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        
R1.0
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
NNF-Local [87]7.2 0.82 12 4.87 13 0.37 18 1.75 7 12.1 8 0.53 6 2.22 2 7.90 2 0.57 9 1.07 5 9.10 7 0.17 3 9.77 1 16.5 1 2.56 2 4.53 3 15.6 2 3.00 3 0.00 1 0.02 32 0.00 1 5.99 10 19.5 23 3.94 2
OFLAF [77]9.0 0.82 12 4.86 12 0.38 20 1.74 5 11.1 5 0.62 13 2.08 1 7.42 1 0.57 9 1.61 12 12.0 12 0.48 14 11.2 6 19.0 6 3.96 6 6.81 21 19.8 11 4.79 21 0.00 1 0.00 1 0.00 1 5.80 7 15.6 3 9.76 17
PMMST [114]9.4 0.65 2 3.86 2 0.05 1 2.23 18 13.5 16 1.21 35 2.81 8 9.66 8 0.83 15 1.29 7 6.70 3 0.42 12 11.7 7 19.1 7 5.55 10 5.50 8 17.8 6 4.52 13 0.00 1 0.02 32 0.00 1 5.44 4 15.8 4 5.70 6
NN-field [71]11.9 0.89 25 5.29 27 0.40 27 2.06 13 14.1 21 0.62 13 2.49 4 8.79 5 0.68 12 0.99 3 8.66 6 0.09 2 9.99 2 16.8 2 2.51 1 6.53 19 11.2 1 2.42 2 0.01 35 0.02 32 0.00 1 5.86 8 19.6 24 2.84 1
MDP-Flow2 [68]13.3 0.77 6 4.59 6 0.31 5 1.46 2 9.56 1 0.39 1 2.59 5 9.00 6 0.91 20 2.48 47 17.7 53 0.70 46 14.1 21 23.0 20 8.20 25 5.27 5 18.2 7 4.66 16 0.00 1 0.00 1 0.00 1 5.91 9 16.7 7 8.80 9
Correlation Flow [75]17.1 0.81 9 4.81 10 0.22 2 2.03 10 13.0 11 0.42 2 5.14 51 15.7 49 0.55 8 1.09 6 8.36 5 0.28 8 16.6 40 26.1 40 10.8 44 7.92 30 22.7 23 4.18 10 0.00 1 0.02 32 0.00 1 5.54 5 17.2 8 5.00 5
WLIF-Flow [93]17.4 0.84 17 4.97 18 0.34 11 2.03 10 13.3 14 0.76 21 3.64 19 12.0 17 1.41 32 2.23 35 14.4 26 0.55 20 13.1 13 21.6 13 7.54 18 8.23 36 20.9 15 5.39 29 0.00 1 0.00 1 0.00 1 6.94 16 18.0 12 10.4 23
NNF-EAC [103]22.7 0.81 9 4.82 11 0.39 25 1.95 9 12.0 7 0.83 24 3.16 11 10.6 11 1.00 22 2.60 51 18.5 56 0.77 51 13.9 18 22.8 19 7.86 20 6.67 20 19.3 9 5.14 27 0.10 50 0.02 32 0.00 1 7.08 19 19.2 18 10.5 24
ComponentFusion [96]23.8 0.98 48 5.81 55 0.37 18 1.59 4 10.7 4 0.53 6 2.84 9 9.86 9 0.85 18 1.94 19 13.3 15 0.54 19 15.3 34 24.9 34 10.5 43 6.83 22 26.2 47 5.50 32 0.03 43 0.00 1 0.32 53 6.69 12 18.5 14 9.59 13
TC/T-Flow [76]24.6 0.71 3 4.20 3 0.40 27 2.67 33 15.4 29 0.77 22 3.30 14 11.2 12 0.44 4 2.33 39 15.9 41 0.60 29 14.8 26 23.6 25 8.02 21 3.70 1 15.8 3 2.27 1 0.13 53 0.02 32 1.23 72 7.85 33 21.7 36 10.9 32
Layers++ [37]24.8 0.91 31 5.39 33 0.43 41 2.18 17 13.9 20 0.96 26 2.73 7 9.43 7 1.40 31 1.70 14 10.5 9 0.56 21 10.2 3 16.8 2 6.50 13 9.09 47 22.7 23 5.92 43 0.21 61 0.02 32 0.69 57 6.88 14 17.6 11 10.9 32
FC-2Layers-FF [74]25.8 0.87 22 5.16 23 0.42 36 2.70 35 17.8 41 1.20 33 2.59 5 8.73 4 1.39 30 1.88 17 13.3 15 0.50 15 11.1 5 18.0 5 6.07 11 9.16 50 21.3 17 5.89 41 0.04 46 0.02 32 0.22 51 7.48 26 19.4 21 11.1 37
AGIF+OF [85]26.2 0.90 27 5.34 29 0.42 36 3.13 47 19.3 50 1.37 40 3.87 23 12.8 20 1.80 45 2.19 32 14.3 24 0.64 34 12.4 9 20.6 9 7.20 16 9.27 52 22.4 20 5.97 47 0.00 1 0.00 1 0.00 1 7.26 22 18.8 16 10.7 29
IIOF-NLDP [131]27.3 1.01 53 5.97 59 0.24 4 2.82 38 17.3 38 0.66 16 4.36 40 14.3 37 0.43 3 0.99 3 7.36 4 0.24 7 15.0 29 24.3 29 6.98 14 9.70 62 24.0 35 6.32 62 0.01 35 0.02 32 0.00 1 7.22 21 19.9 26 7.14 8
LME [70]28.6 0.95 44 5.67 49 0.38 20 1.45 1 9.68 2 0.43 3 5.19 52 13.3 28 6.57 92 2.44 45 18.3 54 0.68 40 15.2 32 24.4 30 10.2 40 6.17 17 21.9 18 5.18 28 0.00 1 0.02 32 0.00 1 7.05 17 19.3 19 10.2 21
nLayers [57]30.0 0.88 23 5.25 25 0.44 45 2.79 37 15.6 33 1.47 45 4.34 39 14.4 38 2.33 59 1.54 10 11.6 11 0.52 18 10.4 4 17.1 4 5.51 9 8.89 42 19.3 9 5.79 40 0.31 72 0.00 1 1.16 70 7.27 23 19.3 19 11.3 43
ALD-Flow [66]30.0 0.79 7 4.72 9 0.38 20 2.44 29 13.5 16 0.80 23 4.33 38 14.7 42 0.88 19 2.92 66 19.4 60 0.82 55 17.5 43 28.1 44 10.0 38 5.61 10 24.7 40 3.10 4 0.00 1 0.00 1 0.00 1 9.09 47 26.3 53 11.9 53
MLDP_OF [89]30.5 0.94 41 5.51 44 0.36 16 1.74 5 11.7 6 0.44 5 4.05 29 13.1 25 0.50 7 1.48 9 12.3 13 0.29 9 15.4 35 24.7 33 9.15 30 5.54 9 18.2 7 3.11 5 1.54 110 0.05 92 9.31 117 8.33 39 21.4 35 9.39 12
3DFlow [135]31.3 0.92 37 5.49 41 0.34 11 2.26 19 15.2 27 0.54 9 3.57 17 12.4 18 0.47 5 0.31 1 3.40 1 0.01 1 13.6 15 22.2 16 7.25 17 12.2 95 27.4 57 7.12 84 2.77 120 0.02 32 10.0 118 5.36 3 15.8 4 4.88 4
PH-Flow [101]31.5 0.93 39 5.49 41 0.42 36 2.87 39 17.6 40 1.33 39 2.99 10 10.1 10 1.76 44 2.27 37 14.6 31 0.68 40 12.5 10 20.8 10 6.28 12 7.79 27 20.9 15 5.39 29 0.39 80 0.02 32 1.63 83 6.88 14 19.0 17 10.3 22
RNLOD-Flow [121]31.8 0.79 7 4.69 7 0.34 11 2.67 33 17.2 37 1.09 30 4.46 44 14.5 40 1.53 36 2.01 22 14.3 24 0.60 29 14.2 23 23.1 22 8.72 28 8.21 34 19.9 12 5.90 42 0.35 76 0.03 88 1.48 81 6.51 11 17.2 8 9.80 19
HAST [109]32.1 0.92 37 5.41 35 0.35 14 3.21 50 13.6 18 1.99 70 2.45 3 8.47 3 0.29 1 2.24 36 14.5 29 0.40 11 11.7 7 19.4 8 3.63 3 11.0 84 24.2 36 6.87 79 2.75 119 0.00 1 11.6 121 4.05 1 13.1 1 4.43 3
ProbFlowFields [128]34.1 1.16 71 6.86 79 0.85 93 2.32 21 14.6 23 1.45 43 4.28 36 14.9 44 2.43 62 1.56 11 9.89 8 0.50 15 18.1 47 29.1 49 11.5 48 4.44 2 20.6 13 4.20 11 0.00 1 0.02 32 0.00 1 8.97 45 25.7 48 9.75 15
IROF++ [58]34.4 0.96 45 5.70 53 0.44 45 3.00 44 19.4 51 1.37 40 3.90 25 12.8 20 1.96 50 2.36 42 15.8 40 0.69 44 14.1 21 23.0 20 8.22 26 9.14 49 25.0 41 6.07 53 0.00 1 0.02 32 0.00 1 7.35 24 20.3 28 10.8 30
Efficient-NL [60]34.7 0.93 39 5.47 40 0.39 25 2.76 36 18.0 43 1.11 31 4.12 33 13.3 28 1.15 25 2.15 29 14.1 22 0.66 36 13.0 12 21.3 12 7.16 15 10.6 77 23.4 29 6.41 68 0.26 66 0.02 32 1.13 68 7.35 24 17.4 10 10.9 32
TC-Flow [46]34.8 0.75 5 4.45 5 0.38 20 2.04 12 12.6 10 0.70 17 4.23 35 14.4 38 0.77 13 2.56 49 17.5 52 0.63 32 17.1 42 27.8 43 9.45 32 5.73 12 25.6 44 3.12 6 0.22 63 0.02 32 2.41 94 10.1 54 25.9 50 15.4 74
SVFilterOh [111]34.9 1.07 59 6.27 66 0.44 45 2.07 14 13.1 13 0.72 18 3.24 12 11.2 12 1.05 23 1.99 21 13.8 19 0.56 21 12.6 11 21.1 11 3.80 4 10.5 75 22.4 20 5.97 47 2.31 115 0.39 111 6.95 110 4.87 2 14.8 2 6.01 7
