Optical flow evaluation results: Average angle error

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

Average 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]	5.2	2.69 3	7.56 4	1.98 3	1.97 4	7.01 4	1.59 4	2.18 2	5.36 3	1.53 4	1.87 3	9.14 7	1.06 4	2.28 2	2.94 1	1.57 2	2.39 5	6.78 2	2.15 9	2.00 21	3.36 17	1.62 15	0.99 1	2.16 3	0.57 2
NN-field [71]	10.1	2.89 8	8.13 16	2.11 5	2.10 6	7.15 9	1.77 15	2.27 4	5.59 5	1.61 8	1.58 1	8.52 6	0.79 1	2.35 4	3.05 5	1.60 3	1.89 1	5.20 1	1.37 1	2.43 49	3.70 50	1.95 38	1.01 2	2.25 4	0.53 1
OFLAF [77]	13.1	3.04 15	7.80 10	2.40 13	2.14 7	7.02 5	1.72 9	2.25 3	5.32 2	1.56 5	2.62 19	13.7 25	1.37 21	2.35 4	3.13 6	1.62 4	2.98 22	7.73 7	2.57 21	2.08 27	3.27 12	2.05 42	1.33 13	2.43 7	1.40 16
PMMST [114]	14.3	3.42 42	7.60 5	2.65 30	2.32 11	6.39 1	2.20 33	2.63 11	6.08 8	2.03 27	2.06 6	6.07 2	1.44 29	2.60 10	3.27 8	1.91 10	2.56 7	6.78 2	2.09 5	2.06 23	3.53 36	1.63 16	1.27 10	2.29 5	1.02 7
nLayers [57]	16.7	2.80 6	7.42 3	2.20 8	2.71 30	7.24 10	2.55 60	2.61 9	6.24 9	2.45 52	2.30 12	12.7 13	1.16 7	2.30 3	3.02 3	1.70 5	2.62 10	6.95 4	2.09 5	2.29 43	3.46 26	1.89 35	1.38 15	3.06 18	1.29 14
MDP-Flow2 [68]	19.1	3.23 31	7.93 13	2.60 22	1.92 2	6.64 2	1.52 1	2.46 7	5.91 7	1.56 5	3.05 44	15.8 54	1.51 39	2.77 24	3.50 18	2.16 27	2.86 18	8.58 18	2.70 32	2.00 21	3.50 33	1.59 13	1.28 11	2.67 12	0.89 4
ComponentFusion [96]	19.4	2.78 5	8.20 17	2.05 4	2.04 5	7.31 11	1.66 8	2.55 8	6.78 13	1.61 8	2.24 11	13.1 15	1.01 3	2.71 21	3.56 20	2.10 22	3.55 51	12.4 58	3.22 58	2.19 38	3.60 43	1.54 12	1.32 12	2.91 14	1.13 9
TC/T-Flow [76]	21.7	2.69 3	7.75 9	1.87 2	2.76 33	10.2 47	1.73 10	3.33 25	9.01 31	1.49 2	2.86 35	16.7 64	1.21 9	2.60 10	3.49 17	1.90 9	2.21 2	7.65 5	2.04 4	1.84 10	3.23 9	3.14 89	2.03 38	4.53 38	1.49 20
FC-2Layers-FF [74]	25.1	3.02 14	7.87 12	2.61 23	2.72 31	9.35 36	2.29 41	2.36 5	5.47 4	2.15 34	2.48 13	12.6 12	1.28 12	2.49 7	3.19 7	2.03 16	3.39 40	8.92 20	2.83 42	2.83 72	3.92 64	2.80 68	1.25 8	2.57 11	1.20 11
WLIF-Flow [93]	26.4	2.96 10	7.67 6	2.40 13	2.41 16	7.70 15	2.10 27	2.98 17	7.63 19	1.97 26	2.71 27	13.5 21	1.33 15	3.01 43	4.00 49	2.40 45	3.03 25	8.32 12	2.44 16	2.09 29	3.36 17	2.04 41	2.26 46	4.97 46	2.59 52
Layers++ [37]	26.8	3.11 18	8.22 20	2.79 42	2.43 19	7.02 5	2.24 36	2.43 6	5.77 6	2.18 37	2.13 8	9.71 9	1.15 6	2.35 4	3.02 3	1.96 11	3.81 59	11.4 44	3.22 58	2.74 67	4.01 69	2.35 53	1.45 16	3.05 17	1.79 30
HAST [109]	27.2	2.58 1	7.12 1	1.81 1	2.41 16	7.05 7	2.10 27	1.83 1	4.19 1	1.17 1	2.84 34	15.5 49	1.08 5	2.23 1	2.97 2	1.40 1	3.72 56	10.0 33	3.92 81	3.40 94	4.90 99	5.66 121	1.20 7	2.09 1	1.24 12
FESL [72]	28.5	2.96 10	7.70 7	2.54 18	3.26 68	10.4 49	2.56 61	3.25 23	8.39 23	2.17 35	2.56 15	13.2 16	1.31 14	2.57 9	3.40 11	2.12 25	2.60 9	7.65 5	2.30 10	2.64 63	4.22 78	2.47 56	1.75 27	3.49 26	1.71 25
AGIF+OF [85]	28.6	3.06 16	8.20 17	2.55 20	3.17 58	10.6 52	2.46 54	3.46 30	8.97 30	2.24 40	2.61 17	13.7 25	1.33 15	2.63 15	3.46 15	2.11 23	2.88 20	8.34 14	2.35 12	2.10 31	3.56 39	2.09 44	1.80 29	3.68 29	2.24 41
Efficient-NL [60]	28.7	2.99 13	8.23 21	2.28 9	2.72 31	8.95 32	2.25 39	3.81 40	9.87 37	2.07 31	2.77 31	14.3 33	1.46 34	2.61 12	3.48 16	1.96 11	3.31 36	8.33 13	2.59 23	2.60 58	3.75 51	2.54 59	1.60 22	3.02 15	1.66 22
LME [70]	28.9	3.15 23	8.04 15	2.31 11	1.95 3	6.65 3	1.59 4	4.03 46	9.31 32	4.57 93	2.69 25	13.6 23	1.42 26	2.85 31	3.61 23	2.42 47	3.47 47	12.8 63	3.17 54	2.12 33	3.53 36	1.73 18	1.34 14	2.75 13	1.18 10
ALD-Flow [66]	29.0	2.82 7	7.86 11	2.16 6	2.84 40	10.1 44	1.86 17	3.73 38	10.4 41	1.67 12	3.10 46	16.8 65	1.28 12	2.69 20	3.60 22	1.85 8	2.79 14	11.3 43	2.32 11	2.07 25	3.25 11	3.10 86	2.03 38	5.11 47	1.94 33
RNLOD-Flow [121]	30.0	2.66 2	7.33 2	2.17 7	2.53 26	9.46 38	1.86 17	3.94 44	10.7 47	1.95 24	2.50 14	13.5 21	1.21 9	2.68 18	3.62 25	2.05 18	2.99 23	8.59 19	2.75 36	3.00 81	4.54 88	3.25 94	1.48 18	3.24 21	1.76 29
IROF++ [58]	30.6	3.17 25	8.69 30	2.61 23	2.79 35	9.61 39	2.33 42	3.43 27	8.86 27	2.38 46	2.87 36	14.8 38	1.52 41	2.74 22	3.57 21	2.19 29	3.20 32	9.70 30	2.71 33	1.96 19	3.45 25	1.22 6	1.80 29	4.06 31	2.50 48
