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        
Average
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
IVANN [87]2.7 0.07 1 0.20 2 0.05 1 0.15 1 0.51 3 0.12 5 0.18 1 0.37 1 0.14 1 0.10 2 0.49 3 0.06 2 0.41 1 0.61 1 0.21 2 0.23 2 0.66 2 0.19 1 0.10 4 0.12 9 0.17 12 0.34 1 0.80 4 0.23 2
OFLAF [77]6.9 0.08 7 0.21 3 0.06 5 0.16 5 0.53 4 0.12 5 0.19 2 0.37 1 0.14 1 0.14 7 0.77 23 0.07 4 0.51 4 0.78 5 0.25 3 0.31 5 0.76 3 0.25 7 0.11 11 0.12 9 0.21 30 0.42 7 0.78 2 0.63 12
MDP-Flow2 [68]7.9 0.08 7 0.21 3 0.07 14 0.15 1 0.48 1 0.11 1 0.20 4 0.40 4 0.14 1 0.15 18 0.80 29 0.08 10 0.63 14 0.93 14 0.43 15 0.26 3 0.76 3 0.23 6 0.11 11 0.12 9 0.17 12 0.38 3 0.79 3 0.44 4
NN-field [71]8.7 0.08 7 0.22 14 0.05 1 0.17 7 0.55 6 0.13 10 0.19 2 0.39 3 0.15 6 0.09 1 0.48 2 0.05 1 0.41 1 0.61 1 0.20 1 0.52 46 0.64 1 0.26 10 0.13 31 0.13 26 0.20 23 0.35 2 0.83 5 0.21 1
ComponentFusion [96]10.0 0.07 1 0.21 3 0.05 1 0.16 5 0.55 6 0.12 5 0.20 4 0.44 7 0.15 6 0.11 3 0.65 6 0.06 2 0.71 27 1.07 32 0.53 29 0.32 7 1.06 20 0.28 13 0.11 11 0.13 26 0.15 7 0.41 6 0.88 9 0.54 5
WLIF-Flow [93]14.7 0.08 7 0.21 3 0.06 5 0.18 9 0.55 6 0.15 19 0.25 13 0.56 14 0.17 12 0.14 7 0.68 7 0.08 10 0.61 12 0.91 13 0.41 13 0.43 23 0.96 11 0.29 18 0.13 31 0.12 9 0.21 30 0.51 27 1.03 28 0.72 26
TC/T-Flow [76]14.9 0.07 1 0.21 3 0.05 1 0.19 14 0.68 26 0.12 5 0.28 18 0.66 23 0.14 1 0.14 7 0.86 37 0.07 4 0.67 24 0.98 23 0.49 24 0.22 1 0.82 5 0.19 1 0.11 11 0.11 1 0.30 67 0.50 22 1.02 25 0.64 14
Layers++ [37]16.5 0.08 7 0.21 3 0.07 14 0.19 14 0.56 9 0.17 26 0.20 4 0.40 4 0.18 18 0.13 6 0.58 4 0.07 4 0.48 3 0.70 3 0.33 6 0.47 34 1.01 14 0.33 35 0.15 52 0.14 47 0.24 42 0.46 12 0.88 9 0.72 26
LME [70]17.0 0.08 7 0.22 14 0.06 5 0.15 1 0.49 2 0.11 1 0.30 26 0.64 18 0.31 69 0.15 18 0.78 26 0.09 23 0.66 20 0.96 19 0.53 29 0.33 8 1.18 32 0.28 13 0.12 22 0.12 9 0.18 16 0.44 8 0.91 11 0.61 10
IROF++ [58]17.4 0.08 7 0.23 19 0.07 14 0.21 26 0.68 26 0.17 26 0.28 18 0.63 17 0.19 30 0.15 18 0.73 19 0.09 23 0.60 10 0.89 10 0.42 14 0.43 23 1.08 23 0.31 25 0.10 4 0.12 9 0.12 4 0.47 14 0.98 18 0.68 21
nLayers [57]17.6 0.07 1 0.19 1 0.06 5 0.22 32 0.59 12 0.19 45 0.25 13 0.54 11 0.20 38 0.15 18 0.84 34 0.08 10 0.53 5 0.78 5 0.34 8 0.44 27 0.84 6 0.30 22 0.13 31 0.13 26 0.20 23 0.47 14 0.97 17 0.67 19
FC-2Layers-FF [74]19.6 0.08 7 0.21 3 0.07 14 0.21 26 0.70 30 0.17 26 0.20 4 0.40 4 0.18 18 0.15 18 0.76 22 0.08 10 0.53 5 0.77 4 0.37 9 0.49 40 1.02 15 0.33 35 0.16 62 0.13 26 0.29 63 0.44 8 0.87 8 0.64 14
Correlation Flow [75]20.0 0.09 28 0.23 19 0.07 14 0.17 7 0.58 11 0.11 1 0.43 46 0.99 49 0.15 6 0.11 3 0.47 1 0.08 10 0.75 33 1.08 33 0.56 34 0.41 19 0.92 9 0.30 22 0.14 41 0.13 26 0.27 55 0.40 5 0.85 6 0.42 3