FESL [72]35.3 0.83 15 4.91 16 0.36 16 3.90 75 21.6 69 1.75 58 4.06 30 13.4 30 1.61 39 2.02 24 14.1 22 0.56 21 13.3 14 21.7 14 8.08 23 9.19 51 22.0 19 6.25 59 0.34 75 0.02 32 1.16 70 7.51 27 18.3 13 11.0 36
Classic+CPF [83]35.5 0.89 25 5.26 26 0.41 32 3.03 45 19.4 51 1.27 38 4.14 34 13.6 31 1.64 42 2.12 28 14.4 26 0.64 34 13.6 15 22.2 16 7.82 19 9.85 66 22.6 22 6.18 56 0.36 77 0.02 32 1.50 82 7.07 18 18.5 14 10.5 24
FMOF [94]36.6 0.83 15 4.92 17 0.43 41 3.35 57 20.0 56 1.57 52 3.37 16 11.4 15 1.46 34 1.98 20 13.8 19 0.56 21 14.2 23 23.2 23 8.08 23 9.98 70 22.7 23 6.19 57 0.42 83 0.02 32 1.87 88 8.11 38 21.0 32 10.5 24
HBM-GC [105]37.7 1.24 77 7.38 81 0.52 59 2.50 31 15.5 32 1.40 42 4.06 30 14.1 35 1.32 28 1.77 15 13.2 14 0.61 31 13.7 17 22.1 15 8.06 22 8.98 45 16.5 4 4.42 12 1.30 107 0.02 32 3.28 101 7.20 20 19.8 25 10.8 30
Aniso-Texture [82]38.1 0.73 4 4.33 4 0.33 8 1.83 8 12.4 9 0.91 25 6.29 62 18.2 56 1.57 37 1.35 8 11.4 10 0.18 5 19.7 60 29.7 51 16.8 78 9.10 48 26.1 46 5.78 39 0.26 66 0.18 99 0.07 42 9.32 49 24.3 47 12.2 54
Ramp [62]38.3 0.90 27 5.36 30 0.41 32 3.14 48 20.0 56 1.52 47 3.86 22 12.9 22 1.93 48 2.01 22 14.5 29 0.59 27 15.1 31 24.4 30 9.67 35 9.44 55 22.9 26 5.95 45 0.29 70 0.02 32 1.38 77 7.83 32 20.9 30 11.5 46
Sparse-NonSparse [56]38.5 0.88 23 5.21 24 0.40 27 3.16 49 19.8 55 1.53 50 3.90 25 12.9 22 2.00 52 2.18 31 15.2 37 0.66 36 15.6 36 25.4 37 10.1 39 9.38 54 23.7 33 5.97 47 0.31 72 0.00 1 1.28 73 7.74 29 20.9 30 11.2 41
PMF [73]38.7 1.08 60 6.23 64 0.35 14 2.33 22 14.8 24 0.60 11 3.87 23 13.6 31 0.62 11 2.29 38 14.4 26 0.44 13 14.0 20 23.3 24 3.86 5 9.55 56 28.3 67 6.63 73 0.89 101 0.79 121 3.74 105 5.66 6 15.8 4 8.92 10
CombBMOF [113]39.1 0.91 31 5.38 31 0.33 8 2.30 20 13.4 15 0.64 15 3.33 15 11.5 16 0.78 14 2.08 26 15.3 38 0.77 51 13.9 18 22.3 18 8.24 27 13.0 104 26.2 47 11.4 111 0.56 88 0.02 32 0.86 62 8.93 44 21.1 33 15.6 75
NL-TV-NCC [25]40.2 0.96 45 5.68 50 0.22 2 2.93 41 18.4 45 0.59 10 4.37 42 14.6 41 0.47 5 1.63 13 14.6 31 0.17 3 18.6 49 29.8 52 9.76 37 11.8 94 31.2 89 7.70 93 0.12 51 0.00 1 0.30 52 9.40 51 26.0 52 9.75 15
LSM [39]40.6 0.86 21 5.13 22 0.40 27 3.22 51 20.3 59 1.54 51 4.08 32 13.6 31 1.93 48 2.09 27 14.9 35 0.63 32 15.6 36 25.3 36 10.2 40 9.58 57 24.6 37 5.95 45 0.30 71 0.02 32 1.43 78 7.97 34 21.7 36 11.1 37
OFH [38]41.9 0.81 9 4.70 8 0.31 5 2.96 43 17.3 38 1.20 33 6.37 64 19.7 62 1.51 35 2.92 66 20.6 68 0.91 57 20.7 69 32.4 72 14.2 61 6.39 18 31.5 90 3.74 9 0.00 1 0.00 1 0.00 1 11.0 60 33.0 78 12.8 57
Sparse Occlusion [54]42.0 0.90 27 5.06 21 0.46 50 2.35 24 14.9 26 1.01 27 4.83 47 15.7 49 1.09 24 2.38 43 17.2 50 0.66 36 16.7 41 26.9 41 8.75 29 7.98 31 24.6 37 5.42 31 0.60 92 0.61 117 0.84 60 8.41 42 22.7 40 10.5 24
Classic+NL [31]42.3 0.91 31 5.38 31 0.45 49 3.22 51 20.4 60 1.49 46 3.97 27 13.1 25 1.97 51 2.33 39 15.0 36 0.68 40 14.9 27 24.0 27 10.2 40 9.83 63 23.9 34 6.24 58 0.33 74 0.02 32 1.28 73 7.80 31 21.2 34 11.1 37
MDP-Flow [26]42.9 0.84 17 5.01 19 0.47 51 2.37 25 13.0 11 1.76 59 4.04 28 14.0 34 2.72 67 2.70 55 21.0 69 0.98 62 18.0 46 28.5 46 13.1 57 8.58 40 26.6 51 5.71 36 0.00 1 0.02 32 0.00 1 12.4 75 31.9 69 16.2 79
EPPM w/o HM [88]43.0 1.16 71 5.61 47 0.33 8 2.33 22 15.4 29 0.60 11 4.28 36 14.7 42 0.32 2 2.20 33 14.7 33 0.59 27 14.3 25 23.6 25 5.47 8 12.2 95 29.9 81 7.04 81 2.28 114 0.03 88 6.80 109 6.72 13 19.4 21 8.96 11
CostFilter [40]45.8 1.14 67 6.62 72 0.40 27 2.38 26 14.8 24 0.53 6 3.58 18 12.5 19 0.84 16 2.62 52 17.3 51 0.51 17 14.9 27 24.9 34 4.14 7 9.99 71 29.2 76 6.06 52 1.38 108 0.81 122 6.01 108 8.00 35 23.2 44 9.84 20
OAR-Flow [125]46.3 1.00 50 5.81 55 0.55 68 3.94 77 18.5 46 1.99 70 6.44 66 20.5 66 2.66 66 2.84 63 18.5 56 0.71 48 18.9 53 30.1 56 11.2 45 5.95 15 26.2 47 3.42 8 0.00 1 0.00 1 0.00 1 9.00 46 26.4 54 12.2 54
Complementary OF [21]46.8 0.91 31 5.39 33 0.43 41 2.42 28 15.2 27 0.74 19 4.36 40 15.5 47 1.16 26 2.63 53 19.5 61 0.76 50 22.5 86 33.0 77 20.1 85 9.92 68 28.5 70 4.80 22 0.00 1 0.00 1 0.00 1 12.6 78 35.6 97 16.9 82
S2D-Matching [84]48.2 1.09 62 6.39 69 0.51 57 3.35 57 20.9 62 1.52 47 5.55 55 17.8 55 2.21 55 1.91 18 13.6 18 0.56 21 15.2 32 24.5 32 9.72 36 10.1 73 23.6 31 6.34 64 0.52 85 0.02 32 2.09 92 7.62 28 20.0 27 11.6 49
COFM [59]48.9 1.15 68 6.80 77 0.58 76 2.62 32 15.8 35 1.25 37 5.68 57 18.2 56 2.12 53 2.20 33 13.5 17 0.58 26 19.6 59 31.0 64 15.7 73 9.91 67 23.3 28 6.03 51 0.81 98 0.00 1 1.43 78 7.76 30 20.7 29 10.6 28
SimpleFlow [49]49.2 0.94 41 5.57 46 0.44 45 3.52 61 21.7 70 1.79 62 5.82 58 17.6 54 2.36 60 2.55 48 16.5 44 0.81 54 16.3 39 26.0 38 11.8 49 10.3 74 23.1 27 6.33 63 0.24 64 0.00 1 0.81 59 8.33 39 22.7 40 11.5 46
IROF-TV [53]49.2 1.10 64 6.24 65 0.57 73 3.29 56 21.5 67 1.72 57 4.40 43 14.2 36 1.87 47 3.04 70 21.7 75 1.11 66 16.2 38 26.0 38 11.3 47 9.60 59 32.4 95 5.72 37 0.00 1 0.02 32 0.00 1 8.00 35 22.4 39 11.2 41
2DHMM-SAS [92]49.6 0.91 31 5.42 36 0.41 32 3.67 68 21.9 72 1.52 47 5.62 56 16.1 51 2.28 58 2.44 45 15.9 41 0.72 49 15.0 29 24.2 28 9.48 33 11.1 87 25.1 43 6.36 66 0.38 79 0.02 32 1.67 85 8.04 37 21.7 36 11.7 50
ACK-Prior [27]49.7 0.82 12 4.87 13 0.32 7 2.12 16 13.7 19 0.43 3 3.68 20 12.9 22 0.92 21 1.77 15 14.0 21 0.19 6 19.5 58 28.2 45 16.7 77 12.3 98 29.1 75 7.52 91 2.44 117 0.30 106 8.47 116 13.9 85 30.2 65 18.0 85
ROF-ND [107]51.0 1.27 82 6.15 63 0.38 20 4.71 85 18.9 48 1.07 29 4.89 48 15.6 48 1.21 27 0.65 2 6.22 2 0.29 9 19.7 60 30.5 59 14.5 63 11.5 92 26.5 50 6.25 59 0.39 80 0.02 32 0.84 60 12.3 74 31.5 67 13.8 65
TV-L1-MCT [64]52.3 0.90 27 5.30 28 0.41 32 3.73 69 22.1 73 1.79 62 4.61 46 15.3 45 1.63 41 2.16 30 14.7 33 0.67 39 17.6 44 27.1 42 15.2 69 11.0 84 25.0 41 6.58 72 0.36 77 0.02 32 2.46 96 9.73 52 23.0 42 16.2 79
