Optical flow evaluation results Statistics:     Average   SD   R2.5   R5.0   R10.0   A50   A75   A95  
Error type:   endpoint   angle   interpolation   normalized interpolation  
Show images: below table   above table        
A75
angle
error
avg. Army
(Hidden texture)
GT   im0   im1
Mequon
(Hidden texture)
GT   im0   im1
Schefflera
(Hidden texture)
GT   im0   im1
Wooden
(Hidden texture)
GT   im0   im1
Grove
(Synthetic)
GT   im0   im1
Urban
(Synthetic)
GT   im0   im1
Yosemite
(Synthetic)
GT   im0   im1
Teddy
(Stereo)
GT   im0   im1
rank all disc untext all disc untext all disc untext all disc untext all disc untext all disc untext all disc untext all disc untext
NNF-Local [87]16.4 2.17 4 5.35 5 1.92 4 1.56 6 6.39 20 1.67 11 1.51 7 3.67 8 1.61 9 1.20 36 4.36 17 1.02 37 2.30 4 3.18 3 1.73 7 2.16 40 6.35 8 2.39 66 2.54 27 4.18 13 2.17 32 0.81 9 1.50 17 0.67 4
NN-field [71]17.1 2.31 8 5.94 13 1.98 5 1.83 23 7.21 38 1.97 30 1.54 9 3.55 7 1.68 13 0.96 10 3.04 4 0.75 6 2.30 4 3.25 4 1.69 5 1.72 19 3.81 1 1.65 7 3.12 59 4.76 55 2.60 57 0.79 6 1.58 26 0.59 2
TC/T-Flow [76]20.4 2.06 1 7.42 30 1.55 1 1.61 12 6.77 29 1.52 4 1.46 5 4.33 19 1.56 6 0.88 3 6.96 46 0.69 2 2.91 20 4.35 27 1.88 11 1.47 5 6.12 7 1.61 6 2.22 9 3.98 4 4.00 103 1.06 41 1.99 46 1.19 53
ComponentFusion [96]20.7 2.12 3 6.18 16 1.80 3 1.67 15 4.82 5 1.91 25 1.34 2 4.01 11 1.47 4 0.88 3 4.74 19 0.72 4 2.99 24 4.35 27 1.96 14 2.03 32 11.2 78 1.96 28 2.90 49 4.62 49 1.90 19 0.93 26 1.56 25 0.89 16
ProFlow_ROB [146]20.7 2.44 11 7.85 39 2.01 6 1.54 4 7.07 34 1.55 5 1.53 8 7.16 56 1.43 2 0.81 1 5.26 26 0.67 1 3.48 44 4.95 49 1.69 5 1.46 4 8.54 34 1.53 4 1.92 3 4.48 34 2.01 23 0.93 26 2.14 52 0.94 26
ALD-Flow [66]23.8 2.26 6 5.81 10 2.07 7 1.56 6 5.71 14 1.66 9 1.46 5 4.64 25 1.66 12 0.95 9 7.15 50 0.80 12 3.18 35 4.57 38 1.76 8 1.51 6 7.63 20 1.60 5 2.61 30 4.27 19 3.90 99 1.04 38 2.22 59 1.18 50
WLIF-Flow [93]24.0 2.63 20 5.51 6 2.41 18 2.14 45 7.08 35 2.32 44 1.63 13 4.19 14 1.84 20 1.05 16 4.21 14 0.88 24 2.92 22 4.37 29 2.30 33 2.02 31 7.21 16 1.89 24 2.73 38 4.27 19 2.78 66 0.84 11 1.37 6 0.83 11
nLayers [57]25.0 2.33 9 5.14 3 2.17 10 2.75 94 7.22 40 3.07 96 1.69 22 4.04 12 2.21 65 0.88 3 2.83 2 0.70 3 2.08 2 3.25 4 1.30 1 1.88 22 6.06 6 1.85 14 2.89 48 4.59 44 2.28 37 0.92 23 1.48 15 0.94 26
OFLAF [77]25.5 2.77 36 5.70 8 2.49 20 1.76 18 5.35 10 1.84 22 1.54 9 2.69 2 1.72 15 1.30 41 3.55 10 1.12 52 2.30 4 3.62 7 1.64 4 2.23 46 5.93 3 2.06 38 2.81 42 4.29 22 2.99 72 1.15 51 1.69 31 1.18 50
MDP-Flow2 [68]26.2 3.08 42 6.23 17 2.73 48 1.55 5 4.80 4 1.64 8 1.63 13 3.27 4 1.61 9 1.37 53 5.15 24 1.15 57 2.91 20 4.19 20 2.20 21 2.24 48 6.43 9 2.17 48 2.62 31 4.35 26 1.88 18 1.08 43 1.66 30 0.95 30
RNLOD-Flow [121]26.9 2.19 5 4.96 2 2.19 11 1.79 20 7.20 37 1.76 17 1.42 3 4.31 17 1.56 6 0.97 11 3.42 9 0.84 17 2.75 15 4.16 17 2.01 16 1.86 21 7.24 17 1.95 27 4.02 97 6.41 114 4.48 118 0.90 18 1.51 18 0.85 12
OAR-Flow [125]27.7 2.55 14 7.57 32 2.36 15 1.81 21 7.94 46 1.94 29 1.72 29 8.40 63 1.95 28 0.94 8 5.90 36 0.79 9 3.49 46 4.83 47 1.84 10 1.16 2 7.84 25 1.22 2 1.93 4 3.63 1 2.26 35 1.10 46 2.16 55 1.34 62
AGIF+OF [85]29.0 2.60 15 6.24 18 2.45 19 2.49 73 9.30 68 2.63 72 1.68 20 4.79 31 2.08 49 1.05 16 4.34 16 0.81 13 2.77 17 4.05 14 2.10 19 1.92 25 7.48 19 1.74 12 2.69 35 4.48 34 2.69 63 0.87 12 1.40 7 0.95 30
Layers++ [37]29.5 2.70 31 6.40 20 2.83 55 2.33 62 6.62 26 2.54 69 1.65 17 3.24 3 2.02 38 0.92 6 2.48 1 0.75 6 2.12 3 3.11 1 1.50 3 2.06 35 8.25 28 1.94 26 3.59 82 5.41 83 3.21 75 0.89 15 1.32 4 0.90 19
LME [70]30.5 2.90 38 5.83 11 2.30 14 1.60 9 4.45 2 1.74 16 1.71 26 4.14 13 2.00 34 1.35 47 6.61 41 1.13 53 3.07 29 4.32 26 2.57 47 2.08 37 8.09 27 2.00 34 2.78 41 4.53 40 2.29 38 1.06 41 1.74 33 0.96 34
HAST [109]31.7 2.09 2 4.28 1 1.69 2 1.60 9 5.31 9 1.55 5 1.28 1 2.09 1 1.40 1 0.92 6 3.39 7 0.78 8 2.01 1 3.14 2 1.48 2 2.40 61 8.62 36 2.41 68 4.08 99 7.33 135 7.69 138 1.23 58 1.59 28 1.73 81
TC-Flow [46]32.1 2.45 12 6.60 22 2.39 17 1.25 1 5.24 7 1.32 1 1.45 4 4.40 22 1.50 5 1.15 33 8.13 57 1.04 39 3.22 36 4.77 45 2.06 18 1.94 26 8.65 37 2.09 42 2.33 21 4.51 37 3.82 97 1.24 59 2.18 57 1.50 76
PH-Flow [101]33.4 2.62 17 7.58 34 2.53 27 2.13 42 8.78 55 2.37 48 1.70 23 4.39 21 2.06 45 1.08 19 7.06 49 0.85 18 2.72 12 3.91 11 2.04 17 2.06 35 8.33 29 1.96 28 3.48 77 4.62 49 4.03 104 0.90 18 1.41 10 0.88 14
Classic+CPF [83]33.8 2.65 26 7.22 29 2.53 27 2.37 64 9.14 65 2.51 65 1.67 19 5.05 35 2.03 40 1.01 12 5.38 28 0.79 9 2.90 19 4.17 18 2.33 35 1.88 22 8.44 31 1.70 9 3.19 62 4.60 46 3.72 90 0.92 23 1.40 7 0.95 30
NNF-EAC [103]33.8 3.07 41 6.73 24 2.70 47 1.62 14 5.30 8 1.72 14 1.71 26 3.89 10 1.79 17 1.36 50 6.36 40 1.15 57 3.02 25 4.37 29 2.28 31 2.44 64 6.90 12 2.28 60 2.90 49 4.51 37 2.19 33 1.12 48 1.83 39 0.98 36
Sparse-NonSparse [56]34.1 2.62 17 7.58 34 2.60 37 2.18 51 8.74 53 2.46 61 1.68 20 4.86 32 2.00 34 1.04 14 7.97 55 0.81 13 3.13 32 4.45 33 2.42 41 1.98 29 8.53 33 1.87 18 3.13 60 4.32 25 3.51 83 0.88 13 1.41 10 0.91 20