AGIF+OF [85]21.0 0.08 7 0.22 14 0.07 14 0.23 43 0.73 34 0.18 36 0.28 18 0.66 23 0.18 18 0.14 7 0.70 10 0.08 10 0.57 7 0.85 7 0.38 10 0.47 34 0.97 12 0.31 25 0.13 31 0.13 26 0.22 35 0.51 27 0.99 21 0.74 35
Classic+CPF [83]22.8 0.08 7 0.23 19 0.07 14 0.22 32 0.73 34 0.17 26 0.30 26 0.70 26 0.18 18 0.14 7 0.72 18 0.08 10 0.63 14 0.93 14 0.45 18 0.51 44 1.03 18 0.32 30 0.14 41 0.12 9 0.30 67 0.48 16 0.93 12 0.72 26
FESL [72]22.8 0.08 7 0.21 3 0.07 14 0.25 53 0.75 40 0.19 45 0.27 15 0.61 15 0.18 18 0.14 7 0.68 7 0.08 10 0.61 12 0.89 10 0.44 16 0.47 34 1.03 18 0.32 30 0.14 41 0.15 57 0.25 47 0.50 22 0.96 15 0.63 12
ALD-Flow [66]23.1 0.07 1 0.21 3 0.06 5 0.19 14 0.64 21 0.13 10 0.30 26 0.73 29 0.15 6 0.17 36 0.92 48 0.07 4 0.78 36 1.14 37 0.59 37 0.33 8 1.30 40 0.21 4 0.12 22 0.12 9 0.28 58 0.54 32 1.19 38 0.73 31
TC-Flow [46]23.4 0.07 1 0.21 3 0.06 5 0.15 1 0.59 12 0.11 1 0.31 31 0.78 34 0.14 1 0.16 31 0.86 37 0.08 10 0.75 33 1.11 35 0.54 31 0.42 21 1.40 48 0.25 7 0.11 11 0.12 9 0.29 63 0.62 40 1.35 41 0.93 55
COFM [59]23.4 0.08 7 0.26 36 0.06 5 0.18 9 0.62 17 0.14 15 0.30 26 0.74 31 0.19 30 0.15 18 0.86 37 0.07 4 0.79 37 1.14 37 0.74 54 0.35 13 0.87 8 0.28 13 0.14 41 0.12 9 0.28 58 0.49 18 0.94 13 0.71 25
Sparse-NonSparse [56]23.6 0.08 7 0.23 19 0.07 14 0.22 32 0.73 34 0.18 36 0.28 18 0.64 18 0.19 30 0.14 7 0.71 15 0.08 10 0.67 24 0.99 25 0.48 21 0.49 40 1.06 20 0.32 30 0.14 41 0.11 1 0.28 58 0.49 18 0.98 18 0.73 31
Efficient-NL [60]23.8 0.08 7 0.22 14 0.06 5 0.21 26 0.67 24 0.17 26 0.31 31 0.73 29 0.18 18 0.14 7 0.71 15 0.08 10 0.59 9 0.88 9 0.39 11 1.30 76 1.35 43 0.67 71 0.14 41 0.13 26 0.26 49 0.45 10 0.85 6 0.55 7
LSM [39]25.2 0.08 7 0.23 19 0.07 14 0.22 32 0.73 34 0.18 36 0.28 18 0.64 18 0.19 30 0.14 7 0.70 10 0.09 23 0.66 20 0.97 21 0.48 21 0.50 42 1.06 20 0.33 35 0.15 52 0.12 9 0.29 63 0.50 22 0.99 21 0.73 31
Ramp [62]25.7 0.08 7 0.24 26 0.07 14 0.21 26 0.72 32 0.18 36 0.27 15 0.62 16 0.19 30 0.15 18 0.71 15 0.09 23 0.66 20 0.97 21 0.49 24 0.51 44 1.09 24 0.34 40 0.15 52 0.12 9 0.30 67 0.48 16 0.96 15 0.72 26
Classic+NL [31]27.5 0.08 7 0.23 19 0.07 14 0.22 32 0.74 38 0.18 36 0.29 23 0.65 22 0.19 30 0.15 18 0.73 19 0.09 23 0.64 17 0.93 14 0.47 19 0.52 46 1.12 27 0.33 35 0.16 62 0.13 26 0.29 63 0.49 18 0.98 18 0.74 35
TV-L1-MCT [64]28.0 0.08 7 0.23 19 0.07 14 0.24 48 0.77 44 0.19 45 0.32 34 0.76 33 0.19 30 0.14 7 0.69 9 0.09 23 0.72 29 1.03 26 0.60 38 0.54 48 1.10 25 0.35 42 0.11 11 0.12 9 0.20 23 0.54 32 1.04 30 0.84 46
PMF [73]28.8 0.09 28 0.25 30 0.07 14 0.19 14 0.60 15 0.14 15 0.23 9 0.46 9 0.17 12 0.17 36 0.87 41 0.09 23 0.58 8 0.86 8 0.26 4 0.82 63 1.17 30 0.54 61 0.21 85 0.22 90 0.36 81 0.39 4 0.75 1 0.59 9
FMOF [94]29.4 0.08 7 0.22 14 0.07 14 0.24 48 0.76 41 0.19 45 0.24 10 0.54 11 0.18 18 0.14 7 0.70 10 0.08 10 0.64 17 0.94 18 0.44 16 1.19 72 1.12 27 0.65 70 0.15 52 0.13 26 0.32 76 0.58 37 1.16 36 0.70 24