RFlow [90]54.0 0.91 31 5.43 37 0.47 51 2.46 30 15.6 33 1.13 32 6.42 65 19.3 61 1.66 43 2.77 58 21.4 73 1.16 69 20.7 69 31.7 68 18.0 83 9.69 61 30.4 82 6.14 54 0.01 35 0.02 32 0.15 46 10.9 59 30.0 64 13.1 60
S2F-IF [123]55.5 1.28 84 7.44 85 0.84 92 3.48 60 22.4 76 1.86 66 5.52 53 19.0 58 3.05 68 2.96 68 16.9 48 1.21 71 21.3 76 34.1 86 14.5 63 5.45 6 25.6 44 4.62 14 0.00 1 0.00 1 0.00 1 12.0 70 32.3 73 14.7 68
Occlusion-TV-L1 [63]55.8 0.98 48 5.50 43 0.48 53 3.25 53 19.5 53 1.82 65 7.36 78 21.2 74 2.44 63 2.73 56 20.4 66 0.93 60 20.5 66 32.1 69 15.5 71 8.22 35 28.1 63 6.69 75 0.00 1 0.00 1 0.00 1 13.1 82 33.5 85 15.9 78
DPOF [18]55.8 1.11 65 6.56 71 0.53 61 4.51 83 21.0 63 2.42 81 3.25 13 11.3 14 0.84 16 2.03 25 15.3 38 0.70 46 17.8 45 28.8 47 9.36 31 11.4 91 26.9 52 6.26 61 4.21 124 0.02 32 10.5 120 10.2 55 26.7 55 11.8 51
DeepFlow2 [108]55.9 1.04 56 5.76 54 0.54 66 3.86 73 19.7 54 2.02 73 6.79 69 20.5 66 3.55 73 3.64 80 22.5 78 1.44 77 18.8 51 30.1 56 12.0 51 7.01 24 27.7 60 4.65 15 0.00 1 0.02 32 0.00 1 12.6 78 32.0 71 16.9 82
FlowFields+ [130]57.9 1.31 86 7.52 87 0.92 99 3.61 64 23.0 79 1.98 69 6.08 59 20.6 68 3.39 71 2.82 61 16.4 43 1.23 72 21.4 79 34.3 89 14.1 59 5.45 6 27.5 59 4.68 18 0.00 1 0.02 32 0.00 1 11.3 62 33.1 81 11.4 44
TF+OM [100]58.9 1.11 65 6.49 70 0.69 84 2.94 42 16.8 36 1.78 60 7.92 82 20.7 70 9.65 94 2.85 64 20.5 67 1.05 65 22.0 84 32.2 70 20.3 86 8.74 41 28.3 67 4.67 17 0.00 1 0.02 32 0.00 1 12.1 72 30.5 66 15.8 77
AggregFlow [97]60.0 1.68 100 9.22 106 0.86 95 4.76 86 25.3 91 2.56 84 7.33 77 22.6 82 5.07 88 2.64 54 16.5 44 0.69 44 19.1 56 30.7 61 11.2 45 5.11 4 17.3 5 3.29 7 0.14 55 0.02 32 0.96 65 9.35 50 25.7 48 13.1 60
Steered-L1 [118]60.1 0.63 1 3.72 1 0.42 36 1.53 3 10.4 3 0.75 20 3.84 21 13.2 27 1.32 28 2.80 59 21.1 71 0.98 62 21.2 75 31.2 65 20.3 86 10.7 81 29.3 78 7.45 90 4.27 125 0.34 108 19.6 127 16.5 94 33.3 82 24.6 100
FlowFields [110]60.2 1.32 87 7.63 89 0.93 101 3.61 64 22.9 78 2.00 72 6.11 60 20.6 68 3.58 74 2.85 64 16.6 46 1.24 73 21.9 83 35.0 98 15.1 68 5.70 11 28.0 62 4.72 19 0.00 1 0.02 32 0.00 1 11.7 65 33.4 83 11.5 46
CRTflow [80]60.4 1.02 55 5.69 51 0.58 76 3.12 46 18.1 44 1.46 44 6.89 71 20.9 72 2.40 61 3.38 76 22.2 76 1.42 76 19.7 60 31.3 66 12.3 52 11.0 84 35.9 107 10.1 106 0.00 1 0.00 1 0.00 1 12.0 70 33.6 86 14.7 68
ComplOF-FED-GPU [35]61.2 0.85 19 5.04 20 0.42 36 3.90 75 21.4 65 1.78 60 4.90 49 16.8 52 1.41 32 3.18 72 21.1 71 1.03 64 21.6 81 33.8 84 15.4 70 10.8 82 34.7 105 5.93 44 0.12 51 0.02 32 1.43 78 11.9 67 34.2 89 15.3 72
TCOF [69]61.4 1.00 50 5.63 48 0.59 79 3.53 62 21.5 67 1.69 56 7.64 80 22.0 78 3.79 77 2.80 59 19.9 64 0.77 51 21.1 73 32.7 74 13.9 58 7.79 27 20.7 14 5.77 38 0.92 102 0.03 88 3.23 100 8.40 41 23.2 44 11.4 44
Adaptive [20]63.1 1.05 57 6.01 60 0.48 53 3.27 54 20.1 58 1.79 62 7.11 74 20.1 63 1.62 40 3.29 74 22.4 77 1.15 68 18.8 51 29.8 52 12.6 54 10.6 77 28.4 69 6.72 77 0.57 91 0.71 120 0.96 65 8.64 43 23.1 43 10.9 32
SRR-TVOF-NL [91]63.9 1.15 68 6.13 62 0.60 80 5.04 88 23.3 81 2.68 86 8.17 83 22.9 83 4.22 85 2.76 57 16.9 48 0.68 40 19.8 63 29.0 48 17.7 82 8.07 32 27.0 54 6.17 55 0.16 57 0.02 32 0.86 62 11.8 66 25.9 50 15.3 72
DeepFlow [86]65.2 1.19 73 6.04 61 0.57 73 4.41 80 21.3 64 2.41 80 8.35 86 22.9 83 6.63 93 4.03 89 24.5 86 1.69 85 19.0 55 30.9 62 11.8 49 7.29 25 29.5 80 4.88 23 0.00 1 0.02 32 0.00 1 15.7 93 35.1 95 23.4 97
TV-L1-improved [17]65.5 0.94 41 5.45 38 0.52 59 2.91 40 17.8 41 1.58 53 7.00 72 20.2 65 2.24 57 3.00 69 21.5 74 1.16 69 20.6 67 32.3 71 15.0 66 12.2 95 34.2 103 7.87 94 0.19 59 0.30 106 0.49 55 10.7 57 29.7 63 12.8 57
PGM-C [120]66.5 1.52 93 8.68 99 0.99 106 3.66 66 23.0 79 2.03 74 6.30 63 21.2 74 3.90 79 3.82 85 22.9 82 1.68 84 21.3 76 34.3 89 14.1 59 6.89 23 28.8 72 5.60 34 0.00 1 0.02 32 0.00 1 11.9 67 34.3 90 14.2 67
Aniso. Huber-L1 [22]67.7 1.06 58 5.69 51 0.65 81 5.24 89 25.4 92 3.29 90 8.19 84 21.4 77 4.09 83 3.10 71 21.0 69 0.97 61 18.5 48 29.1 49 12.6 54 9.08 46 27.0 54 5.56 33 0.68 94 0.08 96 2.93 99 9.25 48 24.1 46 11.8 51
CPM-Flow [116]68.9 1.53 94 8.72 101 0.98 103 3.74 70 23.5 82 2.08 75 6.22 61 20.9 72 3.88 78 3.78 83 22.5 78 1.64 82 21.3 76 34.4 91 14.2 61 7.87 29 28.8 72 6.40 67 0.00 1 0.02 32 0.00 1 12.5 77 35.6 97 14.9 70
Classic++ [32]69.1 1.00 50 5.92 58 0.56 70 3.28 55 19.2 49 1.87 67 6.88 70 20.7 70 3.38 70 3.41 78 23.6 84 1.30 74 20.8 71 33.2 80 15.0 66 10.0 72 31.8 92 6.69 75 0.66 93 0.02 32 2.59 97 11.3 62 29.5 60 13.5 63
Bartels [41]70.0 1.28 84 7.59 88 0.50 55 2.39 27 15.4 29 1.04 28 5.52 53 19.2 59 2.54 65 2.83 62 19.9 64 1.30 74 22.7 89 34.1 86 20.4 88 9.92 68 30.5 83 6.93 80 1.88 113 0.02 32 12.3 122 12.7 80 31.9 69 16.4 81
CBF [12]70.0 0.85 19 4.89 15 0.43 41 4.99 87 22.3 75 4.63 97 6.60 67 19.2 59 4.08 82 3.61 79 24.5 86 1.49 78 20.0 64 30.9 62 16.2 75 9.67 60 27.4 57 5.64 35 2.65 118 0.37 109 6.97 111 11.5 64 28.4 59 16.9 82
EpicFlow [102]71.1 1.51 91 8.63 98 0.98 103 3.76 71 23.5 82 2.11 76 7.14 75 23.6 87 3.97 81 3.79 84 22.6 80 1.64 82 21.5 80 34.4 91 14.8 65 8.97 44 29.2 76 6.53 69 0.00 1 0.02 32 0.00 1 12.4 75 34.5 91 15.2 71
LocallyOriented [52]72.1 1.78 107 9.64 109 0.77 89 6.11 97 28.2 98 3.79 94 10.9 94 28.0 100 5.52 90 3.28 73 19.5 61 1.55 79 22.8 90 33.9 85 17.6 81 9.84 65 24.6 37 6.63 73 0.00 1 0.00 1 0.00 1 11.9 67 29.6 62 15.7 76
CLG-TV [48]73.2 1.01 53 5.46 39 0.50 55 4.16 79 23.5 82 2.40 79 7.52 79 21.2 74 2.51 64 3.33 75 22.8 81 1.14 67 20.9 72 32.4 72 15.6 72 8.94 43 31.7 91 6.35 65 1.27 106 1.18 125 3.55 103 11.1 61 28.2 58 13.5 63
