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]	5.5	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 24	3.36 17	1.62 20	0.99 1	2.16 3	0.57 2
NN-field [71]	10.7	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 54	3.70 53	1.95 43	1.01 2	2.25 4	0.53 1
OFLAF [77]	13.8	3.04 15	7.80 10	2.40 14	2.14 7	7.02 5	1.72 9	2.25 3	5.32 2	1.56 5	2.62 20	13.7 27	1.37 22	2.35 4	3.13 6	1.62 4	2.98 23	7.73 7	2.57 22	2.08 30	3.27 12	2.05 48	1.33 13	2.43 7	1.40 17
PMMST [114]	14.9	3.42 43	7.60 5	2.65 31	2.32 11	6.39 1	2.20 34	2.63 11	6.08 8	2.03 28	2.06 6	6.07 2	1.44 30	2.60 10	3.27 8	1.91 10	2.56 7	6.78 2	2.09 5	2.06 26	3.53 37	1.63 21	1.27 10	2.29 5	1.02 7
nLayers [57]	17.3	2.80 6	7.42 3	2.20 8	2.71 31	7.24 10	2.55 61	2.61 9	6.24 9	2.45 53	2.30 12	12.7 14	1.16 7	2.30 3	3.02 3	1.70 5	2.62 11	6.95 4	2.09 5	2.29 47	3.46 26	1.89 40	1.38 15	3.06 18	1.29 15
MDP-Flow2 [68]	20.0	3.23 31	7.93 13	2.60 23	1.92 2	6.64 2	1.52 1	2.46 7	5.91 7	1.56 5	3.05 46	15.8 60	1.51 40	2.77 24	3.50 18	2.16 28	2.86 19	8.58 18	2.70 33	2.00 24	3.50 34	1.59 18	1.28 11	2.67 12	0.89 4
ComponentFusion [96]	20.2	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 17	1.01 3	2.71 21	3.56 20	2.10 23	3.55 53	12.4 60	3.22 60	2.19 41	3.60 46	1.54 17	1.32 12	2.91 14	1.13 9
TC/T-Flow [76]	22.7	2.69 3	7.75 9	1.87 2	2.76 34	10.2 48	1.73 10	3.33 25	9.01 31	1.49 2	2.86 36	16.7 70	1.21 9	2.60 10	3.49 17	1.90 9	2.21 2	7.65 5	2.04 4	1.84 12	3.23 9	3.14 98	2.03 39	4.53 39	1.49 21
FC-2Layers-FF [74]	26.5	3.02 14	7.87 12	2.61 24	2.72 32	9.35 36	2.29 42	2.36 5	5.47 4	2.15 35	2.48 13	12.6 13	1.28 13	2.49 7	3.19 7	2.03 17	3.39 42	8.92 20	2.83 44	2.83 79	3.92 68	2.80 77	1.25 8	2.57 11	1.20 12
WLIF-Flow [93]	27.5	2.96 10	7.67 6	2.40 14	2.41 16	7.70 15	2.10 28	2.98 17	7.63 19	1.97 27	2.71 28	13.5 23	1.33 16	3.01 44	4.00 50	2.40 46	3.03 26	8.32 12	2.44 17	2.09 32	3.36 17	2.04 47	2.26 47	4.97 48	2.59 55
Layers++ [37]	28.0	3.11 18	8.22 20	2.79 43	2.43 19	7.02 5	2.24 37	2.43 6	5.77 6	2.18 38	2.13 8	9.71 9	1.15 6	2.35 4	3.02 3	1.96 11	3.81 61	11.4 46	3.22 60	2.74 74	4.01 73	2.35 61	1.45 16	3.05 17	1.79 31