IROF-TV [53]30.8 0.09 28 0.25 30 0.08 35 0.22 32 0.77 44 0.19 45 0.30 26 0.70 26 0.19 30 0.18 43 0.93 51 0.11 45 0.73 31 1.04 28 0.56 34 0.44 27 1.69 67 0.31 25 0.09 3 0.11 1 0.12 4 0.50 22 1.08 32 0.73 31
MDP-Flow [26]31.9 0.09 28 0.25 30 0.08 35 0.19 14 0.54 5 0.18 36 0.24 10 0.55 13 0.20 38 0.16 31 0.91 45 0.09 23 0.74 32 1.06 31 0.61 40 0.46 31 1.02 15 0.35 42 0.12 22 0.14 47 0.17 12 0.78 61 1.68 64 0.97 60
2DHMM-SAS [92]33.0 0.08 7 0.24 26 0.07 14 0.23 43 0.78 47 0.17 26 0.42 45 0.90 40 0.22 49 0.15 18 0.75 21 0.09 23 0.65 19 0.96 19 0.48 21 0.56 51 1.13 29 0.34 40 0.15 52 0.13 26 0.30 67 0.56 35 1.13 34 0.79 39
EPPM w/o HM [88]33.1 0.11 46 0.30 55 0.08 35 0.19 14 0.67 24 0.13 10 0.29 23 0.71 28 0.17 12 0.17 36 0.78 26 0.11 45 0.63 14 0.93 14 0.33 6 0.60 53 1.35 43 0.40 52 0.19 76 0.15 57 0.45 89 0.45 10 0.94 13 0.64 14
MLDP_OF [89]33.2 0.11 46 0.28 44 0.09 50 0.18 9 0.56 9 0.13 10 0.34 36 0.79 35 0.17 12 0.16 31 0.82 31 0.09 23 0.72 29 1.05 30 0.50 26 0.34 11 1.10 25 0.27 12 0.18 73 0.15 57 0.44 88 0.76 55 1.09 33 0.69 22
OFH [38]34.1 0.10 39 0.25 30 0.09 50 0.19 14 0.69 28 0.14 15 0.43 46 1.02 52 0.17 12 0.17 36 1.08 57 0.08 10 0.87 48 1.25 45 0.73 51 0.43 23 1.69 67 0.32 30 0.10 4 0.13 26 0.18 16 0.59 38 1.40 46 0.74 35
Sparse Occlusion [54]34.1 0.09 28 0.24 26 0.08 35 0.22 32 0.63 18 0.19 45 0.38 41 0.91 41 0.18 18 0.17 36 0.85 36 0.09 23 0.75 33 1.09 34 0.47 19 0.34 11 1.00 13 0.26 10 0.22 87 0.22 90 0.28 58 0.53 31 1.13 34 0.67 19
NL-TV-NCC [25]35.0 0.10 39 0.26 36 0.08 35 0.22 32 0.72 32 0.15 19 0.35 37 0.85 37 0.16 10 0.15 18 0.70 10 0.09 23 0.79 37 1.16 40 0.51 27 0.78 61 1.38 45 0.48 58 0.16 62 0.15 57 0.26 49 0.55 34 1.16 36 0.55 7
CostFilter [40]35.2 0.10 39 0.27 42 0.08 35 0.20 24 0.63 18 0.15 19 0.22 8 0.45 8 0.18 18 0.19 47 0.88 43 0.12 50 0.60 10 0.90 12 0.28 5 0.75 60 1.19 33 0.50 59 0.21 85 0.24 96 0.40 85 0.46 12 1.02 25 0.62 11
S2D-Matching [84]35.2 0.09 28 0.26 36 0.07 14 0.23 43 0.80 52 0.18 36 0.38 41 0.93 43 0.20 38 0.15 18 0.70 10 0.09 23 0.70 26 1.03 26 0.51 27 0.55 50 1.17 30 0.35 42 0.17 68 0.13 26 0.32 76 0.51 27 1.01 23 0.81 42
AggregFlow [97]36.3 0.11 46 0.32 61 0.08 35 0.31 66 0.96 68 0.23 64 0.36 39 0.85 37 0.27 61 0.17 36 0.84 34 0.10 41 0.79 37 1.17 41 0.54 31 0.27 4 0.85 7 0.19 1 0.11 11 0.13 26 0.15 7 0.59 38 1.19 38 0.83 43
EpicFlow [98]37.0 0.10 39 0.32 61 0.08 35 0.21 26 0.76 41 0.17 26 0.36 39 0.93 43 0.21 43 0.15 18 0.82 31 0.09 23 0.85 45 1.26 49 0.64 42 0.70 57 1.41 50 0.46 56 0.10 4 0.11 1 0.20 23 0.64 42 1.35 41 0.89 52
SimpleFlow [49]37.9 0.09 28 0.24 26 0.08 35 0.24 48 0.78 47 0.20 55 0.43 46 0.96 47 0.21 43 0.16 31 0.77 23 0.09 23 0.71 27 1.04 28 0.55 33 1.47 82 1.59 61 0.76 74 0.13 31 0.12 9 0.22 35 0.50 22 1.04 30 0.72 26