FC-2Layers-FF [74]34.2 2.63 20 5.87 12 2.68 45 2.19 55 8.07 48 2.39 52 1.65 17 3.42 5 2.05 42 1.10 25 3.11 5 0.88 24 2.57 7 3.49 6 2.30 33 2.26 51 7.68 22 2.17 48 3.70 85 5.18 77 3.73 91 0.90 18 1.41 10 0.93 24
IROF++ [58]34.5 2.66 27 6.82 25 2.58 35 2.17 49 9.07 62 2.41 54 1.75 35 5.03 34 2.06 45 1.11 27 7.65 52 0.90 30 2.92 22 4.18 19 2.25 28 2.13 38 9.85 56 1.98 31 2.53 26 4.53 40 1.43 7 0.97 35 1.58 26 0.94 26
JOF [140]37.1 2.52 13 6.01 15 2.37 16 2.40 68 9.13 64 2.66 74 1.63 13 3.82 9 2.17 62 1.02 13 5.46 31 0.79 9 2.69 11 3.93 12 2.24 25 2.16 40 8.05 26 2.20 50 3.97 95 5.74 96 5.45 124 0.82 10 1.33 5 0.82 10
FESL [72]37.2 2.63 20 5.15 4 2.77 52 2.62 87 9.27 67 2.73 79 1.72 29 4.77 29 2.07 48 1.15 33 3.36 6 0.98 35 2.75 15 3.93 12 2.20 21 1.95 27 7.12 14 1.98 31 3.40 72 5.71 95 2.89 68 0.88 13 1.55 22 0.87 13
COFM [59]37.5 2.28 7 7.19 27 2.08 9 1.78 19 6.57 23 1.93 27 1.56 12 5.33 40 2.19 63 0.86 2 4.90 20 0.73 5 3.76 56 4.80 46 3.87 97 2.03 32 7.67 21 1.72 10 2.76 39 4.21 15 4.04 106 1.62 88 1.87 41 2.04 95
Efficient-NL [60]38.0 2.38 10 5.67 7 2.07 7 2.45 72 8.54 50 2.55 70 1.64 16 4.63 24 1.95 28 1.04 14 5.76 34 0.81 13 2.74 13 4.14 16 1.94 13 2.87 79 8.58 35 2.23 53 3.30 67 5.12 74 3.05 73 1.15 51 1.83 39 1.19 53
PMMST [114]39.1 3.55 66 6.48 21 3.33 76 2.18 51 6.49 22 2.47 64 1.93 47 4.28 15 2.09 50 1.60 73 2.84 3 1.43 81 2.60 8 3.72 9 1.91 12 2.22 45 6.05 5 2.13 46 2.70 37 4.48 34 2.08 27 1.18 57 1.91 43 1.09 46
LSM [39]39.6 2.60 15 7.70 38 2.61 39 2.19 55 8.77 54 2.44 59 1.70 23 4.78 30 2.06 45 1.08 19 8.13 57 0.86 20 3.05 27 4.30 23 2.47 42 2.18 43 8.66 40 2.08 40 3.56 80 4.68 54 3.74 92 0.90 18 1.43 13 0.93 24
Classic+NL [31]40.9 2.63 20 7.57 32 2.64 42 2.18 51 9.04 60 2.41 54 1.71 26 4.70 26 2.09 50 1.08 19 7.69 53 0.88 24 3.04 26 4.31 24 2.41 40 2.27 52 8.65 37 2.09 42 3.79 89 5.12 74 3.81 95 0.89 15 1.44 14 0.89 16
FMOF [94]41.3 2.71 33 6.71 23 2.62 41 2.64 88 9.19 66 2.77 80 1.73 32 4.37 20 2.22 66 1.06 18 5.18 25 0.81 13 2.89 18 4.25 22 2.40 39 2.31 54 7.76 24 1.96 28 3.35 70 4.88 67 3.81 95 0.93 26 1.55 22 0.92 22
Ramp [62]41.4 2.64 25 7.64 37 2.56 31 2.20 58 8.90 58 2.46 61 1.73 32 4.74 28 2.09 50 1.11 27 6.81 45 0.88 24 3.07 29 4.46 34 2.38 38 2.28 53 8.52 32 2.15 47 3.40 72 4.25 16 4.16 113 0.94 29 1.53 20 0.97 35
ProbFlowFields [128]42.4 3.31 52 13.8 89 2.85 57 2.03 34 6.67 28 2.23 39 1.89 45 6.06 46 2.29 70 1.23 38 5.14 23 0.95 33 3.70 52 5.08 51 2.29 32 1.60 10 7.44 18 1.85 14 2.43 25 4.30 23 2.45 49 1.29 63 2.32 61 1.38 66
2DHMM-SAS [92]44.1 2.62 17 7.61 36 2.53 27 2.17 49 10.1 78 2.38 50 1.83 40 6.16 49 2.10 54 1.09 23 8.07 56 0.86 20 3.06 28 4.42 32 2.37 37 2.16 40 9.30 46 2.01 35 3.50 78 4.64 51 4.14 112 0.96 33 1.64 29 0.99 39
Adaptive [20]44.6 2.63 20 8.08 44 2.23 12 2.18 51 8.66 52 2.27 42 2.04 56 9.57 70 2.09 50 1.12 30 10.6 76 0.87 22 4.47 102 5.30 68 4.44 113 1.55 7 8.65 37 1.43 3 3.32 68 5.51 85 2.14 31 0.77 5 1.52 19 0.75 8
SVFilterOh [111]45.5 3.48 62 5.72 9 3.45 81 2.38 66 6.06 17 2.41 54 1.93 47 3.46 6 2.05 42 1.53 69 3.71 11 1.27 68 2.65 10 4.10 15 2.00 15 2.47 66 7.08 13 2.28 60 4.60 110 7.10 128 5.92 129 0.73 4 1.16 2 0.70 7
PMF [73]46.3 3.22 50 6.34 19 2.60 37 1.95 30 6.66 27 1.92 26 1.85 41 4.58 23 1.83 19 1.62 74 4.27 15 1.37 75 2.61 9 3.74 10 1.83 9 3.18 88 9.94 59 3.34 94 5.29 126 8.26 142 5.58 128 0.68 3 1.21 3 0.67 4
TV-L1-MCT [64]46.7 2.68 29 6.83 26 2.61 39 2.68 89 10.3 81 2.80 84 1.78 37 5.24 37 2.24 67 1.13 31 5.44 30 0.87 22 3.39 42 4.69 43 2.96 66 2.45 65 9.14 44 2.31 64 2.64 32 4.37 28 2.04 25 1.08 43 1.74 33 1.36 64
S2D-Matching [84]46.8 2.69 30 7.86 41 2.68 45 2.19 55 9.11 63 2.44 59 1.77 36 6.11 48 2.04 41 1.13 31 5.86 35 0.91 31 3.17 34 4.41 31 2.50 44 2.41 62 9.09 43 2.25 57 4.00 96 5.16 76 4.07 107 0.91 22 1.40 7 0.95 30
SimpleFlow [49]48.7 2.74 34 8.28 48 2.73 48 2.50 74 9.73 76 2.83 90 1.89 45 6.81 54 2.35 73 1.11 27 10.4 73 0.89 29 3.27 37 4.47 35 2.63 49 3.03 82 8.91 42 2.39 66 3.10 58 4.25 16 2.76 65 0.89 15 1.49 16 0.89 16
Occlusion-TV-L1 [63]49.1 3.15 44 8.42 50 2.50 21 2.03 34 7.42 42 2.14 36 2.24 67 9.79 72 2.16 60 1.35 47 9.59 66 1.11 48 4.10 80 5.77 100 3.22 77 1.68 18 9.21 45 2.08 40 2.69 35 4.59 44 1.70 14 1.05 39 2.36 64 0.98 36
IROF-TV [53]49.3 2.89 37 8.67 53 2.81 54 2.25 60 9.54 74 2.51 65 1.79 39 5.50 42 2.15 59 1.53 69 11.5 84 1.27 68 3.33 38 4.62 39 2.85 57 2.78 74 13.5 100 2.57 71 2.15 6 4.14 11 1.37 6 0.94 29 1.55 22 0.94 26
MDP-Flow [26]50.0 3.14 43 9.81 61 2.83 55 2.06 37 6.10 18 2.43 57 1.87 43 6.10 47 2.10 54 1.44 58 8.90 62 1.15 57 3.37 40 4.62 39 2.54 46 2.35 57 10.4 65 2.23 53 2.88 46 4.83 60 1.94 21 1.27 62 2.62 72 1.09 46
Correlation Flow [75]50.6 3.18 46 7.85 39 2.85 57 1.74 16 5.77 15 1.69 13 1.94 49 5.25 38 1.70 14 1.47 62 5.67 33 1.26 67 3.66 49 5.20 62 2.53 45 3.06 84 9.57 50 3.10 88 3.42 75 4.94 70 4.03 104 1.17 55 1.80 36 1.16 48
3DFlow [135]51.4 3.21 48 7.43 31 2.64 42 1.92 28 7.04 31 1.85 23 2.03 55 4.31 17 1.84 20 1.65 80 3.41 8 1.33 71 3.14 33 4.51 36 2.24 25 3.66 96 11.8 84 3.87 107 4.19 102 4.93 69 5.46 125 1.05 39 1.54 21 1.02 42