NNF-EAC [103]	30.7	3.31 34	8.21 19	2.68 32	2.19 9	7.49 13	1.76 13	2.73 13	6.62 12	1.70 14	3.18 51	15.8 54	1.64 50	2.87 34	3.66 28	2.24 31	3.02 24	8.07 10	2.59 23	2.19 38	3.48 29	1.74 19	2.85 60	6.52 62	3.12 64
PH-Flow [101]	31.0	3.19 28	8.87 35	2.71 33	2.84 40	9.33 35	2.37 44	2.85 14	7.20 15	2.36 43	2.92 39	15.4 46	1.51 39	2.63 15	3.42 12	2.04 17	3.03 25	8.52 17	2.49 18	2.69 65	3.60 43	3.13 88	1.25 8	2.53 9	1.34 15
Classic+CPF [83]	31.6	3.14 21	8.60 27	2.63 27	3.03 56	10.6 52	2.33 42	3.66 34	9.58 33	2.20 38	2.61 17	14.1 30	1.34 18	2.68 18	3.53 19	2.21 30	2.85 17	7.95 9	2.38 13	2.44 51	3.49 31	2.90 79	1.67 25	3.40 24	2.43 47
Sparse-NonSparse [56]	33.4	3.14 21	8.75 32	2.76 40	3.02 54	10.6 52	2.43 49	3.45 29	8.96 28	2.36 43	2.66 22	13.7 25	1.42 26	2.85 31	3.75 35	2.33 36	3.28 35	9.40 26	2.73 34	2.42 48	3.31 14	2.69 63	1.47 17	3.07 19	1.66 22
TC-Flow [46]	34.4	2.91 9	8.00 14	2.34 12	2.18 8	8.77 27	1.52 1	3.84 42	10.7 47	1.49 2	3.13 47	16.6 63	1.46 34	2.78 25	3.73 34	1.96 11	3.08 28	11.4 44	2.66 27	1.94 17	3.43 22	3.20 93	3.06 65	7.04 64	4.08 89
3DFlow [135]	34.9	3.44 43	8.63 29	2.46 15	2.43 19	8.59 26	1.75 12	3.71 36	9.93 39	1.64 10	1.61 2	4.58 1	1.23 11	2.86 33	3.72 32	2.16 27	4.52 81	11.6 50	4.20 88	3.16 89	4.02 70	4.44 113	1.13 5	2.14 2	0.89 4
LSM [39]	35.6	3.12 19	8.62 28	2.75 39	3.00 52	10.5 51	2.44 51	3.43 27	8.85 26	2.35 42	2.66 22	13.6 23	1.44 29	2.82 27	3.68 29	2.36 38	3.38 39	9.41 27	2.81 40	2.69 65	3.52 34	2.84 72	1.59 21	3.38 23	1.80 31
SVFilterOh [111]	36.3	3.63 49	8.82 33	2.86 44	2.60 28	8.06 18	2.05 26	2.95 15	7.09 14	2.03 27	2.80 33	13.8 28	1.41 25	2.63 15	3.42 12	1.75 7	3.49 48	10.3 35	3.23 61	3.63 102	5.75 120	4.47 114	1.09 4	2.45 8	0.92 6
Correlation Flow [75]	36.4	3.38 40	8.40 23	2.64 28	2.23 10	7.54 14	1.56 3	5.14 67	13.1 66	1.60 7	2.09 7	8.15 5	1.35 20	3.12 51	4.09 56	2.34 37	4.01 70	11.5 48	4.00 83	2.59 57	3.61 45	3.00 84	1.49 19	3.04 16	1.42 18
Ramp [62]	36.6	3.18 27	8.83 34	2.73 36	2.89 45	10.1 44	2.44 51	3.27 24	8.43 24	2.38 46	2.74 29	14.2 31	1.46 34	2.82 27	3.69 31	2.29 34	3.37 38	9.31 24	2.93 46	2.62 61	3.38 20	3.19 92	1.54 20	3.21 20	2.24 41
PMF [73]	37.0	3.61 47	9.07 38	2.62 25	2.40 14	8.05 17	1.83 16	2.61 9	6.27 10	1.65 11	3.35 60	15.4 46	1.58 45	2.54 8	3.27 8	1.71 6	3.59 52	11.1 41	3.46 67	4.07 112	6.18 126	4.02 109	1.06 3	2.38 6	1.25 13
ProbFlowFields [128]	37.4	4.18 68	12.4 83	3.40 74	2.43 19	8.16 20	2.19 32	3.65 33	9.72 35	2.86 67	2.22 9	9.42 8	1.42 26	3.01 43	3.96 46	2.36 38	2.73 13	10.9 36	2.51 19	1.89 16	3.39 21	1.82 24	2.59 53	6.21 60	2.75 55
COFM [59]	37.6	3.17 25	9.90 54	2.46 15	2.41 16	8.34 23	1.92 20	3.77 39	10.5 42	2.54 55	2.71 27	14.9 40	1.19 8	3.08 48	3.92 44	3.25 87	3.83 62	10.9 36	3.15 53	2.20 41	3.35 15	2.91 81	1.62 24	2.56 10	2.09 37
FMOF [94]	38.5	3.12 19	8.23 21	2.73 36	3.25 65	10.7 59	2.52 58	3.01 18	7.61 18	2.20 38	2.56 15	13.4 19	1.33 15	2.75 23	3.61 23	2.24 31	3.66 54	8.50 16	2.78 38	2.62 61	3.84 59	3.27 96	2.66 57	5.69 51	1.95 35
JOF [141]	38.7	3.08 17	8.56 26	2.51 17	3.27 69	10.2 47	2.81 78	3.02 19	7.55 17	2.42 50	2.64 20	14.2 31	1.34 18	2.62 13	3.42 12	2.08 19	3.26 33	8.96 21	2.56 20	3.12 88	4.26 79	4.09 111	2.11 44	4.58 40	2.18 39
OAR-Flow [125]	39.5	3.37 38	9.87 53	2.67 31	4.22 88	12.8 82	2.87 80	4.95 63	13.4 69	2.66 59	3.23 53	16.4 62	1.37 21	2.83 29	3.82 38	1.97 14	2.49 6	10.9 36	1.87 3	1.52 2	2.82 1	1.86 29	1.85 32	4.35 36	1.68 24
Classic+NL [31]	40.0	3.20 30	8.72 31	2.81 43	3.02 54	10.6 52	2.44 51	3.46 30	8.84 25	2.38 46	2.78 32	14.3 33	1.46 34	2.83 29	3.68 29	2.31 35	3.40 41	9.09 23	2.76 37	2.87 74	3.82 58	2.86 76	1.67 25	3.53 27	2.26 44
TV-L1-MCT [64]	41.1	3.16 24	8.48 25	2.71 33	3.28 70	10.8 63	2.60 68	3.95 45	10.5 42	2.38 46	2.69 25	13.9 29	1.45 33	2.94 39	3.79 36	2.63 66	3.50 49	9.75 31	3.06 50	2.08 27	3.35 15	2.29 51	1.95 35	3.89 30	2.71 54
IIOF-NLDP [131]	44.3	3.65 50	9.81 52	2.56 21	2.79 35	9.36 37	2.00 22	4.28 52	11.3 53	1.69 13	2.02 5	7.52 4	1.38 24	3.36 72	4.52 86	2.40 45	3.82 60	11.2 42	3.67 75	2.07 25	3.79 55	1.88 33	2.91 62	5.30 50	4.17 90