Aniso-Texture [82]38.2 0.08 7 0.21 3 0.07 14 0.19 14 0.60 15 0.17 26 0.50 56 1.11 57 0.21 43 0.12 5 0.58 4 0.07 4 0.93 60 1.28 54 0.92 65 0.46 31 1.27 37 0.38 51 0.20 78 0.20 87 0.30 67 0.68 46 1.37 44 0.88 50
Occlusion-TV-L1 [63]39.4 0.09 28 0.26 36 0.07 14 0.22 32 0.74 38 0.18 36 0.51 58 1.15 61 0.21 43 0.18 43 0.91 45 0.10 41 0.87 48 1.25 45 0.72 48 0.47 34 1.38 45 0.36 46 0.10 4 0.12 9 0.11 2 0.83 64 1.78 67 0.96 59
Adaptive [20]42.4 0.09 28 0.26 36 0.06 5 0.23 43 0.78 47 0.18 36 0.54 62 1.19 67 0.21 43 0.18 43 0.91 45 0.10 41 0.88 51 1.25 45 0.73 51 0.50 42 1.28 38 0.31 25 0.14 41 0.16 66 0.22 35 0.65 45 1.37 44 0.79 39
SRR-TVOF-NL [91]42.6 0.11 46 0.29 50 0.08 35 0.28 61 0.91 63 0.20 55 0.39 43 0.92 42 0.24 54 0.17 36 0.77 23 0.09 23 0.81 40 1.11 35 0.79 56 0.33 8 1.02 15 0.28 13 0.19 76 0.18 79 0.31 73 0.57 36 1.01 23 0.77 38
RFlow [90]43.5 0.10 39 0.27 42 0.09 50 0.19 14 0.64 21 0.15 19 0.46 54 1.07 53 0.18 18 0.22 58 1.31 70 0.11 45 0.92 58 1.30 57 0.91 64 0.42 21 1.42 52 0.31 25 0.14 41 0.13 26 0.24 42 0.77 58 1.66 61 0.94 56
TCOF [69]43.6 0.11 46 0.28 44 0.09 50 0.24 48 0.76 41 0.19 45 0.53 59 1.15 61 0.29 65 0.24 60 0.88 43 0.20 71 0.88 51 1.26 49 0.69 45 0.38 15 0.93 10 0.29 18 0.16 62 0.16 66 0.22 35 0.49 18 1.03 28 0.65 17
DPOF [18]43.7 0.12 64 0.33 65 0.08 35 0.26 56 0.80 52 0.20 55 0.24 10 0.49 10 0.20 38 0.19 47 0.83 33 0.13 54 0.66 20 0.98 23 0.40 12 1.11 71 1.41 50 0.57 65 0.25 92 0.14 47 0.55 92 0.51 27 1.02 25 0.54 5
Complementary OF [21]44.2 0.11 46 0.28 44 0.10 63 0.18 9 0.63 18 0.12 5 0.31 31 0.75 32 0.18 18 0.19 47 0.97 52 0.12 50 0.97 65 1.31 61 1.00 71 1.78 91 1.73 70 0.87 82 0.11 11 0.12 9 0.22 35 0.68 46 1.48 49 0.95 57
ACK-Prior [27]44.2 0.11 46 0.25 30 0.09 50 0.18 9 0.59 12 0.13 10 0.27 15 0.64 18 0.16 10 0.15 18 0.78 26 0.09 23 0.82 42 1.14 37 0.71 47 1.90 92 1.90 76 0.99 88 0.23 90 0.17 73 0.49 91 0.77 58 1.44 48 0.91 53
ComplOF-FED-GPU [35]46.5 0.11 46 0.29 50 0.10 63 0.21 26 0.78 47 0.14 15 0.32 34 0.79 35 0.17 12 0.19 47 0.99 53 0.11 45 0.89 53 1.29 55 0.73 51 1.25 74 1.74 71 0.64 69 0.14 41 0.13 26 0.30 67 0.64 42 1.50 51 0.83 43
Classic++ [32]47.8 0.09 28 0.25 30 0.07 14 0.23 43 0.78 47 0.19 45 0.43 46 1.00 50 0.22 49 0.20 51 1.11 58 0.10 41 0.87 48 1.30 57 0.66 44 0.47 34 1.62 62 0.33 35 0.17 68 0.14 47 0.32 76 0.79 62 1.64 59 0.92 54
Aniso. Huber-L1 [22]48.2 0.10 39 0.28 44 0.08 35 0.31 66 0.88 60 0.28 70 0.56 65 1.13 58 0.29 65 0.20 51 0.92 48 0.13 54 0.84 44 1.20 42 0.70 46 0.39 17 1.23 35 0.28 13 0.17 68 0.15 57 0.27 55 0.64 42 1.36 43 0.79 39
DeepFlow [86]50.2 0.12 64 0.31 58 0.11 69 0.28 61 0.82 55 0.22 62 0.44 52 1.00 50 0.33 70 0.26 66 1.34 73 0.15 62 0.81 40 1.21 43 0.58 36 0.38 15 1.55 60 0.25 7 0.11 11 0.11 1 0.24 42 0.93 70 1.82 71 1.12 68