AggregFlow [97]53.0 3.29 51 8.49 51 3.14 68 2.70 91 12.2 100 2.68 76 2.32 71 9.03 65 2.88 90 1.44 58 4.19 13 1.25 66 3.48 44 5.09 52 2.19 20 1.55 7 5.36 2 1.68 8 2.56 29 4.78 57 1.77 16 1.54 84 2.15 53 2.16 101
IIOF-NLDP [131]53.5 3.19 47 10.4 65 2.50 21 2.43 71 9.32 70 2.32 44 1.98 52 5.55 43 1.81 18 1.48 64 6.12 39 1.23 64 3.75 54 5.55 88 2.25 28 3.03 82 9.30 46 3.02 84 2.66 34 4.83 60 2.60 57 1.24 59 1.97 45 1.17 49
HCFN [162]54.0 2.92 39 7.95 42 2.56 31 1.39 2 4.71 3 1.47 2 1.55 11 4.29 16 1.44 3 1.51 67 6.05 38 1.32 70 3.11 31 4.31 24 2.33 35 2.64 70 10.7 71 2.67 73 6.60 141 7.99 140 7.44 135 1.53 83 2.63 75 1.96 93
Aniso-Texture [82]54.9 2.75 35 6.00 14 3.09 65 2.13 42 5.64 12 2.52 68 1.78 37 6.80 53 2.20 64 1.08 19 4.01 12 0.92 32 4.08 77 5.44 78 3.26 81 2.31 54 11.8 84 2.26 58 5.87 134 8.09 141 4.24 114 0.80 8 1.70 32 0.67 4
OFH [38]55.8 3.60 74 10.3 64 3.80 92 1.58 8 7.05 32 1.66 9 1.70 23 9.23 66 1.58 8 1.19 35 10.1 69 1.08 44 3.98 62 5.22 64 3.57 86 2.80 75 12.6 91 3.12 89 2.30 16 4.60 46 2.35 40 1.41 77 2.90 86 1.75 82
Classic++ [32]56.8 2.66 27 8.18 47 2.65 44 2.13 42 7.96 47 2.43 57 1.85 41 9.39 69 2.10 54 1.09 23 10.4 73 0.88 24 3.97 60 5.60 93 2.89 60 2.36 58 13.6 103 2.10 44 4.03 98 5.20 78 4.33 115 0.99 37 2.05 48 0.92 22
CostFilter [40]56.8 3.59 71 8.35 49 3.26 72 2.12 40 6.60 24 2.16 37 2.00 54 5.56 44 2.01 36 2.04 93 7.05 48 1.89 94 2.74 13 3.70 8 2.27 30 3.29 89 10.3 64 3.33 93 5.22 124 9.79 147 6.16 131 0.38 1 1.08 1 0.35 1
DeepFlow2 [108]57.4 3.44 57 12.6 79 3.36 79 1.98 31 8.60 51 2.10 34 2.38 74 11.1 77 2.60 80 1.34 44 14.6 96 1.11 48 3.53 47 5.09 52 2.23 24 1.66 17 9.90 58 1.77 13 2.76 39 4.06 8 3.40 80 1.72 93 3.21 97 2.13 99
S2F-IF [123]57.6 3.54 65 19.2 117 2.58 35 2.41 69 10.4 82 2.59 71 2.57 80 10.6 76 2.59 78 1.29 40 10.5 75 0.98 35 4.07 75 5.38 73 2.90 61 1.65 16 9.94 59 1.85 14 2.27 11 4.26 18 2.35 40 1.33 66 2.49 68 1.32 59
FlowFields+ [130]59.1 3.58 69 19.0 112 2.56 31 2.57 79 10.8 87 2.78 81 2.72 86 11.9 84 2.78 88 1.32 42 10.9 79 1.03 38 3.97 60 5.34 70 2.74 50 1.64 15 9.79 55 1.87 18 2.26 10 4.30 23 2.35 40 1.35 68 2.62 72 1.34 62
CPM-Flow [116]59.8 3.47 59 19.0 112 2.52 23 2.59 81 11.0 93 2.82 86 2.56 78 11.3 79 2.75 83 1.34 44 15.7 101 1.06 40 4.02 67 5.42 75 2.78 52 1.59 9 9.39 48 1.87 18 2.30 16 4.17 12 2.36 43 1.35 68 2.69 79 1.39 68
PGM-C [120]60.7 3.48 62 19.0 112 2.52 23 2.59 81 10.8 87 2.82 86 2.59 81 11.8 83 2.75 83 1.34 44 16.5 107 1.06 40 4.03 69 5.46 81 2.78 52 1.60 10 9.63 52 1.88 21 2.28 12 3.98 4 2.36 43 1.37 72 2.69 79 1.45 72
RFlow [90]60.8 3.62 76 9.91 62 3.53 85 1.83 23 5.50 11 1.93 27 2.14 62 9.57 70 1.86 23 1.32 42 6.75 42 1.14 55 3.98 62 5.35 71 3.24 78 2.39 60 11.7 83 2.24 55 3.45 76 4.60 46 3.63 85 1.64 90 2.90 86 1.91 90
SegFlow [160]61.1 3.47 59 19.0 112 2.52 23 2.59 81 10.9 90 2.82 86 2.55 77 11.4 80 2.75 83 1.36 50 16.2 105 1.06 40 4.05 73 5.44 78 2.91 62 1.63 14 9.70 53 1.88 21 2.30 16 4.19 14 2.36 43 1.35 68 2.50 69 1.43 69
EpicFlow [102]62.4 3.47 59 18.9 110 2.52 23 2.59 81 10.9 90 2.82 86 2.64 83 14.2 94 2.75 83 1.35 47 15.5 99 1.06 40 4.04 71 5.48 82 2.88 59 1.62 13 9.70 53 1.91 25 2.28 12 4.08 10 2.36 43 1.39 76 2.71 81 1.51 77
FlowFields [110]62.9 3.56 68 19.0 112 2.54 30 2.57 79 10.6 85 2.79 82 2.72 86 11.7 82 2.76 87 1.42 55 10.9 79 1.13 53 4.08 77 5.43 77 2.92 64 1.60 10 10.5 67 1.86 17 2.28 12 4.35 26 2.46 51 1.38 75 2.62 72 1.36 64
MLDP_OF [89]63.3 4.16 94 10.4 65 4.04 94 2.04 36 6.61 25 2.04 32 2.36 73 6.60 52 2.05 42 1.43 56 5.65 32 1.18 61 3.75 54 4.86 48 2.96 66 2.96 80 8.71 41 3.47 96 4.20 103 5.51 85 7.24 134 1.16 54 1.87 41 1.21 55
WRT [150]63.4 3.48 62 8.79 55 2.57 34 3.21 101 9.36 72 3.18 97 2.76 89 7.40 58 2.30 71 1.64 79 4.61 18 1.23 64 3.41 43 4.56 37 2.48 43 4.89 122 11.0 75 3.31 91 3.03 55 4.82 59 3.25 77 1.10 46 1.75 35 0.99 39
DMF_ROB [139]65.2 3.70 78 15.2 98 3.34 77 2.21 59 9.03 59 2.40 53 2.84 92 13.7 93 2.65 82 1.41 54 16.9 110 1.10 46 3.92 58 5.17 60 3.14 74 2.01 30 10.6 68 2.11 45 2.37 23 3.72 3 2.62 60 1.49 82 2.74 82 1.68 80
TV-L1-improved [17]65.4 2.70 31 9.05 56 2.29 13 1.85 25 7.06 33 1.97 30 1.94 49 9.28 68 1.90 27 1.10 25 8.96 63 0.85 18 4.07 75 5.60 93 2.75 51 5.44 129 17.3 121 6.29 132 4.75 118 6.82 120 4.73 121 1.13 49 2.68 78 1.06 45
Steered-L1 [118]65.9 3.21 48 8.15 46 3.11 67 1.39 2 4.13 1 1.51 3 1.73 32 5.20 36 1.65 11 1.28 39 10.3 72 1.11 48 4.05 73 5.35 71 3.55 84 3.10 85 12.6 91 2.59 72 6.15 139 6.90 122 13.1 147 1.73 94 3.04 94 2.39 105
BriefMatch [124]66.0 3.03 40 7.96 43 2.73 48 1.75 17 6.88 30 1.73 15 1.72 29 4.70 26 1.73 16 1.51 67 5.38 28 1.39 79 4.01 65 5.27 66 3.72 92 5.57 130 15.9 114 6.02 131 4.65 111 6.85 121 8.98 142 0.95 31 2.30 60 1.77 83
PWC-Net_ROB [147]66.5 4.74 106 14.6 93 3.51 84 2.88 97 8.88 57 2.92 94 2.75 88 9.98 74 3.27 98 1.65 80 4.91 21 1.35 72 4.10 80 5.12 57 2.91 62 2.66 72 10.2 63 2.67 73 1.69 2 4.65 53 1.13 3 1.26 61 2.06 49 1.29 58