SimpleFlow [49]	45.0	3.35 35	9.20 41	2.98 51	3.18 61	10.7 59	2.71 72	5.06 65	12.6 64	2.70 61	2.95 41	15.1 42	1.58 45	2.91 37	3.79 36	2.47 49	3.59 52	9.49 28	2.99 48	2.39 46	3.46 26	2.24 50	1.60 22	3.56 28	1.57 21
CostFilter [40]	45.0	3.84 53	9.64 48	3.06 53	2.55 27	8.09 19	2.03 24	2.69 12	6.47 11	1.88 20	3.66 70	16.8 65	1.88 62	2.62 13	3.34 10	1.99 15	4.05 71	11.0 40	3.65 74	4.16 114	7.18 133	4.66 116	1.16 6	3.36 22	0.87 3
2DHMM-SAS [92]	47.1	3.19 28	8.89 36	2.71 33	3.20 63	11.5 70	2.38 45	5.19 68	12.2 60	2.73 63	2.92 39	15.2 43	1.53 42	2.79 26	3.65 27	2.27 33	3.45 45	9.34 25	2.78 38	2.66 64	3.56 39	3.07 85	2.34 49	5.12 48	2.97 62
S2D-Matching [84]	48.2	3.36 36	9.66 49	2.86 44	3.19 62	11.1 66	2.46 54	4.86 62	12.9 65	2.47 53	2.67 24	13.2 16	1.44 29	2.87 34	3.72 32	2.38 41	3.45 45	9.76 32	2.95 47	3.05 82	3.79 55	3.30 98	1.95 35	4.16 34	3.00 63
MLDP_OF [89]	48.5	4.13 64	10.3 61	3.60 82	2.34 12	7.70 15	1.88 19	4.23 51	10.9 50	1.87 19	2.74 29	14.6 37	1.37 21	3.10 49	3.91 43	2.48 53	3.40 41	9.00 22	3.79 78	3.46 96	4.20 76	5.55 120	2.31 47	4.64 42	1.98 36
MDP-Flow [26]	48.6	3.48 45	9.46 45	3.10 55	2.45 22	7.36 12	2.41 46	3.21 22	8.31 22	2.78 65	3.18 51	17.8 70	1.70 55	3.03 45	3.87 39	2.60 62	3.43 43	12.6 61	2.81 40	2.19 38	3.88 62	1.60 14	4.13 81	9.96 87	3.86 84
FlowFields+ [130]	48.6	4.57 86	13.7 96	3.35 66	2.94 50	10.1 44	2.58 65	4.05 47	10.6 44	3.26 76	2.90 38	13.2 16	1.81 60	3.18 55	4.20 63	2.54 55	2.68 12	11.4 44	2.40 15	1.84 10	3.62 46	1.77 20	2.48 50	5.86 53	2.77 56
AggregFlow [97]	49.0	4.25 74	11.9 80	3.26 58	4.46 93	13.7 92	3.43 90	4.76 60	12.4 61	3.93 90	3.28 56	15.6 50	1.68 52	2.89 36	3.89 41	2.08 19	2.32 3	7.75 8	2.14 7	2.06 23	3.77 53	1.48 11	2.07 42	4.11 32	2.36 45
IROF-TV [53]	49.7	3.40 41	9.29 43	2.95 50	2.99 51	11.1 66	2.53 59	3.81 40	9.81 36	2.44 51	3.25 55	16.9 67	1.78 59	3.27 69	4.10 57	2.93 79	4.47 78	16.0 90	3.53 69	1.70 4	3.21 7	1.12 3	1.91 34	4.75 44	2.19 40
CombBMOF [113]	50.1	3.94 57	10.6 65	2.74 38	2.80 37	8.55 25	2.16 30	3.10 21	7.99 21	1.76 15	2.99 42	13.4 19	1.95 66	3.04 46	3.89 41	2.49 54	5.64 100	12.3 56	6.74 114	3.54 98	5.16 107	2.81 69	1.85 32	4.60 41	1.10 8
S2F-IF [123]	51.1	4.51 84	13.6 95	3.31 62	2.90 46	10.4 49	2.48 57	4.07 49	10.8 49	3.15 72	3.31 57	15.7 53	1.90 63	3.17 53	4.19 61	2.55 58	2.81 16	11.6 50	2.60 25	1.86 13	3.67 48	1.87 30	2.11 44	4.64 42	2.54 51
FlowFields [110]	53.8	4.57 86	13.7 96	3.38 69	3.01 53	10.6 52	2.59 66	4.19 50	11.1 51	3.30 77	3.17 50	15.0 41	1.96 67	3.21 62	4.24 70	2.61 65	2.91 21	12.4 58	2.66 27	1.84 10	3.46 26	1.84 27	2.50 51	6.15 58	2.79 57
NL-TV-NCC [25]	54.3	3.89 55	9.16 40	2.98 51	2.87 44	9.69 40	1.99 21	4.44 56	11.6 55	1.76 15	2.64 20	11.8 11	1.48 38	3.49 84	4.60 91	2.47 49	4.67 86	13.5 68	4.26 91	2.83 72	4.57 90	2.84 72	2.62 55	6.00 57	2.25 43
Sparse Occlusion [54]	54.4	3.62 48	9.12 39	2.90 46	2.92 48	9.08 33	2.56 61	4.49 57	11.8 58	2.11 33	3.14 48	15.8 54	1.57 44	3.26 67	4.22 66	2.36 38	3.52 50	10.9 36	2.66 27	5.10 129	6.32 127	3.15 90	2.02 37	4.92 45	1.71 25
OFH [38]	54.9	3.90 56	9.77 51	3.62 85	2.84 40	11.0 65	2.04 25	5.52 73	14.4 74	1.89 21	3.52 63	20.5 88	1.60 48	3.18 55	4.06 54	2.82 74	3.86 63	14.1 76	3.59 71	1.77 6	3.62 46	1.81 23	2.64 56	7.08 66	2.15 38
EPPM w/o HM [88]	55.0	4.25 74	11.1 69	3.13 56	2.36 13	8.35 24	1.76 13	3.72 37	10.2 40	1.81 17	3.24 54	14.5 36	1.94 65	3.16 52	3.94 45	2.82 74	4.78 89	12.9 64	4.32 92	3.64 104	4.54 88	5.73 122	1.76 28	4.11 32	1.94 33
PGM-C [120]	55.6	4.62 91	14.0 101	3.39 71	3.29 72	12.3 75	2.70 71	4.39 55	11.7 56	3.43 80	4.00 78	19.8 77	2.15 72	3.19 57	4.23 67	2.54 55	2.79 14	11.9 53	2.45 17	1.83 8	3.21 7	1.83 25	2.31 47	5.87 54	1.82 32
Occlusion-TV-L1 [63]	56.8	3.59 46	9.61 46	2.64 28	2.93 49	10.6 52	2.41 46	6.16 80	15.2 78	2.70 61	3.32 58	17.0 68	1.68 52	3.38 74	4.44 80	2.82 74	3.10 30	13.2 67	2.68 30	2.17 34	3.52 34	1.46 9	4.63 93	11.1 102	3.53 73