CRTflow [80]50.3 0.11 46 0.30 55 0.08 35 0.24 48 0.77 44 0.17 26 0.50 56 1.13 58 0.21 43 0.23 59 1.24 65 0.12 50 0.86 47 1.27 52 0.65 43 0.60 53 1.95 80 0.50 59 0.12 22 0.14 47 0.21 30 0.79 62 1.77 66 0.98 61
TriangleFlow [30]51.1 0.11 46 0.29 50 0.09 50 0.26 56 0.95 66 0.17 26 0.47 55 1.07 53 0.18 18 0.16 31 0.87 41 0.09 23 1.07 74 1.47 80 1.10 76 0.87 64 1.39 47 0.57 65 0.15 52 0.19 85 0.23 41 0.63 41 1.33 40 0.84 46
TV-L1-improved [17]53.1 0.09 28 0.26 36 0.07 14 0.20 24 0.71 31 0.16 23 0.53 59 1.18 66 0.22 49 0.21 55 1.24 65 0.11 45 0.90 54 1.31 61 0.72 48 1.51 84 1.93 78 0.84 78 0.18 73 0.17 73 0.31 73 0.73 51 1.62 58 0.87 49
SIOF [67]53.2 0.11 46 0.28 44 0.09 50 0.27 59 0.95 66 0.20 55 0.60 72 1.17 63 0.48 72 0.25 64 1.13 59 0.16 63 0.97 65 1.33 64 1.03 72 0.43 23 1.32 41 0.36 46 0.13 31 0.13 26 0.18 16 0.76 55 1.52 53 1.14 72
CBF [12]55.0 0.10 39 0.28 44 0.09 50 0.34 71 0.80 52 0.37 74 0.43 46 0.95 46 0.26 57 0.21 55 1.14 60 0.13 54 0.90 54 1.27 52 0.82 59 0.41 19 1.23 35 0.30 22 0.23 90 0.19 85 0.39 84 0.76 55 1.56 54 1.02 62
LocallyOriented [52]55.3 0.12 64 0.35 70 0.08 35 0.33 70 1.01 71 0.25 67 0.61 74 1.30 75 0.28 62 0.18 43 0.80 29 0.13 54 0.93 60 1.29 55 0.79 56 0.98 67 1.48 56 0.56 64 0.12 22 0.14 47 0.21 30 0.73 51 1.48 49 0.95 57
Brox et al. [5]57.1 0.11 46 0.32 61 0.11 69 0.27 59 0.93 64 0.22 62 0.39 43 0.94 45 0.24 54 0.24 60 1.25 67 0.13 54 1.10 80 1.39 74 1.43 88 0.89 66 1.77 73 0.55 63 0.10 4 0.13 26 0.11 2 0.91 67 1.83 73 1.13 70
Local-TV-L1 [65]57.1 0.14 73 0.34 67 0.14 77 0.47 77 1.05 74 0.43 77 0.72 78 1.25 72 0.52 73 0.31 74 1.39 76 0.22 73 0.83 43 1.21 43 0.63 41 0.39 17 1.29 39 0.29 18 0.11 11 0.11 1 0.22 35 1.06 75 1.87 74 1.67 83
F-TV-L1 [15]57.5 0.14 73 0.35 70 0.14 77 0.34 71 0.98 69 0.26 68 0.59 71 1.19 67 0.26 57 0.27 69 1.36 75 0.16 63 0.90 54 1.30 57 0.76 55 0.54 48 1.62 62 0.36 46 0.13 31 0.15 57 0.20 23 0.68 46 1.56 54 0.66 18
CLG-TV [48]57.5 0.11 46 0.29 50 0.09 50 0.32 68 0.86 59 0.30 71 0.55 63 1.17 63 0.28 62 0.25 64 1.05 55 0.17 66 0.92 58 1.30 57 0.79 56 0.47 34 1.72 69 0.35 42 0.17 68 0.17 73 0.25 47 0.74 54 1.57 56 0.88 50
Fusion [6]58.8 0.11 46 0.34 67 0.10 63 0.19 14 0.69 28 0.16 23 0.29 23 0.66 23 0.23 52 0.20 51 1.19 62 0.14 60 1.07 74 1.42 77 1.22 81 1.35 77 1.49 57 0.86 80 0.20 78 0.20 87 0.26 49 1.07 77 2.07 83 1.39 79
SuperFlow [81]58.8 0.11 46 0.29 50 0.08 35 0.34 71 0.85 58 0.33 72 0.53 59 1.08 56 0.59 76 0.28 71 1.23 64 0.21 72 0.99 68 1.32 63 1.21 80 0.46 31 1.49 57 0.36 46 0.15 52 0.16 66 0.19 19 0.90 66 1.81 69 1.07 64
Rannacher [23]59.0 0.11 46 0.31 58 0.09 50 0.25 53 0.84 57 0.21 60 0.57 68 1.27 74 0.26 57 0.24 60 1.32 71 0.13 54 0.91 57 1.33 64 0.72 48 1.49 83 1.95 80 0.78 75 0.15 52 0.14 47 0.26 49 0.69 49 1.58 57 0.86 48