CombBMOF [113]66.7 3.55 66 11.6 74 2.79 53 2.52 75 7.21 38 2.51 65 1.88 44 5.63 45 1.84 20 1.67 83 11.2 82 1.51 86 3.68 50 4.62 39 3.07 72 4.08 103 11.4 81 4.79 121 4.72 115 6.58 117 3.82 97 0.92 23 1.82 38 0.88 14
Sparse Occlusion [54]67.5 3.36 53 8.08 44 2.90 59 2.61 86 7.68 43 3.01 95 2.10 58 6.40 51 2.13 57 1.45 60 6.80 43 1.14 55 4.01 65 5.31 69 2.81 55 2.55 68 10.4 65 2.21 52 6.70 143 8.26 142 4.34 116 1.15 51 2.08 50 0.99 39
DeepFlow [86]68.9 3.94 86 12.7 80 4.14 98 2.12 40 9.06 61 2.28 43 2.84 92 12.5 88 3.16 95 1.68 84 15.6 100 1.44 83 3.58 48 5.10 54 2.20 21 1.78 20 11.1 76 1.88 21 2.65 33 4.07 9 3.40 80 2.08 112 3.59 113 3.09 116
EPPM w/o HM [88]69.4 4.03 91 13.7 88 3.25 71 1.91 27 7.71 44 1.83 20 2.14 62 7.85 61 1.96 30 1.80 86 10.2 70 1.63 90 3.72 53 4.62 39 3.24 78 3.93 101 13.2 98 3.79 105 4.35 107 5.68 94 7.45 136 0.97 35 1.93 44 0.98 36
Complementary OF [21]72.3 4.47 102 12.4 78 4.63 107 1.60 9 6.16 19 1.67 11 2.10 58 6.85 55 2.16 60 2.27 98 9.76 67 2.19 103 4.00 64 5.10 54 3.71 90 3.96 102 12.9 95 3.32 92 2.83 43 4.46 33 3.08 74 2.04 110 3.33 102 2.86 110
HBM-GC [105]72.4 5.52 110 7.21 28 5.03 114 2.96 98 7.15 36 3.23 99 2.79 91 4.90 33 2.88 90 3.12 113 4.92 22 2.97 117 3.37 40 4.23 21 3.46 82 3.80 100 6.63 10 3.52 97 5.86 133 7.23 133 4.53 119 0.64 2 2.02 47 0.64 3
FF++_ROB [145]72.5 3.75 80 20.6 119 2.92 60 2.60 85 10.6 85 2.79 82 2.97 99 13.2 92 3.18 96 1.62 74 11.2 82 1.38 78 4.12 82 5.52 86 2.99 69 2.24 48 9.58 51 2.30 63 2.31 19 4.40 31 2.39 47 1.36 71 2.55 70 1.44 71
Rannacher [23]74.1 3.60 74 11.3 71 3.27 73 2.41 69 9.53 73 2.63 72 2.60 82 11.9 84 2.58 77 1.36 50 12.1 87 1.09 45 4.22 88 5.90 107 3.14 74 3.63 95 16.1 117 2.75 78 3.72 86 5.24 80 3.70 89 0.96 33 2.16 55 0.91 20
TF+OM [100]74.1 3.58 69 9.07 57 2.75 51 2.07 38 6.43 21 2.37 48 1.99 53 7.56 60 2.78 88 2.07 94 7.02 47 2.07 101 4.19 87 5.12 57 4.32 108 3.15 87 10.1 62 3.00 83 4.10 100 6.00 102 3.92 100 1.54 84 2.98 91 1.94 91
Aniso. Huber-L1 [22]75.0 3.17 45 9.57 59 3.05 63 3.72 103 11.5 97 4.38 106 2.86 95 10.5 75 3.80 102 1.70 85 11.6 85 1.42 80 4.04 71 5.58 90 2.98 68 2.34 56 9.88 57 2.05 37 4.49 109 5.91 100 3.42 82 1.08 43 2.10 51 1.02 42
F-TV-L1 [15]75.8 5.69 112 13.3 83 6.62 122 2.71 92 12.0 99 2.86 92 2.76 89 12.6 89 2.43 75 2.41 103 16.3 106 2.02 100 4.17 85 5.27 66 3.74 93 2.41 62 10.8 73 2.49 70 3.04 56 4.84 65 2.26 35 0.79 6 1.81 37 0.76 9
TCOF [69]75.9 3.95 87 11.0 69 4.20 99 2.56 78 9.31 69 2.68 76 2.71 85 12.8 91 3.34 99 2.30 99 6.80 43 2.33 105 4.50 104 6.28 124 2.58 48 1.89 24 6.02 4 2.06 38 4.72 115 6.30 107 2.58 54 1.37 72 2.63 75 1.22 57
ComplOF-FED-GPU [35]76.1 4.09 93 12.8 81 4.09 97 1.61 12 9.86 77 1.62 7 2.12 60 8.39 62 1.87 25 1.85 88 12.4 90 1.70 93 3.95 59 5.25 65 3.25 80 3.54 93 15.1 112 3.60 101 3.93 92 4.83 60 4.60 120 1.55 86 2.93 90 1.80 84
NL-TV-NCC [25]76.6 3.89 84 8.49 51 3.34 77 2.52 75 8.44 49 2.38 50 2.25 68 5.49 41 1.99 32 1.87 89 7.61 51 1.53 87 4.36 95 5.91 108 2.78 52 4.12 107 13.0 96 3.58 100 3.85 90 5.74 96 3.79 94 1.63 89 2.81 84 1.46 73
ROF-ND [107]77.3 4.03 91 11.1 70 3.48 83 2.33 62 5.09 6 2.22 38 2.19 65 6.22 50 2.02 38 2.30 99 5.92 37 1.68 92 4.23 89 6.03 114 2.94 65 3.70 98 12.2 87 3.05 86 6.21 140 6.93 124 5.53 126 1.43 79 2.21 58 1.32 59
ACK-Prior [27]77.5 4.28 96 9.53 58 3.85 93 1.87 26 5.68 13 1.83 20 1.97 51 5.25 38 1.96 30 1.98 92 5.26 26 1.65 91 4.08 77 5.12 57 3.79 96 4.53 118 13.0 96 3.61 102 5.63 128 6.40 112 8.50 140 1.92 106 2.90 86 2.64 107
LDOF [28]82.3 3.72 79 14.9 96 3.59 88 2.38 66 14.0 112 2.46 61 2.69 84 14.4 95 2.55 76 1.48 64 33.9 131 1.10 46 4.24 91 5.59 92 3.75 94 2.04 34 16.4 119 1.99 33 2.83 43 4.83 60 2.43 48 2.28 120 4.02 125 3.38 119
CRTflow [80]82.5 3.65 77 14.0 91 3.10 66 2.16 47 7.88 45 2.23 39 2.25 68 11.2 78 1.99 32 1.56 71 12.7 91 1.35 72 4.02 67 5.53 87 3.01 70 6.86 136 19.6 132 8.64 138 3.29 65 5.53 88 3.23 76 2.05 111 3.95 124 2.71 108
DPOF [18]82.8 4.32 97 16.2 100 3.30 74 2.69 90 10.2 79 2.69 78 2.44 76 7.17 57 2.61 81 1.95 91 10.2 70 1.55 88 3.85 57 5.20 62 3.03 71 2.84 77 11.1 76 2.67 73 4.71 114 4.83 60 8.84 141 1.73 94 3.03 93 1.86 87
SRR-TVOF-NL [91]82.8 4.62 105 12.2 77 3.55 86 2.32 61 10.8 87 2.34 46 2.56 78 12.4 87 2.59 78 1.49 66 8.56 60 1.17 60 4.12 82 5.10 54 3.51 83 2.63 69 10.9 74 2.26 58 5.64 130 6.92 123 4.13 111 2.19 117 2.87 85 2.86 110
LocallyOriented [52]83.3 3.46 58 14.6 93 3.01 62 2.84 96 13.3 106 2.85 91 2.92 97 17.6 104 3.05 94 1.63 77 10.6 76 1.43 81 4.23 89 5.79 101 3.19 76 2.48 67 7.69 23 2.87 80 3.41 74 5.63 92 3.25 77 1.65 91 3.48 107 1.86 87
SIOF [67]84.1 4.00 89 8.74 54 3.46 82 2.00 33 13.6 107 2.13 35 3.02 102 15.7 100 3.38 100 2.55 107 13.5 95 2.50 108 4.27 92 5.70 96 3.70 89 3.55 94 11.5 82 4.01 108 3.17 61 4.64 51 2.12 30 1.85 103 3.29 101 2.15 100
Second-order prior [8]84.6 3.40 54 13.6 85 3.19 69 2.16 47 13.8 111 2.34 46 2.43 75 17.1 102 2.26 68 1.20 36 15.7 101 0.96 34 4.44 99 6.10 118 3.08 73 3.41 92 19.7 133 2.67 73 5.42 127 6.02 104 5.40 123 1.44 80 3.44 106 1.48 74