TriangleFlow [30]74.1 1.19 73 6.73 76 0.53 61 3.88 74 21.8 71 1.64 55 6.61 68 20.1 63 1.59 38 2.35 41 19.3 59 0.89 56 25.6 101 37.3 106 23.5 100 13.4 106 30.5 83 8.48 101 0.81 98 0.17 98 1.33 76 10.7 57 28.1 57 13.1 60
Fusion [6]74.3 1.15 68 6.83 78 0.71 86 2.10 15 14.5 22 1.23 36 4.58 45 15.4 46 3.60 75 3.73 82 27.2 96 2.38 92 23.9 94 33.7 82 26.4 105 8.36 37 27.3 56 7.11 83 1.00 103 0.64 119 2.66 98 14.5 90 34.0 88 18.7 87
Rannacher [23]74.6 1.09 62 6.27 66 0.54 66 3.77 72 22.1 73 2.27 77 7.89 81 22.4 80 3.34 69 3.67 81 23.5 83 1.61 80 21.1 73 33.1 78 15.8 74 12.9 102 35.4 106 7.98 95 0.43 84 0.02 32 1.63 83 10.5 56 29.5 60 12.8 57
SIOF [67]74.9 1.24 77 6.63 73 0.51 57 5.26 90 26.2 93 3.22 89 11.5 95 26.1 91 12.3 97 4.49 92 27.4 99 2.29 90 22.8 90 33.3 81 23.4 99 8.56 39 28.8 72 7.15 85 0.00 1 0.02 32 0.00 1 13.6 84 32.1 72 23.6 99
F-TV-L1 [15]75.9 1.22 75 6.63 73 0.53 61 5.86 95 24.8 89 3.51 93 9.25 89 23.4 86 3.44 72 3.91 86 24.9 88 1.61 80 20.3 65 31.5 67 16.2 75 11.3 89 30.9 87 7.40 89 0.15 56 0.47 114 0.17 47 9.88 53 27.6 56 11.1 37
Local-TV-L1 [65]77.5 1.57 95 7.45 86 0.67 83 7.93 101 28.0 97 5.97 102 12.9 102 26.6 93 12.2 96 6.04 107 31.1 106 3.55 106 18.7 50 29.9 55 12.9 56 9.33 53 28.1 63 5.97 47 0.00 1 0.02 32 0.00 1 21.0 110 37.7 102 37.5 115
p-harmonic [29]78.0 1.08 60 6.28 68 0.55 68 3.66 66 20.5 61 2.48 83 8.22 85 23.0 85 3.92 80 5.04 96 28.4 102 3.51 104 24.8 98 34.1 86 30.1 108 7.78 26 32.3 94 6.54 70 0.19 59 0.44 113 0.00 1 14.2 89 33.0 78 21.8 93
OFRF [134]78.5 1.68 100 8.84 103 0.73 87 12.5 111 28.4 100 11.9 112 12.8 101 24.7 88 13.6 99 4.30 91 18.9 58 2.52 93 18.9 53 30.4 58 9.65 34 11.5 92 27.9 61 5.03 26 0.13 53 0.00 1 0.71 58 20.9 109 32.7 77 40.3 118
BriefMatch [124]78.9 0.96 45 5.52 45 0.53 61 3.55 63 18.6 47 1.97 68 4.95 50 16.9 53 1.82 46 2.57 50 19.7 63 0.92 59 21.8 82 32.7 74 20.8 91 16.2 115 33.7 101 13.5 117 3.95 123 0.97 124 15.8 123 17.3 99 34.7 93 25.4 102
TriFlow [95]80.8 1.51 91 8.71 100 0.78 90 4.56 84 22.8 77 3.37 92 12.5 99 28.2 101 17.8 102 2.41 44 18.3 54 0.91 57 24.8 98 34.4 91 25.7 103 5.97 16 23.5 30 4.74 20 19.3 131 0.27 104 59.0 131 13.2 83 32.5 75 14.1 66
Dynamic MRF [7]81.0 1.26 80 7.42 83 0.57 73 3.39 59 21.4 65 1.58 53 7.00 72 22.5 81 2.22 56 3.40 77 24.1 85 1.69 85 25.9 106 37.6 107 24.8 102 14.4 110 41.5 116 9.85 105 0.09 49 0.00 1 0.96 65 19.2 105 39.4 107 25.5 103
DF-Auto [115]81.6 1.84 108 8.87 104 0.90 96 8.40 102 30.1 102 6.82 103 13.3 103 27.9 99 19.6 103 5.29 98 26.6 92 3.01 97 22.2 85 32.9 76 21.0 92 5.80 13 23.6 31 5.02 25 0.18 58 0.61 117 0.00 1 14.8 91 32.4 74 19.9 88
Brox et al. [5]83.9 1.22 75 6.66 75 0.70 85 4.15 78 24.3 87 2.39 78 7.21 76 22.1 79 4.18 84 4.91 94 26.3 91 2.65 94 26.2 109 35.7 102 31.4 110 10.5 75 33.4 100 7.34 88 0.01 35 0.13 97 0.00 1 17.1 98 39.1 106 23.0 96
FlowNet2 [122]85.1 2.63 114 12.9 116 1.14 111 17.9 115 43.1 116 16.1 117 17.0 107 32.9 107 25.3 115 3.92 87 16.7 47 2.16 88 25.8 104 40.2 114 17.0 79 10.6 77 28.2 65 8.09 96 0.02 40 0.00 1 0.20 49 12.2 73 34.5 91 9.71 14
SuperFlow [81]86.4 1.26 80 5.91 57 0.66 82 6.58 99 24.8 89 5.70 101 12.7 100 26.7 94 20.1 104 5.60 102 28.6 103 3.33 101 24.6 97 33.7 82 31.7 113 8.09 33 30.8 86 7.19 86 0.02 40 0.07 94 0.02 41 16.6 95 37.3 100 22.5 94
EPMNet [133]88.1 2.58 113 13.6 117 1.08 108 17.2 114 45.9 118 14.3 114 15.3 106 31.5 106 21.6 107 4.71 93 24.9 88 2.35 91 25.8 104 40.2 114 17.0 79 10.6 77 28.2 65 8.09 96 0.01 35 0.00 1 0.10 44 15.0 92 44.1 115 9.78 18
Second-order prior [8]90.2 1.24 77 6.93 80 0.58 76 5.26 90 27.0 95 3.34 91 9.68 91 26.8 95 5.39 89 4.25 90 26.1 90 2.25 89 22.5 86 34.4 91 19.0 84 12.9 102 41.2 115 8.26 100 1.14 105 0.07 94 2.41 94 12.7 80 32.5 75 18.2 86
SegOF [10]92.4 1.62 98 9.24 107 1.14 111 14.8 113 38.8 113 14.3 114 17.8 109 33.2 108 22.3 109 6.57 108 27.5 100 4.43 109 32.5 119 41.8 118 43.4 123 14.1 109 38.0 110 10.5 107 0.00 1 0.00 1 0.00 1 14.0 86 33.7 87 12.6 56
StereoOF-V1MT [119]93.2 1.42 90 8.08 94 0.56 70 6.56 98 34.1 108 2.73 87 10.0 93 29.8 103 2.19 54 4.91 94 34.6 111 2.66 95 31.4 118 44.5 120 31.4 110 15.8 114 48.0 122 11.6 112 0.05 47 0.00 1 0.52 56 24.0 113 48.7 120 28.5 106
Shiralkar [42]93.8 1.27 82 7.43 84 0.53 61 5.83 94 30.1 102 2.93 88 9.62 90 26.2 92 3.70 76 5.11 97 30.7 105 3.08 98 25.7 102 39.1 111 22.5 97 17.9 116 45.5 118 9.73 104 1.80 111 0.00 1 8.23 115 18.4 103 44.9 116 19.9 88
FlowNetS+ft+v [112]94.8 1.40 89 7.39 82 0.80 91 5.75 93 23.6 85 4.35 96 11.7 97 27.3 97 12.4 98 5.33 99 27.2 96 3.18 100 25.7 102 35.4 101 26.9 106 8.52 38 32.0 93 6.85 78 2.34 116 1.61 128 10.1 119 14.0 86 34.9 94 20.1 91
CNN-flow-warp+ref [117]95.2 1.63 99 9.14 105 0.91 98 5.41 92 24.0 86 4.66 98 11.6 96 29.8 103 10.7 95 5.59 101 27.1 95 3.43 102 26.6 111 36.0 103 31.5 112 11.3 89 33.1 98 7.62 92 0.03 43 0.25 102 0.07 42 20.4 107 40.5 110 28.3 105
Learning Flow [11]95.9 1.35 88 7.83 91 0.56 70 4.48 82 26.8 94 2.43 82 9.85 92 27.1 96 5.06 87 6.65 109 33.5 109 4.13 107 29.9 115 40.0 113 34.1 117 12.8 100 38.5 112 8.86 103 0.28 69 0.29 105 1.13 68 17.0 97 37.6 101 22.8 95
Ad-TV-NDC [36]96.0 3.59 119 8.26 95 6.67 128 21.3 119 38.0 111 22.4 122 19.7 112 33.6 109 21.8 108 13.5 114 33.9 110 15.0 115 19.4 57 30.6 60 12.5 53 9.58 57 28.6 71 6.54 70 0.21 61 0.37 109 0.17 47 28.1 119 43.2 113 47.4 125
StereoFlow [44]96.0 7.67 129 21.8 126 3.86 125 51.5 131 74.0 132 46.2 128 43.7 132 63.5 132 36.8 125 51.6 131 79.4 132 47.5 130 26.1 107 38.0 108 21.1 93 5.83 14 26.9 52 4.93 24 0.00 1 0.02 32 0.00 1 20.7 108 38.1 104 29.7 107
2bit-BM-tele [98]96.4 1.75 103 9.59 108 0.85 93 4.44 81 24.7 88 2.62 85 8.64 87 25.8 90 4.56 86 3.99 88 27.8 101 1.98 87 22.6 88 33.1 78 20.5 89 14.6 111 32.7 97 10.7 108 5.96 128 1.68 129 21.9 129 14.1 88 33.4 83 19.9 88