Complementary OF [21]	57.8	4.44 80	11.2 72	4.04 94	2.51 25	9.77 42	1.74 11	3.93 43	10.6 44	2.04 29	3.87 74	18.8 72	2.19 76	3.17 53	4.00 49	2.92 78	4.64 84	13.8 73	3.64 73	2.17 34	3.36 17	2.51 57	3.08 66	7.04 64	3.65 77
Adaptive [20]	58.8	3.29 32	9.43 44	2.28 9	3.10 57	11.4 69	2.46 54	6.58 84	15.7 84	2.52 54	3.14 48	15.6 50	1.56 43	3.67 93	4.46 82	3.48 97	3.32 37	13.0 66	2.38 13	2.76 70	4.39 83	1.93 37	3.58 73	8.18 73	2.88 59
Aniso-Texture [82]	59.2	2.96 10	7.72 8	2.54 18	2.48 24	8.26 22	2.24 36	6.48 82	15.9 89	2.63 57	1.96 4	10.1 10	0.98 2	3.26 67	4.21 64	2.60 62	5.74 102	16.9 99	5.61 105	4.47 121	5.88 123	3.33 99	3.51 72	7.12 67	3.68 79
ACK-Prior [27]	59.9	4.19 70	9.27 42	3.60 82	2.40 14	8.21 21	1.65 7	3.40 26	8.96 28	1.84 18	2.87 36	14.4 35	1.44 29	3.36 72	4.15 58	3.07 82	6.35 110	16.1 92	4.90 99	4.21 116	4.80 94	6.03 124	3.29 69	5.99 56	2.82 58
CPM-Flow [116]	61.4	4.63 92	14.1 104	3.39 71	3.33 73	12.5 79	2.73 73	4.37 53	11.7 56	3.43 80	4.00 78	19.9 80	2.14 71	3.19 57	4.23 67	2.54 55	3.08 28	12.0 54	2.88 44	1.87 14	3.44 23	1.84 27	2.91 62	7.48 71	2.91 61
EpicFlow [102]	61.7	4.61 90	14.0 101	3.39 71	3.33 73	12.5 79	2.74 74	5.37 70	14.8 77	3.46 83	3.94 77	19.2 74	2.13 70	3.20 59	4.23 67	2.58 61	2.87 19	12.2 55	2.64 26	1.83 8	3.28 13	1.83 25	3.21 68	7.12 67	3.61 74
DPOF [18]	62.0	4.67 95	12.6 88	3.30 60	3.57 79	10.6 52	3.12 87	3.09 20	7.50 16	2.32 41	3.06 45	14.8 38	1.82 61	3.21 62	4.18 60	2.79 73	4.47 78	12.5 60	3.33 62	4.09 113	3.92 64	6.96 126	2.09 43	4.39 37	1.74 27
DeepFlow2 [108]	62.6	4.04 61	11.2 72	3.38 69	3.80 81	12.4 78	2.86 79	5.12 66	13.4 69	3.00 68	4.17 84	20.1 82	2.18 75	2.96 40	3.97 47	2.08 19	3.06 27	12.6 61	2.69 31	2.17 34	3.24 10	2.71 64	4.74 95	10.4 95	4.38 95
TCOF [69]	63.4	4.17 67	10.4 63	3.71 88	3.17 58	10.7 59	2.59 66	6.58 84	15.7 84	3.82 88	3.69 72	16.1 59	2.37 83	3.78 97	4.95 112	2.47 49	2.59 8	8.47 15	2.58 22	3.66 106	4.83 95	2.67 62	1.83 31	4.20 35	1.46 19
ROF-ND [107]	63.5	4.12 62	10.0 55	3.37 68	2.78 34	8.82 29	2.12 29	4.61 59	11.9 59	2.09 32	2.23 10	6.56 3	1.69 54	3.60 90	4.75 101	2.85 77	4.92 92	13.6 71	3.75 76	4.59 123	5.18 108	4.10 112	2.67 58	5.19 49	3.46 72
RFlow [90]	64.5	3.82 52	10.0 55	3.44 77	2.61 29	9.73 41	2.02 23	5.66 75	14.5 75	2.05 30	3.93 76	23.1 102	1.90 63	3.24 64	4.19 61	2.66 69	4.12 74	15.2 86	3.34 64	2.61 59	3.56 39	2.65 61	4.48 88	10.5 98	3.93 88
HBM-GC [105]	65.3	5.25 101	10.5 64	4.34 101	3.17 58	8.78 28	2.94 83	4.38 54	10.6 44	2.68 60	3.59 66	12.8 14	2.47 86	2.96 40	3.64 26	2.64 67	3.96 69	8.26 11	3.56 70	4.40 119	5.92 124	3.62 103	2.55 52	6.34 61	3.29 67
Steered-L1 [118]	65.3	3.30 33	8.44 24	2.91 47	1.89 1	7.14 8	1.60 6	3.61 32	9.91 38	1.89 21	3.45 61	19.4 76	1.64 50	3.42 77	4.30 72	3.39 90	5.18 95	14.5 79	4.37 94	5.09 128	5.05 103	10.1 130	5.56 102	10.2 93	6.24 108
DMF_ROB [140]	66.9	4.37 77	12.3 82	3.62 85	3.46 77	12.9 84	2.60 68	5.98 77	15.8 86	3.23 75	4.05 80	19.8 77	2.15 72	3.10 49	4.06 54	2.57 60	3.79 58	14.3 77	3.13 52	1.88 15	3.12 5	1.99 40	4.34 83	10.0 88	3.87 85
ComplOF-FED-GPU [35]	67.2	4.28 76	11.3 74	3.70 87	3.25 65	13.0 85	2.16 30	4.06 48	11.2 52	1.95 24	3.91 75	19.2 74	2.01 68	3.20 59	4.15 58	2.64 67	4.61 83	16.1 92	3.90 80	2.98 79	3.77 53	3.69 104	2.85 60	7.44 70	2.53 50
SRR-TVOF-NL [91]	67.6	4.47 82	10.9 67	3.32 64	4.04 85	13.2 88	2.90 81	4.81 61	12.5 62	3.15 72	3.33 59	15.3 44	1.61 49	3.24 64	4.03 53	2.70 71	3.94 67	11.8 52	3.33 62	4.16 114	5.21 111	3.44 102	2.06 41	3.48 25	2.42 46
TF+OM [100]	69.8	3.97 58	10.2 58	2.94 49	2.91 47	9.12 34	2.57 64	5.22 69	11.5 54	6.92 98	3.59 66	16.1 59	2.28 80	3.20 59	3.97 47	3.11 83	4.70 87	14.5 79	4.32 92	3.06 84	4.84 96	2.71 64	3.93 77	8.79 78	4.32 94
Aniso. Huber-L1 [22]	70.5	3.71 51	10.1 57	3.08 54	4.36 92	13.0 85	3.77 94	6.92 88	15.3 80	3.60 86	3.54 64	15.9 57	2.04 69	3.38 74	4.45 81	2.47 49	3.88 64	12.9 64	2.74 35	3.37 93	4.36 82	2.85 75	3.16 67	7.52 72	2.90 60
DeepFlow [86]	71.4	4.49 83	11.7 77	4.14 96	4.26 89	12.8 82	3.36 88	5.96 76	14.2 73	5.10 94	4.89 96	23.1 102	2.67 89	2.98 42	4.00 49	2.11 23	3.26 33	13.5 68	2.84 43	2.09 29	3.10 3	2.77 66	5.83 104	11.4 104	5.45 105