Brox et al. [5]85.0 4.01 90 14.7 95 4.49 105 2.75 94 11.5 97 3.21 98 2.33 72 12.2 86 2.34 72 1.46 61 19.9 114 1.19 62 4.62 109 5.71 97 4.89 122 2.13 38 13.3 99 2.28 60 2.87 45 4.78 57 1.55 11 2.30 122 3.68 117 3.31 117
Bartels [41]85.5 4.23 95 10.7 68 4.70 110 2.37 64 5.83 16 2.66 74 2.21 66 7.42 59 2.42 74 2.59 108 8.46 59 2.53 109 4.33 94 5.50 84 4.37 110 3.69 97 14.6 110 4.80 122 4.75 118 6.30 107 7.59 137 1.13 49 2.33 63 1.32 59
Dynamic MRF [7]86.3 4.55 104 13.6 85 5.02 112 1.81 21 8.86 56 1.82 19 2.13 61 12.6 89 1.87 25 1.62 74 13.2 93 1.45 84 4.61 107 5.80 104 4.32 108 4.14 108 21.3 135 4.42 113 3.22 64 4.41 32 5.01 122 2.11 113 3.92 123 3.51 120
CLG-TV [48]87.4 3.59 71 9.91 62 3.24 70 4.16 108 11.1 94 4.96 108 3.12 103 11.5 81 3.97 103 2.31 101 13.0 92 1.99 99 4.56 106 6.11 119 3.95 99 2.85 78 12.2 87 2.78 79 4.23 106 5.87 99 2.86 67 1.17 55 2.45 67 1.04 44
TriangleFlow [30]87.9 3.96 88 11.5 72 4.08 96 2.14 45 10.2 79 2.07 33 2.16 64 9.80 73 1.86 23 1.47 62 9.22 64 1.11 48 5.37 131 7.25 138 4.72 118 4.49 117 13.7 105 4.62 118 3.78 88 7.33 135 4.11 109 1.73 94 3.48 107 2.30 102
p-harmonic [29]88.3 4.47 102 14.4 92 4.52 106 2.71 92 9.33 71 2.89 93 3.40 104 15.0 97 3.02 93 1.93 90 24.1 121 1.59 89 4.15 84 5.18 61 3.66 88 3.37 91 16.0 115 3.54 98 3.90 91 5.36 82 2.71 64 1.29 63 2.41 66 1.38 66
Local-TV-L1 [65]88.8 4.95 107 13.2 82 5.40 115 4.37 110 14.6 114 5.04 110 4.59 111 17.8 106 5.96 112 2.42 104 16.9 110 2.25 104 3.68 50 5.03 50 2.82 56 2.25 50 10.6 68 2.24 55 2.55 28 4.37 28 2.91 71 2.73 129 4.10 127 7.77 135
FlowNetS+ft+v [112]89.0 3.42 56 13.4 84 3.39 80 2.54 77 11.2 95 2.80 84 2.94 98 18.6 110 4.76 105 1.43 56 27.4 124 1.20 63 4.67 112 6.35 127 3.71 90 1.96 28 12.3 89 2.01 35 4.10 100 6.00 102 4.11 109 1.76 97 3.49 110 2.37 104
CBF [12]89.7 3.59 71 10.5 67 3.68 90 4.72 112 10.4 82 6.02 117 2.28 70 9.24 67 2.96 92 1.63 77 12.2 88 1.36 74 4.48 103 5.75 99 3.99 101 2.70 73 10.7 71 2.48 69 6.13 138 7.02 125 5.92 129 1.45 81 2.65 77 1.66 79
DF-Auto [115]89.8 3.88 83 17.6 104 2.93 61 5.44 118 14.7 115 6.44 118 4.54 110 16.8 101 9.38 118 2.22 97 15.0 98 1.95 96 4.32 93 6.00 112 3.88 98 1.44 3 7.14 15 1.73 11 4.20 103 6.78 119 1.70 14 2.42 125 4.04 126 3.34 118
CNN-flow-warp+ref [117]89.9 3.90 85 19.8 118 3.73 91 3.40 102 10.9 90 4.21 104 3.85 108 23.8 123 6.07 113 1.65 80 22.4 119 1.37 75 4.38 98 5.58 90 4.08 102 2.23 46 13.8 106 2.33 65 2.41 24 4.27 19 2.24 34 2.43 126 3.66 116 3.64 124
SuperFlow [81]92.2 3.40 54 11.5 72 3.31 75 3.97 105 12.2 100 5.00 109 3.01 101 17.9 107 7.70 116 2.66 109 18.1 113 2.64 112 4.17 85 5.42 75 4.16 106 2.19 44 10.6 68 2.20 50 4.22 105 6.11 106 2.45 49 2.12 115 3.64 115 3.59 122
OFRF [134]93.3 4.35 98 9.74 60 4.34 100 5.12 116 13.1 105 5.68 115 3.74 107 14.7 96 5.10 106 2.91 111 11.0 81 2.84 114 3.34 39 4.74 44 2.24 25 3.34 90 9.46 49 3.23 90 3.67 84 5.54 89 5.56 127 3.05 133 3.88 121 9.53 140
StereoFlow [44]96.5 21.8 149 37.8 144 27.4 149 24.3 147 37.6 149 22.4 145 28.3 149 39.2 144 28.8 144 24.0 147 47.7 141 21.6 146 5.15 125 5.49 83 6.01 137 0.95 1 6.87 11 1.06 1 1.68 1 3.70 2 0.92 1 1.29 63 2.32 61 1.49 75
LiteFlowNet [142]96.6 6.43 115 24.0 125 4.45 103 3.74 104 10.4 82 3.78 101 4.32 109 15.2 99 3.78 101 2.36 102 8.74 61 1.97 98 4.88 119 6.06 115 4.38 111 4.23 111 14.0 107 3.68 103 3.56 80 5.59 91 1.98 22 1.70 92 2.79 83 1.83 85
TriFlow [95]97.3 4.44 99 13.8 89 3.62 89 3.16 100 9.65 75 3.81 102 2.89 96 19.6 113 6.36 114 2.48 106 7.88 54 2.33 105 4.37 97 5.44 78 4.28 107 2.98 81 8.42 30 3.07 87 11.7 148 7.70 138 21.5 148 1.76 97 2.98 91 1.94 91
Learning Flow [11]98.0 3.80 82 11.9 75 3.58 87 3.02 99 13.0 104 3.34 100 2.84 92 17.9 107 3.18 96 1.82 87 34.6 134 1.50 85 5.44 134 7.32 139 4.61 115 3.10 85 18.8 128 3.04 85 3.94 93 6.38 111 3.65 87 1.37 72 3.38 104 1.18 50
Fusion [6]98.2 3.76 81 16.9 101 4.07 95 1.99 32 7.37 41 2.26 41 2.07 57 8.51 64 2.28 69 1.59 72 24.8 122 1.37 75 5.00 123 6.36 128 4.98 127 4.70 121 16.2 118 5.01 125 6.00 137 7.50 137 4.38 117 2.97 132 3.74 120 3.55 121
ContinualFlow_ROB [152]99.3 7.09 121 26.0 129 5.87 119 6.48 123 13.6 107 7.04 123 7.43 121 21.2 118 9.67 119 3.12 113 10.8 78 2.57 111 5.41 133 6.38 129 4.71 116 6.48 135 15.7 113 7.64 136 2.20 7 4.02 7 1.33 5 1.42 78 2.40 65 1.64 78
Shiralkar [42]99.5 4.46 100 18.3 107 4.36 101 1.93 29 16.4 117 1.87 24 2.99 100 17.6 104 2.01 36 2.10 95 21.0 116 1.96 97 4.36 95 5.72 98 3.55 84 5.65 131 19.4 130 5.11 128 4.90 122 5.57 90 7.14 133 2.11 113 4.71 133 2.53 106
StereoOF-V1MT [119]102.2 4.46 100 18.0 106 4.46 104 2.09 39 18.6 123 1.79 18 3.70 106 20.6 116 2.13 57 2.18 96 25.0 123 1.91 95 5.52 136 6.98 136 4.82 120 5.01 127 25.8 140 4.73 119 3.21 63 5.27 81 3.64 86 2.32 123 4.64 131 2.83 109
EAI-Flow [151]103.3 7.60 123 21.3 120 6.38 121 4.08 106 15.8 116 4.21 104 5.17 113 18.4 109 5.60 110 3.05 112 15.7 101 2.94 116 4.45 100 5.81 105 3.60 87 4.33 112 12.6 91 4.10 109 5.63 128 6.30 107 3.58 84 1.33 66 2.55 70 1.43 69
SegOF [10]103.8 5.62 111 17.1 102 3.08 64 8.33 129 20.9 125 10.1 132 7.44 122 21.7 119 13.3 127 5.42 130 21.0 116 4.47 125 4.81 118 5.51 85 5.74 136 4.97 125 17.1 120 4.83 123 2.12 5 4.38 30 1.46 8 2.17 116 3.23 98 3.74 126