TriFlow [95]60.7 0.12 64 0.33 65 0.09 50 0.30 65 0.89 61 0.27 69 0.56 65 1.17 63 0.57 75 0.21 55 0.92 48 0.16 63 1.07 74 1.38 70 1.19 79 0.35 13 1.19 33 0.29 18 0.52 98 0.22 90 1.30 98 0.73 51 1.42 47 0.83 43
Second-order prior [8]61.0 0.11 46 0.31 58 0.09 50 0.26 56 0.93 64 0.20 55 0.57 68 1.25 72 0.26 57 0.20 51 1.04 54 0.12 50 0.94 62 1.34 66 0.83 61 0.61 55 1.93 78 0.47 57 0.20 78 0.16 66 0.34 80 0.77 58 1.64 59 1.07 64
p-harmonic [29]62.0 0.12 64 0.36 75 0.11 69 0.25 53 0.82 55 0.21 60 0.57 68 1.24 69 0.28 62 0.26 66 1.20 63 0.19 70 1.07 74 1.39 74 1.31 84 0.44 27 1.65 65 0.37 50 0.15 52 0.16 66 0.21 30 0.87 65 1.76 65 1.06 63
Bartels [41]62.7 0.12 64 0.30 55 0.11 69 0.22 32 0.65 23 0.19 45 0.35 37 0.86 39 0.23 52 0.28 71 1.32 71 0.18 68 0.97 65 1.38 70 0.98 67 1.20 73 1.76 72 0.78 75 0.20 78 0.17 73 0.48 90 0.91 67 1.88 75 1.22 73
Dynamic MRF [7]63.8 0.12 64 0.34 67 0.11 69 0.22 32 0.89 61 0.16 23 0.44 52 1.13 58 0.20 38 0.24 60 1.29 69 0.14 60 1.11 81 1.52 87 1.13 77 1.54 85 2.37 92 0.93 83 0.13 31 0.12 9 0.31 73 1.27 86 2.33 92 1.66 82
SegOF [10]64.4 0.15 76 0.36 75 0.10 63 0.57 80 1.16 80 0.59 85 0.68 77 1.24 69 0.64 78 0.32 75 0.86 37 0.26 75 1.18 87 1.50 86 1.47 90 1.63 88 2.09 84 0.96 85 0.08 2 0.13 26 0.12 4 0.70 50 1.50 51 0.69 22
LDOF [28]66.5 0.12 64 0.35 70 0.10 63 0.32 68 1.06 75 0.24 66 0.43 46 0.98 48 0.30 68 0.45 80 2.48 96 0.26 75 1.01 71 1.37 69 1.05 74 1.10 70 2.08 83 0.67 71 0.12 22 0.15 57 0.24 42 0.94 71 2.05 80 1.10 66
Ad-TV-NDC [36]66.6 0.23 89 0.40 81 0.31 93 0.92 91 1.42 88 0.93 90 1.05 88 1.60 86 0.74 83 0.48 81 1.27 68 0.49 83 0.85 45 1.25 45 0.60 38 0.44 27 1.47 54 0.32 30 0.12 22 0.13 26 0.19 19 1.59 93 2.06 82 2.87 96
StereoFlow [44]69.7 0.46 100 0.77 99 0.47 97 1.41 96 2.26 99 1.16 93 1.30 97 1.94 95 1.02 94 1.33 96 2.98 98 1.16 95 1.08 78 1.49 83 0.99 68 0.31 5 1.40 48 0.22 5 0.07 1 0.11 1 0.08 1 0.98 73 1.88 75 1.31 76
Shiralkar [42]70.6 0.13 72 0.39 78 0.10 63 0.28 61 1.08 76 0.19 45 0.61 74 1.33 79 0.25 56 0.27 69 1.35 74 0.18 68 1.01 71 1.47 80 0.90 63 0.88 65 2.04 82 0.54 61 0.20 78 0.16 66 0.42 86 1.04 74 2.13 87 1.10 66
Learning Flow [11]71.2 0.11 46 0.32 61 0.09 50 0.29 64 0.99 70 0.23 64 0.55 63 1.24 69 0.29 65 0.36 76 1.56 81 0.25 74 1.25 91 1.64 93 1.41 86 1.55 87 2.32 91 0.85 79 0.14 41 0.18 79 0.24 42 1.09 78 2.09 85 1.27 74
IAOF2 [51]73.2 0.14 73 0.35 70 0.12 74 0.42 75 1.09 78 0.38 75 0.64 76 1.32 78 0.55 74 0.92 89 1.60 83 1.04 90 1.00 70 1.38 70 0.94 66 0.80 62 1.43 53 0.58 67 0.20 78 0.18 79 0.32 76 0.92 69 1.66 61 1.13 70
Filter Flow [19]74.2 0.17 78 0.39 78 0.13 75 0.43 76 1.09 78 0.38 75 0.75 79 1.34 80 0.78 86 0.70 87 1.54 80 0.68 86 1.13 84 1.38 70 1.51 91 0.57 52 1.32 41 0.44 53 0.22 87 0.23 94 0.26 49 0.96 72 1.66 61 1.12 68