LDOF [28]97.0 1.59 97 8.06 92 0.97 102 6.08 96 27.9 96 3.79 94 8.98 88 25.2 89 6.05 91 5.90 105 33.2 108 3.14 99 23.5 92 34.5 95 22.7 98 9.83 63 34.0 102 7.30 87 0.86 100 1.28 126 3.67 104 16.7 96 39.7 109 23.5 98
SPSA-learn [13]97.2 1.77 105 7.72 90 0.90 96 11.0 106 33.2 105 9.40 108 17.3 108 34.2 110 22.7 111 11.0 111 32.2 107 10.9 111 26.1 107 34.9 97 31.8 115 12.8 100 34.2 103 11.9 113 0.00 1 0.03 88 0.00 1 25.5 117 39.4 107 39.6 117
BlockOverlap [61]98.5 1.73 102 8.32 96 1.07 107 8.43 103 28.3 99 7.39 104 14.3 104 29.4 102 16.3 101 6.01 106 26.7 94 4.24 108 20.6 67 29.8 52 20.6 90 12.4 99 29.4 79 8.20 99 3.91 122 0.92 123 16.5 125 19.1 104 31.7 68 36.0 111
Filter Flow [19]99.0 1.97 110 10.2 111 1.14 111 8.79 104 33.9 107 5.66 99 18.8 110 35.7 111 26.2 116 21.9 118 42.4 115 22.0 118 27.9 113 36.8 105 35.0 118 13.2 105 32.6 96 8.11 98 0.05 47 0.02 32 0.37 54 17.5 100 33.0 78 25.2 101
HBpMotionGpu [43]99.5 2.47 112 11.8 113 1.09 109 11.4 108 35.3 109 10.0 110 20.3 115 38.5 115 26.3 117 5.67 103 26.6 92 3.51 104 24.1 95 34.8 96 26.1 104 10.9 83 30.7 85 7.04 81 0.27 68 0.05 92 0.89 64 19.3 106 37.1 99 32.8 109
GraphCuts [14]103.0 1.57 95 8.32 96 0.92 99 12.3 110 39.3 114 8.40 105 15.2 105 31.3 105 23.1 112 5.40 100 28.8 104 2.88 96 25.4 100 38.0 108 21.1 93 24.5 126 31.1 88 14.4 119 1.86 112 0.02 32 7.91 114 23.9 112 41.6 112 37.4 114
IAOF [50]103.3 1.77 105 8.80 102 0.98 103 11.2 107 32.5 104 9.32 107 19.8 113 35.7 111 20.2 105 17.5 116 37.6 112 19.8 116 23.7 93 35.0 98 22.3 96 18.1 119 40.2 113 10.9 109 0.56 88 0.02 32 2.17 93 24.8 115 37.8 103 43.9 120
UnFlow [129]103.4 7.34 126 24.6 131 3.32 122 21.7 120 50.1 121 19.1 118 26.8 122 53.1 128 25.0 113 13.7 115 42.5 116 12.5 114 42.2 127 53.7 128 45.6 126 15.1 113 46.2 119 12.1 114 0.00 1 0.00 1 0.00 1 17.5 100 43.7 114 21.5 92
IAOF2 [51]105.5 1.85 109 9.64 109 1.13 110 7.56 100 29.4 101 5.66 99 12.2 98 27.5 98 15.7 100 32.6 124 43.3 118 38.7 127 24.3 96 35.0 98 23.9 101 17.9 116 33.1 98 13.0 115 1.11 104 0.25 102 4.83 106 17.8 102 35.5 96 25.9 104
Black & Anandan [4]106.1 1.75 103 8.07 93 0.73 87 11.6 109 36.6 110 8.94 106 18.9 111 36.4 113 20.3 106 12.4 113 40.5 114 12.0 113 26.3 110 36.2 104 30.5 109 13.4 106 37.3 108 11.0 110 0.75 96 0.42 112 1.90 90 21.4 111 38.6 105 32.5 108
Nguyen [33]108.2 2.73 115 11.0 112 1.16 115 33.4 125 38.0 111 43.1 127 24.6 119 41.9 116 32.1 122 28.7 122 46.5 119 32.2 123 29.8 114 39.8 112 35.5 119 13.9 108 40.4 114 13.0 115 0.03 43 0.02 32 0.20 49 31.6 120 46.3 118 50.5 127
Modified CLG [34]109.2 2.46 111 12.2 114 1.37 116 10.5 105 33.6 106 9.99 109 20.2 114 37.9 114 27.9 119 9.52 110 38.0 113 7.95 110 27.6 112 38.6 110 31.7 113 11.2 88 37.6 109 8.53 102 0.70 95 0.24 101 3.33 102 24.7 114 45.8 117 38.5 116
2D-CLG [1]110.3 6.98 125 23.0 128 3.54 123 20.1 118 40.7 115 21.4 120 26.6 121 44.0 117 36.7 123 34.7 125 55.1 123 39.7 128 31.1 117 41.5 117 38.2 120 15.0 112 42.0 117 13.6 118 0.02 40 0.02 32 0.12 45 31.7 121 51.0 122 44.9 121
GroupFlow [9]113.1 3.39 117 16.8 122 1.37 116 23.0 121 51.6 123 21.5 121 20.7 116 45.1 120 22.3 109 5.67 103 27.3 98 3.50 103 34.6 121 51.5 126 22.0 95 22.4 123 47.9 121 25.4 127 0.55 87 0.47 114 1.70 86 25.2 116 47.9 119 33.5 110
SILK [79]113.4 3.45 118 15.8 120 2.61 120 19.0 116 44.9 117 19.5 119 23.5 118 44.1 118 26.6 118 12.0 112 42.7 117 11.1 112 35.3 122 46.3 123 44.8 124 18.0 118 49.4 123 14.5 120 1.53 109 0.00 1 5.00 107 32.1 124 50.8 121 47.1 124
Horn & Schunck [3]115.5 3.02 116 12.7 115 1.15 114 14.5 112 45.9 118 11.1 111 22.6 117 44.4 119 25.2 114 21.6 117 47.3 120 22.5 119 34.0 120 43.8 119 43.1 122 19.6 120 51.5 125 18.6 123 0.56 88 0.22 100 1.77 87 34.9 126 55.9 126 46.4 123
Heeger++ [104]116.6 3.74 120 16.1 121 1.49 118 23.6 122 64.4 131 14.1 113 36.0 128 49.4 126 37.3 126 38.6 129 67.3 129 38.6 126 46.7 130 58.2 130 50.9 129 36.6 130 68.1 132 34.5 131 0.41 82 0.00 1 1.87 88 31.8 122 51.3 123 37.0 112
TI-DOFE [24]117.0 7.50 127 18.0 123 10.6 129 41.8 129 54.1 126 49.7 129 31.9 126 54.7 131 39.7 128 41.8 130 61.8 126 48.6 131 35.5 124 45.7 122 45.0 125 21.9 122 52.6 126 21.7 125 0.25 65 0.00 1 1.31 75 43.7 129 61.4 129 58.6 129
FFV1MT [106]119.1 4.51 122 19.1 124 2.74 121 19.4 117 58.6 130 14.7 116 40.8 130 53.4 130 50.0 131 38.5 128 73.8 131 37.7 124 46.4 129 56.0 129 56.7 132 33.1 129 66.2 130 31.1 129 0.75 96 0.02 32 2.04 91 31.8 122 51.3 123 37.0 112
Periodicity [78]120.4 6.73 124 29.6 135 3.88 126 24.0 123 52.2 124 25.5 123 36.6 129 47.1 123 40.1 129 23.0 119 60.3 125 20.8 117 53.1 132 69.7 132 49.1 128 36.9 131 67.0 131 33.4 130 0.54 86 0.02 32 7.78 113 34.7 125 64.9 131 46.1 122
Adaptive flow [45]121.1 4.48 121 15.3 119 1.90 119 37.1 127 47.9 120 40.5 125 28.1 123 45.1 120 37.9 127 23.3 120 53.8 122 24.8 120 30.1 116 41.4 116 28.5 107 22.6 124 46.3 120 15.6 121 17.3 130 5.51 131 58.1 130 26.0 118 41.5 111 40.5 119
SLK [47]122.2 8.22 132 24.0 130 12.3 130 41.4 128 57.7 129 50.8 130 29.7 125 53.3 129 36.7 123 52.4 132 57.7 124 61.8 132 42.6 128 52.1 127 54.9 130 23.9 125 54.4 128 24.4 126 3.11 121 0.00 1 7.07 112 45.8 131 61.9 130 61.9 130
PGAM+LK [55]125.4 7.83 130 22.3 127 13.7 131 29.1 124 54.2 127 31.3 124 25.6 120 48.1 125 29.9 121 29.7 123 68.4 130 28.3 122 38.2 125 50.8 125 43.0 121 25.1 127 56.4 129 21.4 124 6.54 129 0.57 116 19.1 126 38.5 127 60.8 128 51.7 128
FOLKI [16]125.8 5.65 123 23.4 129 4.60 127 35.1 126 52.9 125 42.6 126 28.3 124 52.7 127 29.6 120 24.1 121 53.7 121 27.7 121 38.9 126 49.3 124 47.8 127 25.3 128 54.3 127 27.7 128 5.73 127 1.38 127 20.1 128 43.9 130 60.5 127 62.2 131