CompactFlow_ROB [159]104.3 9.64 134 29.9 136 5.40 115 6.23 122 12.8 103 6.77 121 8.77 128 20.9 117 16.5 132 3.26 115 11.9 86 2.83 113 5.24 128 6.31 125 4.71 116 4.38 114 14.5 108 4.74 120 2.21 8 4.89 68 1.06 2 1.86 105 3.34 103 1.83 85
WOLF_ROB [148]105.2 5.28 109 22.2 122 4.65 109 4.15 107 21.9 129 3.81 102 6.02 117 23.6 122 5.35 109 2.47 105 16.5 107 2.33 105 4.50 104 5.65 95 4.12 104 4.15 109 14.8 111 3.83 106 3.00 54 4.84 65 2.67 62 2.25 119 4.11 128 3.66 125
Ad-TV-NDC [36]106.7 8.75 129 15.3 99 12.3 140 10.5 136 24.2 135 12.3 136 8.96 130 28.2 127 11.5 121 5.31 129 22.8 120 5.55 130 4.03 69 5.79 101 2.86 58 2.80 75 10.0 61 2.87 80 3.04 56 4.52 39 2.66 61 4.62 140 5.79 140 30.9 148
AugFNG_ROB [143]107.8 7.79 124 28.5 134 5.02 112 9.56 133 18.5 122 11.3 135 8.78 129 26.2 124 17.3 135 3.46 118 9.97 68 2.86 115 5.26 129 6.24 123 4.77 119 4.44 115 14.5 108 4.15 110 2.99 53 5.22 79 1.30 4 1.85 103 3.18 96 2.10 98
Filter Flow [19]111.4 6.76 117 17.6 104 4.37 102 5.01 114 17.6 119 5.49 114 5.98 116 26.3 125 18.4 137 7.23 132 29.9 128 6.91 133 5.12 124 6.23 121 5.36 131 5.23 128 11.9 86 4.95 124 6.64 142 8.75 145 3.75 93 0.95 31 2.15 53 1.21 55
Modified CLG [34]111.6 6.79 118 24.7 126 6.63 123 7.09 125 17.4 118 9.40 129 10.1 131 29.2 129 16.6 133 4.48 126 27.5 125 3.86 121 4.80 116 6.31 125 4.48 114 2.65 71 17.6 123 2.69 77 2.92 51 4.94 70 2.07 26 3.19 135 5.17 136 5.78 131
LFNet_ROB [149]111.9 8.41 128 29.9 136 5.80 118 5.03 115 13.7 110 5.06 112 7.93 125 22.4 121 5.30 108 3.31 116 14.9 97 2.56 110 5.26 129 6.39 130 4.98 127 4.56 120 17.8 124 4.51 117 3.73 87 5.99 101 2.59 56 1.82 102 3.26 100 2.08 97
ResPWCR_ROB [144]112.7 8.23 126 22.9 123 6.93 124 4.20 109 12.3 102 4.43 107 5.27 114 15.1 98 5.64 111 3.74 120 17.2 112 3.36 119 4.79 115 5.55 88 5.34 130 4.99 126 13.6 103 5.09 127 4.72 115 6.59 118 2.89 68 2.38 124 3.59 113 2.92 112
IAOF2 [51]112.9 5.05 108 13.6 85 4.64 108 4.90 113 14.5 113 5.78 116 3.68 105 18.6 110 5.15 107 12.3 141 34.1 133 13.8 141 4.65 110 6.21 120 3.78 95 4.47 116 13.5 100 3.70 104 5.73 131 7.13 130 3.98 102 1.96 108 3.53 111 2.35 103
FlowNet2 [122]114.2 8.99 131 25.8 127 7.01 125 9.84 134 19.0 124 10.7 133 7.98 126 20.1 114 13.5 128 4.47 125 9.41 65 4.21 124 5.17 126 6.08 116 4.92 124 4.10 105 11.2 78 4.43 114 5.98 136 7.71 139 2.90 70 1.78 99 2.92 89 1.89 89
TVL1_ROB [138]114.5 13.5 140 26.7 131 16.1 144 14.6 140 23.8 134 16.6 141 16.9 139 36.5 140 25.4 142 11.9 140 33.8 130 12.8 139 4.66 111 6.23 121 3.96 100 2.38 59 16.0 115 2.89 82 2.32 20 4.57 42 1.49 9 5.63 144 6.44 141 12.6 143
EPMNet [133]114.5 8.88 130 26.2 130 7.20 128 9.32 132 18.2 120 10.0 131 7.14 119 18.8 112 12.3 124 4.79 127 12.3 89 4.62 128 5.17 126 6.08 116 4.92 124 4.10 105 11.2 78 4.43 114 4.88 121 7.05 127 2.56 53 1.93 107 3.57 112 2.07 96
BlockOverlap [61]114.8 6.80 119 12.1 76 5.94 120 5.51 119 13.6 107 6.58 119 5.32 115 22.2 120 7.30 115 4.20 121 16.7 109 4.06 123 4.45 100 5.39 74 5.11 129 4.91 123 12.5 90 4.34 112 6.77 144 7.13 130 9.52 143 2.02 109 3.24 99 9.49 139
HBpMotionGpu [43]115.7 5.92 113 15.0 97 4.79 111 7.78 127 22.4 131 9.04 128 7.17 120 39.2 144 17.3 135 3.31 116 13.4 94 3.14 118 4.71 113 5.88 106 4.84 121 3.74 99 13.5 100 3.54 98 5.96 135 7.17 132 3.68 88 2.24 118 3.43 105 4.65 127
2D-CLG [1]116.7 9.69 135 37.7 143 7.18 127 11.1 137 21.9 129 13.9 139 19.0 144 34.8 135 28.7 143 13.0 142 46.7 139 12.8 139 4.97 121 5.79 101 5.47 134 4.08 103 21.2 134 4.32 111 2.29 15 4.00 6 1.64 12 4.47 139 5.51 139 6.55 133
SPSA-learn [13]116.7 6.87 120 21.3 120 7.92 131 6.02 121 21.1 127 6.96 122 7.55 123 27.5 126 12.7 126 4.44 123 29.2 126 4.59 127 4.80 116 5.92 109 4.93 126 4.94 124 17.3 121 5.02 126 3.37 71 5.01 72 2.29 38 4.14 138 4.97 135 6.49 132
GraphCuts [14]117.2 6.34 114 17.1 102 5.55 117 5.30 117 20.9 125 5.26 113 6.05 118 20.4 115 12.4 125 2.85 110 20.9 115 2.15 102 4.74 114 5.95 110 4.90 123 8.69 140 12.6 91 5.19 129 5.79 132 6.40 112 6.80 132 2.45 127 3.48 107 3.59 122
GroupFlow [9]117.6 9.15 133 25.8 127 10.5 137 11.6 139 30.0 142 12.3 136 10.2 132 35.4 137 11.9 122 3.50 119 15.8 104 3.39 120 5.48 135 6.56 132 4.42 112 9.25 141 24.8 137 10.8 143 2.35 22 4.58 43 1.67 13 2.93 131 5.22 137 4.99 128
Black & Anandan [4]118.3 7.19 122 18.9 110 8.40 132 5.96 120 22.6 132 6.69 120 8.73 127 28.7 128 12.1 123 4.46 124 29.4 127 4.52 126 4.91 120 6.59 133 4.09 103 4.18 110 19.4 130 4.44 116 4.69 112 6.36 110 2.01 23 3.13 134 4.46 129 5.06 129
IAOF [50]119.4 6.54 116 18.3 107 7.13 126 6.99 124 18.4 121 7.90 126 7.71 124 32.3 132 8.44 117 8.21 135 31.8 129 9.78 137 4.61 107 6.01 113 4.14 105 4.35 113 18.9 129 3.43 95 4.69 112 6.08 105 3.31 79 3.23 136 4.69 132 15.9 146
2bit-BM-tele [98]122.5 8.99 131 18.6 109 10.2 135 4.45 111 11.3 96 5.04 110 4.66 112 17.3 103 4.41 104 5.23 128 21.7 118 5.04 129 4.99 122 5.96 111 5.46 133 6.47 134 18.3 125 7.49 135 7.77 146 8.57 144 12.5 146 2.29 121 3.89 122 2.99 115