Classic++ [32]	72.2	3.37 38	9.67 50	2.91 47	3.28 70	12.1 73	2.61 70	5.46 72	14.1 72	3.00 68	3.63 68	20.2 85	1.70 55	3.24 64	4.34 74	2.60 62	4.65 85	16.0 90	3.60 72	3.09 85	3.94 67	3.28 97	4.64 94	10.4 95	3.71 80
TV-L1-improved [17]	72.5	3.36 36	9.63 47	2.62 25	2.82 38	10.7 59	2.23 34	6.50 83	15.8 86	2.73 63	3.80 73	21.3 93	1.76 58	3.34 71	4.38 78	2.39 42	5.97 104	18.1 106	5.67 106	3.57 100	4.92 101	3.43 101	4.01 80	9.84 86	3.44 71
LocallyOriented [52]	75.2	4.54 85	12.8 90	3.27 59	4.73 97	14.8 99	3.73 93	7.77 95	18.3 103	3.44 82	3.56 65	15.6 50	2.22 77	3.46 81	4.47 83	2.69 70	3.15 31	10.2 34	3.19 56	2.61 59	4.20 76	2.52 58	4.39 85	8.52 75	5.23 101
SIOF [67]	75.4	4.23 72	10.2 58	3.31 62	3.97 83	14.5 97	2.97 84	7.81 97	16.4 92	7.48 100	4.82 92	20.1 82	2.96 92	3.54 87	4.49 84	3.12 84	4.31 76	13.5 68	4.13 86	2.36 45	3.59 42	1.68 17	3.46 71	7.39 69	3.37 69
TriangleFlow [30]	77.7	4.12 62	10.6 65	3.47 78	3.47 78	13.1 87	2.41 46	6.00 78	15.2 78	2.17 35	2.99 42	16.0 58	1.58 45	4.46 119	5.79 124	4.15 111	5.42 98	13.9 75	5.24 100	3.10 87	5.47 116	2.90 79	3.02 64	6.82 63	3.64 76
Brox et al. [5]	78.2	4.44 80	12.4 83	4.22 99	3.72 80	13.5 91	3.06 85	4.97 64	13.3 68	3.11 70	4.58 90	22.0 96	2.37 83	3.79 99	4.60 91	4.33 115	3.91 66	17.0 100	3.45 66	2.22 42	3.79 55	1.19 4	4.62 92	10.0 88	3.38 70
CRTflow [80]	78.2	4.18 68	11.8 79	3.20 57	3.22 64	10.8 63	2.43 49	6.20 81	15.5 82	2.63 57	4.21 85	22.0 96	2.24 78	3.32 70	4.34 74	2.44 48	7.43 117	19.3 112	8.15 120	2.55 55	4.09 72	2.59 60	4.60 91	11.2 103	4.45 96
OFRF [134]	79.5	4.77 98	11.6 75	4.03 93	8.72 112	15.3 103	8.51 115	8.49 106	16.7 94	7.32 99	4.55 89	15.3 44	3.16 99	2.92 38	3.87 39	2.13 26	3.76 57	9.69 29	3.22 58	2.98 79	4.50 87	4.04 110	4.59 90	5.76 52	8.61 116
BriefMatch [124]	79.9	3.44 43	9.01 37	2.77 41	2.85 43	9.93 43	2.23 34	2.97 16	7.65 20	1.94 23	3.64 69	20.1 82	1.75 57	4.10 113	4.90 110	5.82 125	7.95 119	17.8 103	8.08 119	4.73 125	5.20 109	12.2 132	7.88 121	12.0 107	13.7 127
Rannacher [23]	80.3	4.13 64	11.0 68	3.61 84	3.39 75	12.3 75	2.80 77	7.26 90	17.4 99	3.59 85	4.40 87	23.1 102	2.24 78	3.43 79	4.54 88	2.56 59	5.41 97	18.5 107	4.23 89	2.92 76	3.91 63	2.82 70	3.45 70	9.14 79	3.27 66
F-TV-L1 [15]	81.3	5.44 104	12.5 87	5.69 108	5.46 101	15.0 102	4.03 96	7.48 92	16.3 91	3.42 79	5.08 98	23.3 105	2.81 91	3.42 77	4.34 74	3.03 80	4.05 71	15.1 85	3.18 55	2.43 49	3.92 64	1.87 30	3.90 76	9.35 83	2.61 53
Local-TV-L1 [65]	82.1	5.33 102	12.6 88	5.19 106	6.90 107	15.7 106	6.22 105	10.0 109	18.2 102	8.89 102	5.81 104	24.7 110	3.70 103	3.05 47	4.00 49	2.39 42	4.05 71	14.6 81	3.09 51	1.95 18	3.11 4	2.15 47	5.85 105	10.8 100	7.34 111
SuperFlow [81]	82.2	4.16 66	11.1 69	3.32 64	4.80 98	12.2 74	4.68 100	7.80 96	16.0 90	10.6 110	5.16 100	22.4 100	3.24 100	3.39 76	4.24 70	3.71 101	3.44 44	13.7 72	2.91 45	3.19 90	4.62 92	1.87 30	4.74 95	10.6 99	4.24 92
DF-Auto [115]	82.4	5.04 100	13.7 96	3.30 60	6.51 104	14.1 96	6.09 104	8.14 101	16.5 93	10.2 108	5.06 97	21.3 93	3.10 98	3.74 95	4.91 111	3.25 87	2.67 11	11.4 44	2.14 7	3.36 92	5.23 112	1.45 8	4.45 87	9.18 80	4.28 93
TriFlow [95]	83.1	4.73 97	12.4 83	3.49 80	4.03 84	12.5 79	3.70 92	8.18 103	17.2 97	10.4 109	3.50 62	15.4 46	2.32 82	3.43 79	4.21 64	3.42 91	3.90 65	12.3 56	3.76 77	7.86 134	5.72 119	16.2 134	2.80 59	5.89 55	2.50 48
CLG-TV [48]	83.2	4.00 59	10.3 61	3.40 74	4.33 91	12.3 75	4.08 97	6.78 86	15.5 82	3.64 87	4.07 81	17.7 69	2.39 85	3.79 99	4.86 105	3.23 86	4.48 80	16.5 97	3.80 79	3.55 99	4.65 93	2.89 78	4.00 79	10.1 91	3.18 65
CBF [12]	84.7	3.88 54	10.2 58	3.50 81	4.60 95	11.3 68	5.06 101	5.43 71	13.1 66	3.39 78	4.09 82	21.2 92	2.16 74	3.80 102	4.72 100	3.52 98	4.33 77	14.4 78	3.01 49	4.97 126	5.51 117	4.93 118	3.99 78	9.27 82	3.91 87
Bartels [41]	86.3	4.43 78	11.1 69	4.17 98	2.83 39	8.84 30	2.56 61	4.54 58	12.5 62	2.80 66	4.87 93	22.1 98	3.05 96	3.58 89	4.35 77	4.15 111	5.55 99	17.5 101	5.78 107	3.74 107	5.02 102	5.98 123	5.21 101	11.9 106	5.20 100