HCIC-L [99]126.0 8.04 131 19.9 125 3.64 124 56.4 132 56.0 128 70.0 132 40.9 131 45.5 122 62.3 132 38.3 127 62.5 127 38.2 125 35.3 122 45.3 121 32.0 116 20.7 121 38.1 111 18.5 122 26.5 132 13.0 132 59.2 132 40.6 128 51.8 125 48.7 126
Pyramid LK [2]128.4 7.59 128 14.5 118 15.4 132 47.0 130 50.5 122 58.8 131 32.1 127 47.7 124 42.4 130 36.1 126 62.9 128 41.1 129 48.9 131 61.1 131 55.0 131 41.7 132 50.3 124 40.3 132 4.64 126 2.07 130 16.3 124 56.9 132 71.9 132 77.2 132
AdaConv-v1 [126]133.0 25.9 133 27.4 132 29.8 133 96.8 133 97.6 133 95.4 133 93.0 133 90.8 133 99.0 133 88.2 133 85.6 133 91.5 133 97.0 133 98.5 133 88.6 133 86.2 133 81.3 133 83.9 133 64.9 133 56.4 133 97.3 133 100.0 133 99.9 133 99.9 133
SepConv-v1 [127]133.0 25.9 133 27.4 132 29.8 133 96.8 133 97.6 133 95.4 133 93.0 133 90.8 133 99.0 133 88.2 133 85.6 133 91.5 133 97.0 133 98.5 133 88.6 133 86.2 133 81.3 133 83.9 133 64.9 133 56.4 133 97.3 133 100.0 133 99.9 133 99.9 133
SuperSlomo [132]133.0 25.9 133 27.4 132 29.8 133 96.8 133 97.6 133 95.4 133 93.0 133 90.8 133 99.0 133 88.2 133 85.6 133 91.5 133 97.0 133 98.5 133 88.6 133 86.2 133 81.3 133 83.9 133 64.9 133 56.4 133 97.3 133 100.0 133 99.9 133 99.9 133
Move the mouse over the numbers in the table to see the corresponding images. Click to compare with the ground truth.

References

Methodtime*framescolor Reference and notes
[1] 2D-CLG 844 2 gray The 2D-CLG method by Bruhn et al. as implemented by Stefan Roth. [A. Bruhn, J. Weickert, and C. Schnörr. Lucas/Kanade meets Horn/Schunck: combining local and global optic flow methods. IJCV 63(3), 2005.] Parameters were set to match the published performance on Yosemite sequence, which may not be optimal for other sequences.
[2] Pyramid LK 12 2 color A modification of Bouguet's pyramidal implementation of Lucas-Kanade.
[3] Horn & Schunck 49 2 gray A modern Matlab implementation of the Horn & Schunck method by Deqing Sun. Parameters set to optimize AAE on all training data.
[4] Black & Anandan 328 2 gray A modern Matlab implementation of the Black & Anandan method by Deqing Sun.
[5] Brox et al. 18 2 color T. Brox, A. Bruhn, N. Papenberg, and J. Weickert. High accuracy optical flow estimation based on a theory for warping. ECCV 2004. (Improved using separate robust functions as proposed in A. Bruhn and J. Weickert, Towards ultimate motion estimation, ICCV 2005; improved by training on the training set.)
[6] Fusion 2,666 2 color V. Lempitsky, S. Roth, and C. Rother. Discrete-continuous optimization for optical flow estimation. CVPR 2008.
[7] Dynamic MRF 366 2 gray B. Glocker, N. Paragios, N. Komodakis, G. Tziritas, and N. Navab. Optical flow estimation with uncertainties through dynamic MRFs. CVPR 2008. (Method improved since publication.)
[8] Second-order prior 14 2 gray W. Trobin, T. Pock, D. Cremers, and H. Bischof. An unbiased second-order prior for high-accuracy motion estimation. DAGM 2008. (Method improved since publication; for details see W. Trobin, Ph.D. thesis, 2009.)
[9] GroupFlow 600 2 gray X. Ren. Local Grouping for Optical Flow. CVPR 2008.
[10] SegOF 60 2 color L. Xu, J. Chen, and J. Jia. Segmentation based variational model for accurate optical flow estimation. ECCV 2008. Code available.
[11] Learning Flow 825 2 gray D. Sun, S. Roth, J.P. Lewis, and M. Black. Learning optical flow (SRF-LFC). ECCV 2008.
[12] CBF 69 2 color W. Trobin, T. Pock, D. Cremers, and H. Bischof. Continuous energy minimization via repeated binary fusion. ECCV 2008. (Method improved since publication; for details see W. Trobin, Ph.D. thesis, 2009.)
[13] SPSA-learn 200 2 color Y. Li and D. Huttenlocher. Learning for optical flow using stochastic optimization. ECCV 2008.
[14] GraphCuts 1,200 2 color T. Cooke. Two applications of graph-cuts to image processing. DICTA 2008.
[15] F-TV-L1 8 2 gray A. Wedel, T. Pock, J. Braun, U. Franke, and D. Cremers. Duality TV-L1 flow with fundamental matrix prior. IVCNZ 2008.
[16] FOLKI 1.4 2 gray G. Le Besnerais and F. Champagnat. Dense optical flow by iterative local window registration. ICIP 2005.
[17] TV-L1-improved 2.9 2 gray A. Wedel, T. Pock, C. Zach, H. Bischof, and D. Cremers. An improved algorithm for TV-L1 optical flow computation. Proceedings of the Dagstuhl Visual Motion Analysis Workshop 2008. Code at GPU4Vision.
[18] DPOF 287 2 color C. Lei and Y.-H. Yang. Optical flow estimation on coarse-to-fine region-trees using discrete optimization. ICCV 2009. (Method improved since publication.)
[19] Filter Flow 34,000 2 color S. Seitz and S. Baker. Filter flow. ICCV 2009.
[20] Adaptive 9.2 2 gray A. Wedel, D. Cremers, T. Pock, and H. Bischof. Structure- and motion-adaptive regularization for high accuracy optic flow. ICCV 2009.
[21] Complementary OF 44 2 color H. Zimmer, A. Bruhn, J. Weickert, L. Valgaerts, A. Salgado, B. Rosenhahn, and H.-P. Seidel. Complementary optic flow. EMMCVPR 2009.
[22] Aniso. Huber-L1 2 2 gray M. Werlberger, W. Trobin, T. Pock, A. Wedel, D. Cremers, and H. Bischof. Anisotropic Huber-L1 optical flow. BMVC 2009. Code at GPU4Vision.
[23] Rannacher 0.12 2 gray J. Rannacher. Realtime 3D motion estimation on graphics hardware. Bachelor thesis, Heidelberg University, 2009.
[24] TI-DOFE 260 2 gray C. Cassisa, S. Simoens, and V. Prinet. Two-frame optical flow formulation in an unwarped multiresolution scheme. CIARP 2009.
[25] NL-TV-NCC 20 2 color M. Werlberger, T. Pock, and H. Bischof. Motion estimation with non-local total variation regularization. CVPR 2010.
[26] MDP-Flow 188 2 color L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. CVPR 2010.