Modified CLG [34]75.7 0.19 84 0.46 86 0.17 81 0.49 79 1.08 76 0.51 81 0.93 83 1.59 84 0.82 88 0.49 82 1.65 86 0.42 81 1.14 85 1.48 82 1.42 87 1.06 69 2.16 88 0.68 73 0.12 22 0.14 47 0.20 23 1.12 81 2.17 89 1.52 80
GroupFlow [9]75.8 0.21 85 0.51 88 0.21 87 0.79 89 1.69 92 0.72 88 0.86 82 1.64 87 0.74 83 0.30 73 1.07 56 0.26 75 1.29 94 1.81 96 0.82 59 1.94 94 2.30 90 1.36 95 0.11 11 0.14 47 0.19 19 1.06 75 1.96 77 1.35 78
GraphCuts [14]75.9 0.16 77 0.38 77 0.14 77 0.59 83 1.36 87 0.46 78 0.56 65 1.07 53 0.64 78 0.26 66 1.14 60 0.17 66 0.96 63 1.35 67 0.84 62 2.25 98 1.79 74 1.22 94 0.22 87 0.17 73 0.43 87 1.22 84 2.05 80 1.78 86
IAOF [50]76.3 0.17 78 0.39 78 0.18 83 0.61 84 1.23 82 0.55 84 1.20 92 1.87 94 0.73 82 0.66 86 1.46 77 0.72 87 0.99 68 1.36 68 0.99 68 0.73 59 1.83 75 0.45 54 0.18 73 0.15 57 0.27 55 1.30 87 1.81 69 2.09 91
SPSA-learn [13]76.4 0.18 82 0.45 85 0.17 81 0.57 80 1.32 85 0.51 81 0.84 81 1.50 81 0.72 81 0.52 84 1.64 85 0.49 83 1.12 83 1.42 77 1.39 85 1.75 90 2.14 86 1.06 91 0.13 31 0.13 26 0.19 19 1.32 88 2.08 84 1.73 85
Black & Anandan [4]76.7 0.18 82 0.42 83 0.19 84 0.58 82 1.31 84 0.50 80 0.95 85 1.58 83 0.70 80 0.49 82 1.59 82 0.45 82 1.08 78 1.42 77 1.22 81 1.43 80 2.28 89 0.83 77 0.15 52 0.17 73 0.17 12 1.11 79 1.98 78 1.30 75
BlockOverlap [61]77.2 0.17 78 0.35 70 0.16 80 0.48 78 1.02 72 0.46 78 0.75 79 1.31 77 0.59 76 0.40 79 1.47 78 0.33 80 0.96 63 1.26 49 1.14 78 1.40 79 1.47 54 0.86 80 0.31 95 0.22 90 0.86 97 1.20 83 1.78 67 2.19 92
HBpMotionGpu [43]77.5 0.17 78 0.41 82 0.13 75 0.61 84 1.34 86 0.59 85 0.95 85 1.68 88 0.76 85 0.38 77 1.63 84 0.27 78 1.11 81 1.49 83 1.27 83 0.66 56 1.53 59 0.45 54 0.20 78 0.18 79 0.28 58 1.12 81 2.04 79 1.67 83
2D-CLG [1]78.8 0.28 91 0.62 93 0.21 87 0.67 87 1.21 81 0.70 87 1.12 89 1.80 91 0.99 93 1.07 93 2.06 91 1.12 94 1.23 90 1.52 87 1.62 94 1.54 85 2.15 87 0.96 85 0.10 4 0.11 1 0.16 10 1.38 91 2.26 91 1.83 88
2bit-BM-tele [99]79.3 0.21 85 0.42 83 0.23 90 0.39 74 1.04 73 0.35 73 0.60 72 1.30 75 0.36 71 0.38 77 1.49 79 0.30 79 1.01 71 1.41 76 0.99 68 1.39 78 1.68 66 0.95 84 0.31 95 0.23 94 0.70 95 1.11 79 2.09 85 1.61 81
Nguyen [33]79.7 0.22 87 0.47 87 0.19 84 0.87 90 1.29 83 0.97 91 1.17 91 1.81 92 0.92 91 0.99 91 1.82 87 1.07 91 1.17 86 1.49 83 1.46 89 0.72 58 2.09 84 0.60 68 0.14 41 0.14 47 0.20 23 1.37 89 2.18 90 1.86 89
Horn & Schunck [3]83.8 0.22 87 0.55 89 0.22 89 0.61 84 1.53 90 0.52 83 1.01 87 1.73 89 0.80 87 0.78 88 2.02 89 0.77 88 1.26 92 1.58 91 1.55 92 1.43 80 2.59 95 1.00 89 0.16 62 0.18 79 0.15 7 1.51 92 2.50 93 1.88 90
TI-DOFE [24]86.2 0.38 97 0.64 94 0.47 97 1.16 94 1.72 93 1.26 96 1.39 98 2.06 100 1.17 96 1.29 95 2.21 93 1.41 97 1.27 93 1.61 92 1.57 93 1.28 75 2.57 94 1.01 90 0.13 31 0.15 57 0.16 10 1.87 95 2.71 95 2.53 94