Fusion [6]	86.4	4.43 78	13.7 96	4.08 95	2.47 23	8.91 31	2.24 36	3.70 35	9.68 34	3.12 71	3.68 71	19.8 77	2.54 88	4.26 116	5.16 117	4.31 114	6.32 107	16.8 98	6.15 111	4.55 122	5.78 121	3.10 86	7.12 115	13.6 116	7.86 115
p-harmonic [29]	87.1	4.64 93	13.0 91	4.43 102	3.41 76	11.9 71	2.93 82	7.60 93	18.1 101	3.96 91	4.65 91	21.0 90	2.97 94	3.46 81	4.33 73	3.34 89	4.75 88	17.5 101	4.60 98	3.05 82	4.17 74	2.15 47	5.09 100	10.9 101	3.77 82
CNN-flow-warp+ref [117]	88.0	4.93 99	14.5 108	4.29 100	4.18 87	11.9 71	4.24 98	8.23 104	19.7 110	6.35 97	5.13 99	24.4 109	2.96 92	3.55 88	4.40 79	3.85 104	3.82 60	15.0 83	3.39 65	1.96 19	3.44 23	2.14 46	10.0 125	14.8 122	10.8 123
Dynamic MRF [7]	88.7	4.58 88	12.4 83	4.14 96	3.25 65	13.9 93	2.27 40	6.02 79	16.8 95	2.36 43	4.39 86	22.6 101	2.51 87	3.61 91	4.55 89	3.46 93	6.81 112	22.2 122	6.78 116	2.41 47	3.48 29	3.69 104	9.26 123	17.8 126	10.2 120
SegOF [10]	89.0	5.85 105	13.5 94	3.98 92	7.40 108	14.9 100	8.13 113	8.55 107	17.3 98	9.01 103	6.50 109	18.1 71	5.14 111	3.90 106	4.53 87	4.81 119	6.57 111	21.7 120	6.81 117	1.65 3	3.49 31	1.08 2	3.71 74	9.23 81	3.63 75
FlowNetS+ft+v [112]	89.8	4.22 71	12.1 81	3.48 79	4.50 94	13.4 89	3.85 95	8.29 105	18.4 104	6.20 96	4.87 93	21.6 95	3.01 95	3.93 107	5.04 114	3.47 96	3.71 55	15.3 87	3.21 57	3.32 91	5.12 105	3.87 106	3.76 75	9.44 84	3.74 81
LDOF [28]	90.5	4.60 89	13.0 91	3.77 89	4.67 96	15.5 105	3.67 91	5.63 74	14.0 71	4.21 92	5.80 103	27.1 119	3.43 101	3.52 86	4.50 85	3.46 93	4.84 91	17.8 103	4.04 84	2.46 53	4.14 73	3.25 94	4.85 98	12.0 107	3.78 83
Second-order prior [8]	90.9	4.03 60	11.6 75	3.35 66	3.88 82	14.0 95	3.08 86	7.21 89	17.6 100	3.57 84	4.14 83	19.9 80	2.31 81	3.66 92	4.86 105	2.73 72	7.32 115	21.2 118	6.76 115	4.02 110	4.58 91	4.01 108	4.27 82	10.4 95	5.12 97
FlowNet2 [122]	94.5	8.58 120	18.6 117	6.31 110	9.39 117	17.6 111	9.09 118	8.06 100	15.8 86	9.81 106	5.61 102	16.2 61	4.12 105	4.04 110	4.88 107	3.79 102	4.92 92	16.2 94	4.50 95	4.28 117	6.73 129	2.84 72	2.05 40	4.54 39	1.41 17
StereoFlow [44]	95.1	17.1 136	28.1 136	17.9 135	18.7 133	29.7 134	16.5 128	20.1 133	30.9 132	17.5 128	21.2 133	38.3 135	17.9 131	4.60 120	5.05 115	5.52 121	2.38 4	11.5 48	1.77 2	1.25 1	2.92 2	0.71 1	4.49 89	10.3 94	4.23 91
EPMNet [133]	95.3	8.37 119	18.8 119	6.44 112	9.35 116	18.4 113	8.78 117	7.42 91	14.7 76	8.61 101	5.98 106	20.4 87	4.27 107	4.04 110	4.88 107	3.79 102	4.92 92	16.2 94	4.50 95	3.65 105	6.14 125	2.42 55	2.60 54	6.15 58	1.74 27
Ad-TV-NDC [36]	96.5	8.36 118	14.0 101	11.1 128	12.9 124	19.9 119	12.8 124	14.4 120	23.1 113	12.1 114	7.40 112	20.6 89	6.33 112	3.47 83	4.66 96	2.39 42	3.95 68	13.8 73	3.51 68	2.48 54	3.75 51	2.05 42	9.75 124	12.1 109	16.7 131
Learning Flow [11]	99.5	4.23 72	11.7 77	3.41 76	4.16 86	15.3 103	3.42 89	6.78 86	16.9 96	3.83 89	6.41 108	25.3 113	4.25 106	4.66 122	6.01 129	4.00 107	6.33 109	20.7 117	5.30 101	3.09 85	4.84 96	2.91 81	7.08 114	15.0 123	5.27 102
Shiralkar [42]	99.7	4.64 93	14.1 104	3.94 90	4.29 90	16.9 109	2.77 75	7.75 94	18.8 106	3.19 74	5.54 101	25.0 112	3.56 102	3.51 85	4.55 89	3.04 81	7.41 116	20.1 116	6.41 112	3.76 108	4.35 81	5.28 119	6.56 111	14.4 121	5.30 103
StereoOF-V1MT [119]	100.3	4.71 96	14.1 104	3.95 91	5.10 100	20.3 121	2.78 76	7.98 99	20.7 111	2.57 56	4.48 88	21.1 91	2.79 90	4.20 115	5.29 119	4.10 109	6.85 114	22.3 123	6.42 113	2.45 52	4.17 74	3.15 90	10.5 126	18.4 129	10.5 121
IAOF2 [51]	101.2	5.38 103	13.7 96	4.50 103	5.95 103	14.6 98	5.61 103	8.80 108	18.8 106	9.40 104	12.2 122	23.8 108	13.1 126	3.86 103	4.89 109	3.12 84	5.21 96	14.9 82	4.54 97	4.33 118	5.15 106	3.93 107	4.39 85	8.57 76	3.87 85
TVL1_ROB [139]	102.2	11.3 125	19.8 120	13.0 130	12.9 124	19.6 118	13.7 126	17.4 127	27.8 126	18.0 129	12.6 124	28.9 121	11.8 124	3.71 94	4.78 103	3.46 93	4.21 75	18.0 105	3.99 82	1.79 7	3.54 38	1.21 5	7.58 119	13.9 119	8.92 118
Modified CLG [34]	102.5	7.17 113	17.1 116	6.47 113	6.85 106	14.9 100	7.48 109	14.0 116	24.8 117	15.7 124	8.35 115	27.3 120	6.36 113	3.96 108	4.99 113	4.08 108	4.54 82	19.3 112	4.15 87	2.33 44	3.86 61	2.40 54	6.00 106	13.8 118	5.40 104
