 93.4 148 86.5 149 85.7 149 99.4 149 99.9 148 99.9 148 99.9 148
InterpCNN [160]148.5 82.5 148 78.4 148 94.0 149 98.6 148 99.3 148 97.9 148 99.9 148 99.9 148 99.9 148 97.4 149 96.9 149 99.7 149 100.0 149 99.9 149 99.8 149 93.4 148 95.5 149 93.4 148 86.5 149 85.7 149 99.4 149 99.9 148 99.9 148 99.9 148
OFRI [161]148.5 82.5 148 78.4 148 94.0 149 98.6 148 99.3 148 97.9 148 99.9 148 99.9 148 99.9 148 97.4 149 96.9 149 99.7 149 100.0 149 99.9 149 99.8 149 93.4 148 95.5 149 93.4 148 86.5 149 85.7 149 99.4 149 99.9 148 99.9 148 99.9 148
AVG_FLOW_ROB [141]152.9 93.7 161 89.5 161 90.8 148 99.0 161 99.4 161 98.5 161 99.9 148 99.9 148 99.9 148 95.9 148 91.8 148 95.9 148 99.8 148 99.7 148 99.7 148 96.8 161 95.1 148 94.6 161 85.8 148 76.3 148 97.8 148 100.0 161 100.0 161 99.9 148
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. IEEE TIP 26(8):4055-4067, 2017.
[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.
[136] CtxSyn 0.07 2 color S. Niklaus and F. Liu. (Interpolation results only.) Context-aware synthesis for video frame interpolation. CVPR 2018.
[137] H+S_ROB 5 2 color ROB 2018 baseline submission, based on: E. Meinhardt-Llopis, J. Sanchez, and D. Kondermann. Horn-Schunck optical flow with a multi-scale strategy. Image Processing On Line 3:151–172, 2013.
[138] TVL1_ROB 1 2 color ROB 2018 baseline submission, based on: J. Sanchez, E. Meinhardt-Llopis, and G. Facciolo. TV-L1 optical flow estimation. Image Processing On Line 3:137-150, 2013.
[139] 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.
[140] 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.
[141] AVG_FLOW_ROB N/A 2 N/A Average flow field of ROB 2018 training set.
[142] 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.
[143] AugFNG_ROB 0.10 all color Anonymous. FusionNet and AugmentedFlowNet: Selective proxy ground truth for training on unlabeled images. ECCV 2018 submission 2834.
[144] ResPWCR_ROB 0.2 2 color Anonymous. Learning optical flow with residual connections. ROB 2018 submission.
[145] 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.
[146] ProFlow_ROB 76 3 color Anonymous. ProFlow: Learning to predict optical flow. BMVC 2018 submission 277.
[147] PWC-Net_ROB 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.
[148] WOLF_ROB 0.02 2 color Anonymous. Reversed deep neural network for optical flow. ROB 2018 submission.
[149] LFNet_ROB 0.068 2 color Anonymous. Learning a flow network. ROB 2018 submission.
[150] 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.
[151] 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.
[152] ContinualFlow_ROB 0.5 all color M Neoral, J. Sochman, and J. Matas. Continual occlusions and optical flow estimation. ACCV 2018.
[153] CyclicGen 0.088 2 color Anonymous. (Interpolation results only.) Deep video frame interpolation using cyclic frame generation. AAAI 2019 submission 323.
[154] TOF-M 0.393 2 color T. Xue, B. Chen, J. Wu, D. Wei, and W. Freeman. Video enhancement with task-oriented flow. arXiv 1711.09078, 2017.
[155] MEMC-Net+ 0.16 2 color W. Bao, W.-S. Lai, X. Zhang, Z. Gao, and M.-H. Yang. (Interpolation results only.) MEMC-Net: Motion estimation and motion compensation driven neural network for video interpolation and enhancement. Submitted to TPAMI 2018.
[156] CFRF 0.128 2 color Anonymous. (Interpolation results only.) Coarse-to-fine refinement framework for video frame interpolation. CVPR 2019 submission 1992.
[157] MPRN 0.32 4 color Anonymous. (Interpolation results only.) Multi-frame pyramid refinement network for video frame interpolation. CVPR 2019 submission 1361.
[158] DAIN 0.13 2 color Anonymous. (Interpolation results only.) DAIN: Depth-aware video frame interpolation. CVPR 2019 submission 1769.
[159] PyrWarp 0.14 2 color Anonymous. (Interpolation results only.) Feature pyramid warping for video frame interpolation. CVPR 2019 submission 868.
[160] InterpCNN 0.65 2 color Anonymous. (Interpolation results only.) Video frame interpolation with a stack of synthesis networks and intermediate optical flows. CVPR 2019 submission 6533.
[161] OFRI 0.31 2 color Anonymous. (Interpolation results only.) Efficient video frame interpolation via optical flow refinement. CVPR 2019 submission 6743.
* 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.