SILK [79]86.8 0.25 90 0.55 89 0.29 91 0.77 88 1.49 89 0.79 89 1.14 90 1.83 93 0.84 89 0.59 85 1.82 87 0.55 85 1.36 95 1.69 94 1.82 96 1.92 93 2.65 96 1.15 93 0.16 62 0.13 26 0.36 81 1.69 94 2.54 94 2.30 93
HCIC-L [100]89.4 0.43 99 0.64 94 0.29 91 1.90 100 1.89 96 2.31 100 1.20 92 1.51 82 1.44 99 1.49 98 2.58 97 1.55 98 1.21 89 1.52 87 1.03 72 1.01 68 1.63 64 0.98 87 0.83 100 0.55 100 1.52 100 1.26 85 1.82 71 1.34 77
Adaptive flow [45]91.0 0.36 95 0.59 91 0.37 96 1.21 95 1.60 91 1.23 95 1.21 94 1.77 90 1.18 97 0.94 90 2.03 90 0.97 89 1.20 88 1.57 90 1.08 75 1.73 89 1.90 76 1.12 92 0.59 99 0.37 99 1.37 99 1.37 89 2.16 88 1.81 87
SLK [47]91.7 0.30 93 0.70 96 0.36 95 1.09 93 1.77 94 1.21 94 1.25 96 1.98 97 1.03 95 1.56 99 2.26 94 1.71 99 1.54 98 1.82 97 2.14 98 2.02 95 2.79 98 1.36 95 0.17 68 0.16 66 0.26 49 2.43 97 3.18 97 3.31 98
Periodicity [78]93.0 0.31 94 0.78 100 0.20 86 1.54 98 2.62 100 1.71 97 1.86 100 2.00 98 1.66 100 1.15 94 3.05 99 1.07 91 5.17 100 6.79 100 4.19 100 3.79 100 5.26 100 2.93 100 0.12 22 0.18 79 0.36 81 2.67 98 5.01 99 3.18 97
PGAM+LK [55]94.5 0.37 96 0.70 96 0.59 99 1.08 92 1.89 96 1.15 92 0.94 84 1.59 84 0.88 90 1.40 97 3.28 100 1.33 96 1.37 96 1.70 95 1.67 95 2.10 96 2.53 93 1.39 97 0.36 97 0.28 98 0.65 93 1.89 96 2.72 96 2.71 95
FOLKI [16]95.7 0.29 92 0.73 98 0.33 94 1.52 97 1.96 98 1.80 98 1.23 95 2.04 99 0.95 92 0.99 91 2.20 92 1.08 93 1.53 97 1.85 98 2.07 97 2.14 97 3.23 99 1.60 98 0.26 93 0.21 89 0.68 94 2.67 98 3.27 98 4.32 99
Pyramid LK [2]97.9 0.39 98 0.61 92 0.61 100 1.67 99 1.78 95 2.00 99 1.50 99 1.97 96 1.38 98 1.57 100 2.39 95 1.78 100 2.94 99 3.72 99 2.98 99 3.33 99 2.74 97 2.43 99 0.30 94 0.24 96 0.73 96 3.80 100 5.08 100 4.88 100
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. Veltkamp, and N. van der Aa. Adaptive guided image filter to warped interpolation image for variational optical flow computation. Submitted to Pattern Recognition 2014.
[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] IVANN 673 2 color Anonymous. Constructing dense correspondence for complex motion - integrated variational and nearest neighbor field (IVANN). CVPR 2014 submission 283.
[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. Submitted to IEEE TCSVT 2013.
[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. Submitted to TIP 2014.
[98] EpicFlow 17 2 color Anonymous. EpicFlow: edge-preserving interpolation of correspondences for optical flow. (Parameters optimized on MPI-Sintel.) ECCV 2014 submission 159.
[99] 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.
[100] HCIC-L 330 2 color Anonymous. Globally-optimal image correspondence using a hierarchical graphical model. NIPS 2014 submission 114.
* 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.