2D-CLG [1]	103.1	10.1 122	22.6 127	7.59 118	9.84 119	16.9 109	11.1 123	16.9 126	28.2 127	18.8 132	14.1 126	31.1 125	13.1 126	3.86 103	4.62 94	4.53 116	5.98 105	21.2 118	5.97 109	1.76 5	3.14 6	1.46 9	6.29 108	12.9 115	5.81 106
SPSA-learn [13]	103.6	6.84 112	16.7 114	6.74 114	8.47 110	19.4 116	7.49 110	12.5 112	23.1 113	13.1 118	8.40 116	25.8 116	7.08 115	3.87 105	4.66 96	4.10 109	6.32 107	18.8 108	6.89 118	2.56 56	3.85 60	1.79 21	7.29 116	12.5 112	7.47 113
GraphCuts [14]	103.6	6.25 106	14.3 107	5.53 107	8.60 111	20.1 120	6.61 107	7.91 98	15.4 81	10.9 111	4.88 95	19.0 73	3.05 96	3.78 97	4.71 98	3.94 105	8.74 124	16.4 96	5.39 103	4.04 111	4.87 98	4.85 117	6.35 109	12.2 110	6.05 107
Filter Flow [19]	103.7	6.48 107	14.6 109	4.96 104	5.73 102	15.7 106	5.07 102	10.1 110	18.6 105	14.3 120	9.04 117	23.3 105	7.80 117	3.98 109	4.71 98	4.21 113	5.86 103	15.0 83	5.41 104	4.98 127	6.87 130	2.78 67	4.82 97	8.66 77	3.65 77
HBpMotionGpu [43]	105.4	6.57 109	15.0 111	5.17 105	8.29 109	18.0 112	8.29 114	14.1 117	26.5 120	13.2 119	6.12 107	25.3 113	3.94 104	3.79 99	4.62 94	3.97 106	4.80 90	15.7 88	4.11 85	4.40 119	5.20 109	2.87 77	6.28 107	11.7 105	7.31 110
GroupFlow [9]	106.0	8.00 115	18.6 117	8.09 120	11.1 122	23.7 126	10.3 121	12.6 113	25.6 118	12.8 116	5.84 105	20.3 86	4.39 108	4.69 123	5.81 125	3.67 99	9.29 125	22.4 124	10.1 127	2.11 32	3.99 68	2.29 51	5.75 103	10.0 88	7.39 112
IAOF [50]	106.2	6.49 108	14.6 109	6.42 111	9.22 115	18.5 114	7.94 112	16.4 125	27.4 124	13.0 117	8.22 113	22.2 99	7.73 116	3.77 96	4.76 102	3.42 91	6.84 113	18.8 108	4.23 89	3.59 101	4.46 85	2.83 71	7.51 118	10.1 91	10.6 122
Black & Anandan [4]	106.8	6.81 111	15.4 112	7.43 116	8.77 113	19.5 117	7.35 108	13.0 114	22.9 112	12.5 115	8.29 114	26.1 117	6.77 114	4.18 114	5.28 118	3.69 100	6.19 106	20.0 115	5.34 102	3.63 102	5.05 103	1.79 21	6.45 110	12.2 110	5.17 99
BlockOverlap [61]	110.1	6.67 110	13.1 93	5.87 109	6.62 105	13.9 93	6.53 106	10.6 111	19.5 109	10.1 107	6.97 111	24.9 111	5.13 110	4.38 117	4.61 93	6.37 128	7.47 118	15.7 88	6.05 110	6.23 130	6.41 128	13.0 133	6.92 113	9.60 85	12.2 125
Nguyen [33]	110.2	7.88 114	16.8 115	7.02 115	13.4 126	19.0 115	15.3 127	17.6 128	28.9 128	17.2 127	12.0 121	26.9 118	11.6 123	4.38 117	5.07 116	5.58 124	5.69 101	19.7 114	5.93 108	2.75 68	4.02 70	1.91 36	6.59 112	12.5 112	6.52 109
UnFlow [129]	111.0	14.6 134	25.8 132	9.09 124	9.40 118	16.8 108	9.89 120	14.2 118	26.9 121	11.2 112	10.0 118	25.4 115	8.67 119	5.43 129	5.90 126	6.72 129	8.64 122	24.0 126	9.41 125	3.51 97	4.90 99	1.37 7	4.37 84	12.6 114	3.33 68
2bit-BM-tele [98]	112.5	8.00 115	15.8 113	8.40 122	4.91 99	13.4 89	4.67 99	8.14 101	19.0 108	5.12 95	6.62 110	23.5 107	5.04 109	4.08 112	4.78 103	4.61 118	8.68 123	18.8 108	8.31 121	6.46 132	7.08 132	9.47 129	7.36 117	14.1 120	9.62 119
Horn & Schunck [3]	116.2	8.01 117	19.9 121	8.38 121	9.13 114	23.2 125	7.71 111	14.2 118	25.9 119	14.6 122	12.4 123	30.6 123	11.3 122	4.64 121	5.64 121	4.60 117	8.21 121	24.4 127	8.45 122	4.01 109	5.41 113	1.95 38	9.16 122	17.5 124	8.86 117
SILK [79]	117.6	9.34 121	20.4 122	10.5 127	10.4 120	21.9 122	10.3 121	16.0 124	27.5 125	14.5 121	10.3 119	29.0 122	8.54 118	4.81 124	5.65 122	5.56 123	9.41 126	25.4 129	8.74 123	2.79 71	3.68 49	4.62 115	10.9 127	17.8 126	12.3 126
Heeger++ [104]	119.2	11.9 128	21.8 125	8.08 119	12.5 123	29.7 134	9.42 119	14.8 121	27.1 122	9.68 105	14.3 127	31.0 124	12.7 125	4.98 126	5.74 123	4.97 120	17.5 134	34.1 135	18.4 134	2.75 68	5.44 114	2.15 47	12.3 129	18.8 130	14.8 129
TI-DOFE [24]	120.2	13.4 132	23.2 128	16.5 134	16.5 130	24.1 127	18.2 132	20.2 134	31.1 134	20.6 133	19.9 132	32.9 128	20.8 133	4.89 125	5.90 126	5.54 122	8.04 120	23.9 125	8.81 124	2.97 78	4.34 80	1.88 33	10.9 127	17.7 125	11.9 124
H+S_ROB [138]	121.8	13.0 130	27.1 135	9.66 125	13.4 126	24.8 129	13.4 125	18.7 132	30.9 132	18.3 131	25.8 136	35.7 132	26.4 135	7.08 134	8.13 134	9.10 133	14.6 132	31.3 134	16.3 132	2.17 34	4.44 84	2.11 45	15.1 133	19.9 132	14.2 128