Nguyen [33]125.1 8.16 125 23.0 124 7.57 130 16.5 143 22.7 133 19.3 143 16.8 138 36.0 138 20.7 140 13.8 143 39.5 135 14.7 143 5.40 132 6.44 131 6.70 138 4.54 119 18.5 127 5.42 130 3.50 78 5.02 73 2.08 27 4.00 137 5.50 138 8.53 137
UnFlow [129]125.2 19.4 148 44.0 148 10.2 135 11.3 138 21.2 128 12.4 138 18.1 141 36.0 138 15.5 130 7.47 134 34.0 132 6.40 132 7.10 143 7.11 137 8.76 143 8.31 139 24.8 137 9.26 139 5.13 123 6.50 115 1.52 10 1.57 87 3.14 95 2.01 94
Heeger++ [104]127.8 18.3 147 32.1 140 10.5 137 9.98 135 34.3 148 7.90 126 16.0 136 32.7 133 11.0 120 9.23 136 47.6 140 7.86 135 5.95 138 6.74 134 5.71 135 23.4 148 49.5 149 24.5 148 3.61 83 6.53 116 2.58 54 1.78 99 3.68 117 2.96 113
SILK [79]128.5 10.7 136 31.4 139 13.1 142 8.77 130 26.6 137 9.80 130 13.6 134 34.9 136 16.7 134 6.53 131 45.4 137 6.08 131 6.11 139 7.36 141 6.71 139 6.96 137 29.4 143 7.39 134 2.97 52 4.77 56 3.96 101 5.00 141 6.99 142 10.7 141
Horn & Schunck [3]129.3 8.40 127 27.2 132 9.62 133 7.28 126 28.3 139 7.55 125 13.3 133 31.9 131 15.8 131 7.35 133 48.5 142 7.69 134 5.84 137 7.34 140 5.45 132 5.80 132 25.8 140 6.79 133 5.25 125 7.11 129 2.11 29 5.21 142 8.30 144 6.66 134
FFV1MT [106]133.7 17.0 146 35.1 142 10.1 134 8.30 128 33.0 146 7.40 124 17.2 140 40.0 146 15.3 129 9.57 137 55.8 148 8.75 136 7.99 148 8.46 148 10.1 146 21.8 147 36.1 146 23.3 147 4.43 108 7.02 125 4.09 108 1.78 99 3.68 117 2.96 113
Periodicity [78]133.7 12.3 138 51.4 167 7.39 129 9.23 131 38.3 150 11.1 134 34.7 150 48.1 150 36.0 149 4.27 122 57.7 149 3.99 122 24.4 150 73.2 150 16.2 149 29.6 150 74.3 150 29.4 150 3.29 65 5.67 93 1.90 19 6.64 145 44.8 150 21.5 147
TI-DOFE [24]134.2 16.4 144 34.0 141 21.2 148 21.5 146 31.9 143 25.3 147 24.4 148 41.0 148 33.0 148 22.8 146 46.3 138 25.2 147 6.25 140 7.67 143 6.82 140 6.37 133 25.6 139 7.87 137 3.94 93 5.78 98 1.78 17 8.49 148 9.86 147 12.5 142
H+S_ROB [137]134.4 14.9 142 45.1 149 10.5 137 15.0 142 29.6 141 16.1 140 24.2 147 40.2 147 29.9 147 33.2 149 52.4 146 34.9 148 7.74 147 8.16 145 11.7 148 13.6 146 42.2 148 17.3 146 2.88 46 5.51 85 2.54 52 8.22 147 8.90 145 8.03 136
SLK [47]135.0 12.3 138 43.0 147 16.5 145 19.8 145 32.9 145 22.4 145 21.4 145 38.4 142 29.3 146 41.6 150 51.6 144 44.5 150 6.87 142 7.63 142 8.94 144 8.09 138 31.2 145 9.56 140 3.34 69 5.41 83 2.60 57 8.13 146 9.23 146 13.9 145
Adaptive flow [45]141.2 16.4 144 28.7 135 16.7 146 17.2 144 25.5 136 19.6 144 18.8 143 37.6 141 36.5 150 11.2 139 43.6 136 11.9 138 7.11 144 7.79 144 7.88 141 10.1 144 24.1 136 10.1 142 16.1 149 14.2 149 22.1 149 2.92 130 4.89 134 5.22 130
HCIC-L [99]142.0 24.1 150 31.3 138 12.9 141 27.6 149 28.7 140 69.9 150 16.0 136 30.6 130 23.1 141 18.1 145 55.4 147 17.8 145 7.39 145 8.35 147 8.32 142 12.6 145 18.3 125 14.4 145 25.6 150 23.8 150 23.6 150 2.62 128 4.51 130 9.36 138
PGAM+LK [55]142.8 14.0 141 40.6 145 18.8 147 14.9 141 33.1 147 17.8 142 14.4 135 32.9 134 19.3 138 15.7 144 63.6 150 14.9 144 6.36 141 6.81 135 9.14 145 9.83 143 30.7 144 9.83 141 10.4 147 12.2 148 10.3 144 5.30 143 7.26 143 13.0 144
FOLKI [16]143.1 11.0 137 41.0 146 14.5 143 24.9 148 32.3 144 36.7 148 18.7 142 43.8 149 20.5 139 10.9 138 50.5 143 13.8 141 7.42 146 8.28 146 10.6 147 9.75 142 36.9 147 12.1 144 4.77 120 7.29 134 11.0 145 12.2 149 11.4 148 36.4 149
Pyramid LK [2]146.1 15.8 143 28.2 133 30.4 150 35.8 150 28.0 138 49.6 149 22.3 146 38.6 143 29.1 145 31.8 148 51.7 145 39.0 149 18.3 149 24.8 149 24.1 150 26.7 149 28.6 142 26.7 149 7.19 145 8.98 146 7.70 139 32.7 150 40.6 149 57.0 150
AdaConv-v1 [126]151.1 45.2 151 50.1 150 46.0 151 78.3 151 79.6 151 76.9 151 78.3 151 73.0 151 77.6 151 79.2 151 80.8 151 79.6 151 83.7 151 84.3 151 83.6 151 82.1 151 80.6 151 81.5 151 69.6 152 58.5 152 75.3 152 84.4 151 84.7 151 83.9 151
SepConv-v1 [127]151.1 45.2 151 50.1 150 46.0 151 78.3 151 79.6 151 76.9 151 78.3 151 73.0 151 77.6 151 79.2 151 80.8 151 79.6 151 83.7 151 84.3 151 83.6 151 82.1 151 80.6 151 81.5 151 69.6 152 58.5 152 75.3 152 84.4 151 84.7 151 83.9 151
SuperSlomo [132]151.1 45.2 151 50.1 150 46.0 151 78.3 151 79.6 151 76.9 151 78.3 151 73.0 151 77.6 151 79.2 151 80.8 151 79.6 151 83.7 151 84.3 151 83.6 151 82.1 151 80.6 151 81.5 151 69.6 152 58.5 152 75.3 152 84.4 151 84.7 151 83.9 151
CtxSyn [136]151.1 45.2 151 50.1 150 46.0 151 78.3 151 79.6 151 76.9 151 78.3 151 73.0 151 77.6 151 79.2 151 80.8 151 79.6 151 83.7 151 84.3 151 83.6 151 82.1 151 80.6 151 81.5 151 69.6 152 58.5 152 75.3 152 84.4 151 84.7 151 83.9 151
CyclicGen [153]151.1 45.2 151 50.1 150 46.0 151 78.3 151 79.6 151 76.9 151 78.3 151 73.0 151 77.6 151 79.2 151 80.8 151 79.6 151 83.7 151 84.3 151 83.6 151 82.1 151 80.6 151 81.5 151 69.6 152 58.5 152 75.3 152 84.4 151 84.7 151 83.9 151
TOF-M [154]151.1 45.2 151 50.1 150 46.0 151 78.3 151 79.6 151 76.9 151 78.3 151 73.0 151 77.6 151 79.2 151 80.8 151 79.6 151 83.7 151 84.3 151 83.6 151 82.1 151 80.6 151 81.5 151 69.6 152 58.5 152 75.3 152 84.4 151 84.7 151 83.9 151