[27] ACK-Prior 5872 2 color K. Lee, D. Kwon, I. Yun, and S. Lee. Optical flow estimation with adaptive convolution kernel prior on discrete framework. CVPR 2010.
[28] LDOF 122 2 color T. Brox and J. Malik. Large displacement optical flow: descriptor matching in variational motion estimation. PAMI 33(3):500-513, 2011.
[29] p-harmonic 565 2 gray J. Gai and R. Stevenson. Optical flow estimation with p-harmonic regularization. ICIP 2010.
[30] TriangleFlow 4200 2 gray B. Glocker, H. Heibel, N. Navab, P. Kohli, and C. Rother. TriangleFlow: Optical flow with triangulation-based higher-order likelihoods. ECCV 2010.
[31] Classic+NL 972 2 color D. Sun, S. Roth, and M. Black. Secrets of optical flow estimation and their principles. CVPR 2010. Matlab code.
[32] Classic++ 486 2 gray A modern implementation of the classical formulation descended from Horn & Schunck and Black & Anandan; see D. Sun, S. Roth, and M. Black, Secrets of optical flow estimation and their principles, CVPR 2010.
[33] Nguyen 33 2 gray D. Nguyen. Tuning optical flow estimation with image-driven functions. ICRA 2011.
[34] Modified CLG 133 2 gray R. Fezzani, F. Champagnat, and G. Le Besnerais. Combined local global method for optic flow computation. EUSIPCO 2010.
[35] ComplOF-FED-GPU 0.97 2 color P. Gwosdek, H. Zimmer, S. Grewenig, A. Bruhn, and J. Weickert. A highly efficient GPU implementation for variational optic flow based on the Euler-Lagrange framework. CVGPU Workshop 2010.
[36] Ad-TV-NDC 35 2 gray M. Nawaz. Motion estimation with adaptive regularization and neighborhood dependent constraint. DICTA 2010.
[37] Layers++ 18206 2 color D. Sun, E. Sudderth, and M. Black. Layered image motion with explicit occlusions, temporal consistency, and depth ordering. NIPS 2010.
[38] OFH 620 3 color H. Zimmer, A. Bruhn, J. Weickert. Optic flow in harmony. IJCV 93(3) 2011.
[39] LSM 1615 2 color K. Jia, X. Wang, and X. Tang. Optical flow estimation using learned sparse model. ICCV 2011.
[40] CostFilter 55 2 color C. Rhemann, A. Hosni, M. Bleyer, C. Rother, and M. Gelautz. Fast cost-volume filtering for visual correspondence and beyond. CVPR 2011.
[41] Bartels 0.15 2 gray C. Bartels and G. de Haan. Smoothness constraints in recursive search motion estimation for picture rate conversion. IEEE TCSVT 2010. Version improved since publication: mapped on GPU.
[42] Shiralkar 600 2 gray M. Shiralkar and R. Schalkoff. A self organization-based optical flow estimator with GPU implementation. MVA 23(6):1229-1242.
[43] HBpMotionGpu 1000 5 gray S. Grauer-Gray and C. Kambhamettu. Hierarchical belief propagation to reduce search space using CUDA for stereo and motion estimation. WACV 2009. (Method improved since publication.)
[44] StereoFlow 7200 2 color G. Rosman, S. Shem-Tov, D. Bitton, T. Nir, G. Adiv, R. Kimmel, A. Feuer, and A. Bruckstein. Over-parameterized optical flow using a stereoscopic constraint. SSVM 2011:761-772.
[45] Adaptive flow 121 2 gray T. Arici. Energy minimization based motion estimation using adaptive smoothness priors. Submitted to IEEE TIP 2011.
[46] TC-Flow 2500 5 color S. Volz, A. Bruhn, L. Valgaerts, and H. Zimmer. Modeling temporal coherence for optical flow. ICCV 2011.
[47] SLK 300 2 gray T. Corpetti and E. Mémin. Stochastic uncertainty models for the luminance consistency assumption. IEEE TIP 2011.
[48] CLG-TV 29 2 gray M. Drulea. Total variation regularization of local-global optical flow. ITSC 2011. Matlab code.
[49] SimpleFlow 1.7 2 color M. Tao, J. Bai, P. Kohli, S. Paris. SimpleFlow: a non-iterative, sublinear optical flow algorithm. EUROGRAPHICS 2012.
[50] IAOF 57 2 gray D. Nguyen. Improving motion estimation using image-driven functions and hybrid scheme. PSIVT 2011.
[51] IAOF2 56 2 gray D. Nguyen. Enhancing the sharpness of flow field using image-driven functions with occlusion-aware filter. Submitted to TIP 2011.
[52] LocallyOriented 9541 2 gray Y.Niu, A. Dick, and M. Brooks. Locally oriented optical flow computation. To appear in TIP 2012.
[53] IROF-TV 261 2 color H. Rashwan, D. Puig, and M. Garcia. On improving the robustness of differential optical flow. ICCV 2011 Artemis workshop.
[54] Sparse Occlusion 2312 2 color A. Ayvaci, M. Raptis, and S. Soatto. Sparse occlusion detection with optical flow. Submitted to IJCV 2011.
[55] PGAM+LK 0.37 2 gray A. Alba, E. Arce-Santana, and M. Rivera. Optical flow estimation with prior models obtained from phase correlation. ISVC 2010.
[56] Sparse-NonSparse 713 2 color L. Chen, J. Wang, and Y. Wu. Decomposing and regularizing sparse/non-sparse components for motion field estimation. Submitted to PAMI 2013.
[57] nLayers 36150 4 color D. Sun, E. Sudderth, and M. Black. Layered segmentation and optical flow estimation over time. CVPR 2012.
[58] IROF++ 187 2 color H. Rashwan, D. Puig, and M. Garcia. Variational optical flow estimation based on stick tensor voting. IEEE TIP 2013.
[59] COFM 600 3 color M. Mozerov. Constrained optical flow estimation as a matching problem. IEEE TIP 2013.
[60] Efficient-NL 400 2 color P. Krähenbühl and V. Koltun. Efficient nonlocal regularization for optical flow. ECCV 2012.
[61] BlockOverlap 2 2 gray M. Santoro, G. AlRegib, and Y. Altunbasak. Motion estimation using block overlap minimization. Submitted to MMSP 2012.
[62] Ramp 1200 2 color A. Singh and N. Ahuja. Exploiting ramp structures for improving optical flow estimation. ICPR 2012.
[63] Occlusion-TV-L1 538 3 gray C. Ballester, L. Garrido, V. Lazcano, and V. Caselles. A TV-L1 optical flow method with occlusion detection. DAGM-OAGM 2012.
[64] TV-L1-MCT 90 2 color M. Mohamed and B. Mertsching. TV-L1 optical flow estimation with image details recovering based on modified census transform. ISVC 2012.
[65] Local-TV-L1 500 2 gray L. Raket. Local smoothness for global optical flow. ICIP 2012.
[66] ALD-Flow 61 2 color M. Stoll, A. Bruhn, and S. Volz. Adaptive integration of feature matches into variational optic flow methods. ACCV 2012.
[67] SIOF 234 2 color L. Xu, Z. Dai, and J. Jia. Scale invariant optical flow. ECCV 2012.
[68] MDP-Flow2 342 2 color L. Xu, J. Jia, and Y. Matsushita. Motion detail preserving optical flow estimation. PAMI 34(9):1744-1757, 2012. Code available.
[69] TCOF 1421 all gray J. Sanchez, A. Salgado, and N. Monzon. Optical flow estimation with consistent spatio-temporal coherence models. VISAPP 2013.
[70] LME 476 2 color W. Li, D. Cosker, M. Brown, and R. Tang. Optical flow estimation using Laplacian mesh energy. CVPR 2013.
[71] NN-field 362 2 color L. Chen, H. Jin, Z. Lin, S. Cohen, and Y. Wu. Large displacement optical flow from nearest neighbor fields. CVPR 2013.
[72] FESL 3310 2 color W. Dong, G. Shi, X. Hu, and Y. Ma. Nonlocal sparse and low-rank regularization for optical flow estimation. Submitted to IEEE TIP 2013.
[73] PMF 35 2 color J. Lu, H. Yang, D. Min, and M. Do. PatchMatch filter: efficient edge-aware filtering meets randomized search for fast correspondence field estimation. CVPR 2013.
[74] FC-2Layers-FF 2662 4 color D. Sun, J. Wulff, E. Sudderth, H. Pfister, and M. Black. A fully-connected layered model of foreground and background flow. CVPR 2013.
[75] Correlation Flow 290 2 color M. Drulea and S. Nedevschi. Motion estimation using the correlation transform. TIP 2013. Matlab code.
[76] TC/T-Flow 341 5 color M. Stoll, S. Volz, and A. Bruhn. Joint trilateral filtering for multiframe optical flow. ICIP 2013.
[77] OFLAF 1530 2 color T. Kim, H. Lee, and K. Lee. Optical flow via locally adaptive fusion of complementary data costs. ICCV 2013.
[78] Periodicity 8000 4 color G. Khachaturov, S. Gonzalez-Brambila, and J. Gonzalez-Trejo. Periodicity-based computation of optical flow. Submitted to Computacion y Sistemas (CyS) 2013.
[79] SILK 572 2 gray P. Zille, C. Xu, T. Corpetti, L. Shao. Observation models based on scale interactions for optical flow estimation. Submitted to IEEE TIP.
[80] CRTflow 13 3 color O. Demetz, D. Hafner, and J. Weickert. The complete rank transform: a tool for accurate and morphologically invariant matching of structures. BMVC 2013.
[81] SuperFlow 178 2 color Anonymous. Superpixel based optical flow estimation. ICCV 2013 submission 507.