HCIC-L [99]	124.1	15.7 135	22.0 126	10.1 126	31.5 136	26.6 132	41.0 136	14.8 121	23.1 113	16.8 126	18.4 131	34.4 130	18.2 132	5.94 130	6.35 130	6.35 127	10.6 129	19.2 111	11.4 129	18.7 136	17.8 136	19.2 135	4.93 99	8.34 74	5.16 98
SLK [47]	124.3	11.6 126	26.0 133	14.6 133	15.3 129	25.0 130	17.5 130	17.8 130	30.1 131	18.1 130	25.4 135	33.6 129	28.0 136	5.25 127	5.90 126	7.03 130	10.3 128	27.4 131	10.6 128	2.89 75	4.47 86	2.94 83	14.9 132	20.7 133	18.8 132
FFV1MT [106]	125.1	12.0 129	23.3 129	8.83 123	10.7 121	26.6 132	8.71 116	15.6 123	29.0 129	12.0 113	16.6 130	36.3 134	15.5 129	6.51 133	6.40 131	10.4 134	16.2 133	30.7 133	17.7 133	3.41 95	5.44 114	3.35 100	12.3 129	18.8 130	14.8 129
Adaptive flow [45]	126.9	13.2 131	20.8 123	14.0 132	17.1 132	22.0 123	17.9 131	18.1 131	27.1 122	22.8 135	11.8 120	31.1 125	10.5 120	6.35 132	7.13 133	6.25 126	9.87 127	21.8 121	9.44 126	12.6 135	11.4 135	20.0 136	7.75 120	13.6 116	7.73 114
PGAM+LK [55]	128.2	11.8 127	25.6 130	13.9 131	14.8 128	24.4 128	16.7 129	13.2 115	24.0 116	15.0 123	16.2 129	41.2 136	15.3 128	5.40 128	5.45 120	8.10 131	12.3 131	26.5 130	12.1 130	7.42 133	8.24 134	7.87 127	13.2 131	18.3 128	19.4 133
Periodicity [78]	129.2	11.2 124	27.0 134	7.46 117	16.6 131	29.8 136	18.2 132	25.3 136	31.2 136	24.9 136	12.7 125	35.7 132	11.1 121	31.7 136	41.4 136	25.1 136	23.8 136	41.5 136	23.8 136	2.92 76	5.62 118	6.90 125	18.6 135	33.1 136	22.3 134
FOLKI [16]	129.9	10.5 123	25.6 130	11.9 129	20.9 134	26.2 131	26.1 134	17.6 128	31.1 134	16.5 125	15.4 128	32.6 127	16.0 130	6.16 131	6.53 132	9.07 132	12.2 130	29.7 132	13.0 131	4.67 124	5.83 122	9.41 128	18.2 134	22.8 134	25.1 135
Pyramid LK [2]	132.8	13.9 133	20.9 124	21.4 136	24.1 135	23.1 124	30.2 135	20.9 135	29.5 130	21.9 134	22.2 134	34.6 131	25.0 134	18.7 135	23.1 135	20.2 135	21.2 135	24.5 128	21.0 135	6.41 131	7.02 131	10.8 131	25.6 136	31.5 135	34.5 136
AdaConv-v1 [126]	137.0	39.2 137	39.9 137	41.8 137	73.0 137	74.5 137	71.1 137	70.1 137	67.3 137	71.8 137	64.4 137	66.2 137	65.9 137	76.5 137	78.1 137	72.0 137	68.2 137	64.9 137	66.5 137	52.3 137	45.1 137	70.9 137	81.8 137	81.6 137	82.3 137
SepConv-v1 [127]	137.0	39.2 137	39.9 137	41.8 137	73.0 137	74.5 137	71.1 137	70.1 137	67.3 137	71.8 137	64.4 137	66.2 137	65.9 137	76.5 137	78.1 137	72.0 137	68.2 137	64.9 137	66.5 137	52.3 137	45.1 137	70.9 137	81.8 137	81.6 137	82.3 137
SuperSlomo [132]	137.0	39.2 137	39.9 137	41.8 137	73.0 137	74.5 137	71.1 137	70.1 137	67.3 137	71.8 137	64.4 137	66.2 137	65.9 137	76.5 137	78.1 137	72.0 137	68.2 137	64.9 137	66.5 137	52.3 137	45.1 137	70.9 137	81.8 137	81.6 137	82.3 137
FGIK [136]	137.0	39.2 137	39.9 137	41.8 137	73.0 137	74.5 137	71.1 137	70.1 137	67.3 137	71.8 137	64.4 137	66.2 137	65.9 137	76.5 137	78.1 137	72.0 137	68.2 137	64.9 137	66.5 137	52.3 137	45.1 137	70.9 137	81.8 137	81.6 137	82.3 137
CtxSyn [137]	137.0	39.2 137	39.9 137	41.8 137	73.0 137	74.5 137	71.1 137	70.1 137	67.3 137	71.8 137	64.4 137	66.2 137	65.9 137	76.5 137	78.1 137	72.0 137	68.2 137	64.9 137	66.5 137	52.3 137	45.1 137	70.9 137	81.8 137	81.6 137	82.3 137

Move the mouse over the numbers in the table to see the corresponding images. Click to compare with the ground truth.

References

Method	time*	frames	color	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] FGIK	0.18	2	color	Anonymous. (Interpolation results only.) Learning flow-guided interpolation kernels for video frame synthesis. ECCV 2018 submission 433.
[137] CtxSyn	0.07	2	color	S. Niklaus and F. Liu. (Interpolation results only.) Context-aware synthesis for video frame interpolation. CVPR 2018.
[138] 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.
[139] 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.
[140] 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.
[141] 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.

* 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.