MPRN [155]151.1 45.2 151 50.1 150 46.0 151 78.3 151 79.6 151 76.9 151 78.3 151 73.0 151 77.6 151 79.2 151 80.8 151 79.6 151 83.7 151 84.3 151 83.6 151 82.1 151 80.6 151 81.5 151 69.6 152 58.5 152 75.3 152 84.4 151 84.7 151 83.9 151
DAIN [156]151.1 45.2 151 50.1 150 46.0 151 78.3 151 79.6 151 76.9 151 78.3 151 73.0 151 77.6 151 79.2 151 80.8 151 79.6 151 83.7 151 84.3 151 83.6 151 82.1 151 80.6 151 81.5 151 69.6 152 58.5 152 75.3 152 84.4 151 84.7 151 83.9 151
FRUCnet [157]151.1 45.2 151 50.1 150 46.0 151 78.3 151 79.6 151 76.9 151 78.3 151 73.0 151 77.6 151 79.2 151 80.8 151 79.6 151 83.7 151 84.3 151 83.6 151 82.1 151 80.6 151 81.5 151 69.6 152 58.5 152 75.3 152 84.4 151 84.7 151 83.9 151
OFRI [158]151.1 45.2 151 50.1 150 46.0 151 78.3 151 79.6 151 76.9 151 78.3 151 73.0 151 77.6 151 79.2 151 80.8 151 79.6 151 83.7 151 84.3 151 83.6 151 82.1 151 80.6 151 81.5 151 69.6 152 58.5 152 75.3 152 84.4 151 84.7 151 83.9 151
PyrWarp [161]151.1 45.2 151 50.1 150 46.0 151 78.3 151 79.6 151 76.9 151 78.3 151 73.0 151 77.6 151 79.2 151 80.8 151 79.6 151 83.7 151 84.3 151 83.6 151 82.1 151 80.6 151 81.5 151 69.6 152 58.5 152 75.3 152 84.4 151 84.7 151 83.9 151
FGME [163]151.1 45.2 151 50.1 150 46.0 151 78.3 151 79.6 151 76.9 151 78.3 151 73.0 151 77.6 151 79.2 151 80.8 151 79.6 151 83.7 151 84.3 151 83.6 151 82.1 151 80.6 151 81.5 151 69.6 152 58.5 152 75.3 152 84.4 151 84.7 151 83.9 151
MS-PFT [164]151.1 45.2 151 50.1 150 46.0 151 78.3 151 79.6 151 76.9 151 78.3 151 73.0 151 77.6 151 79.2 151 80.8 151 79.6 151 83.7 151 84.3 151 83.6 151 82.1 151 80.6 151 81.5 151 69.6 152 58.5 152 75.3 152 84.4 151 84.7 151 83.9 151
MEMC-Net+ [165]151.1 45.2 151 50.1 150 46.0 151 78.3 151 79.6 151 76.9 151 78.3 151 73.0 151 77.6 151 79.2 151 80.8 151 79.6 151 83.7 151 84.3 151 83.6 151 82.1 151 80.6 151 81.5 151 69.6 152 58.5 152 75.3 152 84.4 151 84.7 151 83.9 151
ADC [166]151.1 45.2 151 50.1 150 46.0 151 78.3 151 79.6 151 76.9 151 78.3 151 73.0 151 77.6 151 79.2 151 80.8 151 79.6 151 83.7 151 84.3 151 83.6 151 82.1 151 80.6 151 81.5 151 69.6 152 58.5 152 75.3 152 84.4 151 84.7 151 83.9 151
DSepConv [167]151.1 45.2 151 50.1 150 46.0 151 78.3 151 79.6 151 76.9 151 78.3 151 73.0 151 77.6 151 79.2 151 80.8 151 79.6 151 83.7 151 84.3 151 83.6 151 82.1 151 80.6 151 81.5 151 69.6 152 58.5 152 75.3 152 84.4 151 84.7 151 83.9 151
MAF-net [168]151.1 45.2 151 50.1 150 46.0 151 78.3 151 79.6 151 76.9 151 78.3 151 73.0 151 77.6 151 79.2 151 80.8 151 79.6 151 83.7 151 84.3 151 83.6 151 82.1 151 80.6 151 81.5 151 69.6 152 58.5 152 75.3 152 84.4 151 84.7 151 83.9 151
AVG_FLOW_ROB [141]165.9 85.5 168 80.5 168 99.9 168 99.9 168 99.9 168 99.9 168 96.1 168 99.9 168 95.9 168 89.9 168 87.4 168 95.1 168 99.9 168 99.9 168 99.9 168 95.8 168 81.5 168 91.9 168 39.9 151 40.1 151 34.2 151 99.9 168 99.9 168 99.9 168
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] MPRN 0.32 4 color Anonymous. (Interpolation results only.) Multi-frame pyramid refinement network for video frame interpolation. CVPR 2019 submission 1361.
[156] DAIN 0.13 2 color Anonymous. (Interpolation results only.) DAIN: Depth-aware video frame interpolation. CVPR 2019 submission 1769.
[157] FRUCnet 0.65 2 color V. T. Nguyen, K. Lee, and H.-J. Lee. (Interpolation results only.) A stacked deep MEMC network for frame rate up conversion and its application to HEVC. Submitted to IEEE TCSVT 2019.
[158] OFRI 0.31 2 color Anonymous. (Interpolation results only.) Efficient video frame interpolation via optical flow refinement. CVPR 2019 submission 6743.
[159] CompactFlow_ROB 0.05 2 color Anonymous. CompactFlow: spatially shiftable window revisited. CVPR 2019 submission 1387.
[160] SegFlow 3.2 2 color J. Chen, Z. Cai, J. Lai, and X. Xie. Efficient segmentation-based PatchMatch for large displacement optical flow estimation. IEEE TCSVT 2018.
[161] PyrWarp 0.14 2 color Anonymous. (Interpolation results only.) Video frame interpolation using differentiable forward-warping of feature pyramids. ICCV 2019 submission 741.
[162] HCFN 0.18 2 color Anonymous. Practical coarse-to-fine optical flow with deep networks. ICCV 2019 submission 116.
[163] FGME 0.23 2 color Anonymous. (Interpolation results only.) Fine-grained motion estimation for video frame interpolation. ICCV 2019 submission 4327.
[164] MS-PFT 0.44 2 color X. Cheng and Z. Chen. (Interpolation results only.) A multi-scale position feature transform network for video frame interpolation. Submitted to TCSVT 2019.
[165] MEMC-Net+ 0.12 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.
[166] ADC 0.01 2 color Anonymous. (Interpolation results only.) Learning spatial transform for video frame interpolation. ICCV 2019 submission 5424.
[167] DSepConv 0.3 2 color Anonymous. (Interpolation results only.) Video frame interpolation via deformable separable convolution. AAAI 2020 submission 2271.
[168] MAF-net 0.3 2 color Anonymous. (Interpolation results only.) MAF-net: Motion attention feedback network for video frame interpolation. AAAI 2020 submission 9862.
* 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.