[82] Aniso-Texture 300 2 color Anonymous. Texture information-based optical flow estimation using an incremental multi-resolution approach. ITC-CSCC 2013 submission 267.
[83] Classic+CPF 640 2 gray Z. Tu, R. Veltkamp, and N. van der Aa. A combined post-filtering method to improve accuracy of variational optical flow estimation. Submitted to Pattern Recognition 2013.
[84] S2D-Matching 1200 2 color Anonymous. Locally affine sparse-to-dense matching for motion and occlusion estimation. ICCV 2013 submission 1479.
[85] AGIF+OF 438 2 gray Z. Tu, R. Poppe, and R. Veltkamp. Adaptive guided image filter to warped interpolation image for variational optical flow computation. Submitted to Signal Processing 2015.
[86] DeepFlow 13 2 color P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013.
[87] NNF-Local 673 2 color Z. Chen, H. Jin, Z. Lin, S. Cohen, and Y. Wu. Large displacement optical flow with nearest neighbor field. Submitted to PAMI 2014.
[88] EPPM w/o HM 2.5 2 color L. Bao, Q. Yang, and H. Jin. Fast edge-preserving PatchMatch for large displacement optical flow. CVPR 2014.
[89] MLDP_OF 165 2 gray M. Mohamed, H. Rashwan, B. Mertsching, M. Garcia, and D. Puig. Illumination-robust optical flow approach using local directional pattern. IEEE TCSVT 24(9):1499-1508, 2014.
[90] RFlow 20 2 gray S. Ali, C. Daul, and W. Blondel. Robust and accurate optical flow estimation for weak texture and varying illumination condition: Application to cystoscopy. IPTA 2014.
[91] SRR-TVOF-NL 32 all color P. Pohl, M. Sirotenko, E. Tolstaya, and V. Bucha. Edge preserving motion estimation with occlusions correction for assisted 2D to 3D conversion. IS&T/SPIE Electronic Imaging 2014.
[92] 2DHMM-SAS 157 2 color M.-C. Shih, R. Shenoy, and K. Rose. A two-dimensional hidden Markov model with spatially-adaptive states with application of optical flow. ICIP 2014 submission.
[93] WLIF-Flow 700 2 color Z. Tu, R. Veltkamp, N. van der Aa, and C. Van Gemeren. Weighted local intensity fusion method for variational optical flow estimation. Submitted to TIP 2014.
[94] FMOF 215 2 color N. Jith, A. Ramakanth, and V. Babu. Optical flow estimation using approximate nearest neighbor field fusion. ICASSP 2014.
[95] TriFlow 150 2 color TriFlow. Optical flow with geometric occlusion estimation and fusion of multiple frames. ECCV 2014 submission 914.
[96] ComponentFusion 6.5 2 color Anonymous. Fast optical flow by component fusion. ECCV 2014 submission 941.
[97] AggregFlow 1642 2 color D. Fortun, P. Bouthemy, and C. Kervrann. Aggregation of local parametric candidates and exemplar-based occlusion handling for optical flow. Preprint arXiv:1407.5759.
[98] 2bit-BM-tele 124 2 gray R. Xu and D. Taubman. Robust dense block-based motion estimation using a two-bit transform on a Laplacian pyramid. ICIP 2013.
[99] HCIC-L 330 2 color Anonymous. Globally-optimal image correspondence using a hierarchical graphical model. NIPS 2014 submission 114.
[100] TF+OM 600 2 color R. Kennedy and C. Taylor. Optical flow with geometric occlusion estimation and fusion of multiple frames. EMMCVPR 2015.
[101] PH-Flow 800 2 color J. Yang and H. Li. Dense, accurate optical flow estimation with piecewise parametric model. CVPR 2015.
[102] EpicFlow 16 2 color J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. EpicFlow: edge-preserving interpolation of correspondences for optical flow. CVPR 2015.
[103] NNF-EAC 380 2 color Anonymous. Variational method for joint optical flow estimation and edge-aware image restoration. CVPR 2015 submission 2336.
[104] Heeger++ 6600 5 gray Anonymous. A context aware biologically inspired algorithm for optical flow (updated results). CVPR 2015 submission 2238.
[105] HBM-GC 330 2 color A. Zheng and Y. Yuan. Motion estimation via hierarchical block matching and graph cut. Submitted to ICIP 2015.
[106] FFV1MT 358 5 gray F. Solari, M. Chessa, N. Medathati, and P. Kornprobst. What can we expect from a V1-MT feedforward architecture for optical flow estimation? Submitted to Signal Processing: Image Communication 2015.
[107] ROF-ND 4 2 color S. Ali, C. Daul, E. Galbrun, and W. Blondel. Illumination invariant large displacement optical flow using robust neighbourhood descriptors. Submitted to CVIU 2015.
[108] DeepFlow2 16 2 color J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. Deep convolutional matching. Submitted to IJCV, 2015.
[109] HAST 2667 2 color Anonymous. Highly accurate optical flow estimation on superpixel tree. ICCV 2015 submission 2221.
[110] FlowFields 15 2 color C. Bailer, B. Taetz, and D. Stricker. Flow Fields: Dense unregularized correspondence fields for highly accurate large displacement optical flow estimation. ICCV 2015.
[111] SVFilterOh 1.56 2 color Anonymous. Fast estimation of large displacement optical flow using PatchMatch and dominant motion patterns. CVPR 2016 submission 1788.
[112] FlowNetS+ft+v 0.5 2 color Anonymous. Learning optical flow with convolutional neural networks. ICCV 2015 submission 235.
[113] CombBMOF 51 2 color M. Brüggemann, R. Kays, P. Springer, and O. Erdler. Combined block-matching and adaptive differential motion estimation in a hierarchical multi-scale framework. ICGIP 2014. (Method improved since publication.)
[114] PMMST 182 2 color F. Zhang, S. Xu, and X. Zhang. High accuracy correspondence field estimation via MST based patch matching. Submitted to TIP 2015.
[115] DF-Auto 70 2 color N. Monzon, A. Salgado, and J. Sanchez. Regularization strategies for discontinuity-preserving optical flow methods. Submitted to TIP 2015.
[116] CPM-Flow 3 2 color Anonymous. Efficient coarse-to-fine PatchMatch for large displacement optical flow. CVPR 2016 submission 241.
[117] CNN-flow-warp+ref 1.4 3 color D. Teney and M. Hebert. Learning to extract motion from videos in convolutional neural networks. ArXiv 1601.07532, 2016.
[118] Steered-L1 804 2 color Anonymous. Optical flow estimation via steered-L1 norm. Submitted to WSCG 2016.
[119] StereoOF-V1MT 343 2 gray Anonymous. Visual features for action-oriented tasks: a cortical-like model for disparity and optic flow computation. BMVC 2016 submission 132.
[120] PGM-C 5 2 color Y. Li. Pyramidal gradient matching for optical flow estimation. Submitted to PAMI 2016.
[121] RNLOD-Flow 1040 2 gray C. Zhang, Z. Chen, M. Wang, M. Li, and S. Jiang. Robust non-local TV-L1 optical flow estimation with occlusion detection. Submitted to TIP 2016.
[122] FlowNet2 0.091 2 color Anonymous. FlowNet 2.0: Evolution of optical flow estimation with deep networks. CVPR 2017 submission 900.
[123] S2F-IF 20 2 color Anonymous. S2F-IF: Slow-to-fast interpolator flow. CVPR 2017 submission 765.
[124] BriefMatch 0.068 2 gray G. Eilertsen, P.-E. Forssen, and J. Unger. Dense binary feature matching for real-time optical flow estimation. SCIA 2017 submission 62.
[125] OAR-Flow 60 2 color Anonymous. Order-adaptive regularisation for variational optical flow: global, local and in between. SSVM 2017 submission 20.
[126] AdaConv-v1 2.8 2 color S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive convolution. CVPR 2017.
[127] SepConv-v1 0.2 2 color S. Niklaus, L. Mai, and F. Liu. (Interpolation results only.) Video frame interpolation via adaptive separable convolution. ICCV 2017.
[128] ProbFlowFields 37 2 color A. Wannenwetsch, M. Keuper, and S. Roth. ProbFlow: joint optical flow and uncertainty estimation. ICCV 2017.
[129] UnFlow 0.12 2 color Anonymous. UnFlow: Unsupervised learning of optical flow with a bidirectional census loss. Submitted to AAAI 2018.
[130] FlowFields+ 10.5 2 color C. Bailer, B. Taetz, and D. Stricker. Flow fields: Dense correspondence fields for highly accurate large displacement optical flow estimation. Submitted to PAMI 2017.
[131] IIOF-NLDP 150 2 color D.-H. Trinh, W. Blondel, and C. Daul. A general form of illumination-invariant descriptors in variational optical flow estimation. ICIP 2017.
[132] SuperSlomo 0.5 2 color Anonymous. (Interpolation results only.) Super SloMo: High quality estimation of multiple intermediate frames for video interpolation. CVPR 2018 submission 325.
[133] EPMNet 0.061 2 color Anonymous. EPM-convolution multilayer-network for optical flow estimation. ICME 2018 submission 1119.
[134] OFRF 90 2 color T. Mai, M. Gouiffes, and S. Bouchafa. Optical Flow refinement using iterative propagation under color, proximity and flow reliability constraints. Submitted to Signal, Image and Video Processing 2017.
[135] 3DFlow 328 2 color J. Chen, Z. Cai, J. Lai, and X. Xie. A filtering based framework for optical flow estimation. IEEE TCSVT 2018.
* The "time" column lists the reported runtime in seconds on the "Urban" sequence. Note that these runtimes are not normalized by processor speed or type.