HAST [109]	28.8	2.58 1	7.12 1	1.81 1	2.41 16	7.05 7	2.10 28	1.83 1	4.19 1	1.17 1	2.84 35	15.5 54	1.08 5	2.23 1	2.97 2	1.40 1	3.72 58	10.0 33	3.92 85	3.40 102	4.90 107	5.66 130	1.20 7	2.09 1	1.24 13
AGIF+OF [85]	29.8	3.06 16	8.20 17	2.55 21	3.17 60	10.6 54	2.46 55	3.46 30	8.97 30	2.24 41	2.61 18	13.7 27	1.33 16	2.63 15	3.46 15	2.11 24	2.88 21	8.34 14	2.35 13	2.10 34	3.56 41	2.09 50	1.80 30	3.68 30	2.24 42
FESL [72]	30.0	2.96 10	7.70 7	2.54 19	3.26 71	10.4 51	2.56 62	3.25 23	8.39 23	2.17 36	2.56 15	13.2 18	1.31 15	2.57 9	3.40 11	2.12 26	2.60 9	7.65 5	2.30 11	2.64 70	4.22 82	2.47 65	1.75 28	3.49 27	1.71 26
Efficient-NL [60]	30.0	2.99 13	8.23 21	2.28 9	2.72 32	8.95 32	2.25 40	3.81 40	9.87 37	2.07 32	2.77 32	14.3 36	1.46 35	2.61 12	3.48 16	1.96 11	3.31 38	8.33 13	2.59 24	2.60 65	3.75 54	2.54 68	1.60 22	3.02 15	1.66 23
LME [70]	30.0	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 97	2.69 26	13.6 25	1.42 27	2.85 31	3.61 23	2.42 48	3.47 49	12.8 67	3.17 56	2.12 36	3.53 37	1.73 23	1.34 14	2.75 13	1.18 11
ALD-Flow [66]	30.4	2.82 7	7.86 11	2.16 6	2.84 41	10.1 45	1.86 18	3.73 38	10.4 41	1.67 12	3.10 48	16.8 71	1.28 13	2.69 20	3.60 22	1.85 8	2.79 15	11.3 45	2.32 12	2.07 28	3.25 11	3.10 95	2.03 39	5.11 49	1.94 34
RNLOD-Flow [121]	31.3	2.66 2	7.33 2	2.17 7	2.53 27	9.46 38	1.86 18	3.94 44	10.7 47	1.95 24	2.50 14	13.5 23	1.21 9	2.68 18	3.62 25	2.05 19	2.99 24	8.59 19	2.75 37	3.00 89	4.54 94	3.25 103	1.48 18	3.24 21	1.76 30
IROF++ [58]	31.5	3.17 25	8.69 30	2.61 24	2.79 36	9.61 39	2.33 43	3.43 27	8.86 27	2.38 47	2.87 38	14.8 41	1.52 42	2.74 22	3.57 21	2.19 30	3.20 34	9.70 30	2.71 34	1.96 22	3.45 25	1.22 7	1.80 30	4.06 32	2.50 51
NNF-EAC [103]	32.0	3.31 35	8.21 19	2.68 33	2.19 9	7.49 13	1.76 13	2.73 13	6.62 12	1.70 14	3.18 53	15.8 60	1.64 52	2.87 34	3.66 28	2.24 32	3.02 25	8.07 10	2.59 24	2.19 41	3.48 30	1.74 24	2.85 63	6.52 65	3.12 67
ProFlow_ROB [147]	32.0	3.29 32	9.91 55	2.35 13	2.50 25	10.0 44	1.83 16	4.04 47	11.6 55	1.96 26	2.86 36	15.0 44	1.22 11	2.87 34	3.89 41	1.97 14	2.60 9	10.5 36	2.20 10	1.53 4	3.54 39	1.53 16	2.50 52	6.37 64	2.33 46
PH-Flow [101]	32.4	3.19 28	8.87 35	2.71 34	2.84 41	9.33 35	2.37 45	2.85 14	7.20 15	2.36 44	2.92 41	15.4 51	1.51 40	2.63 15	3.42 12	2.04 18	3.03 26	8.52 17	2.49 19	2.69 72	3.60 46	3.13 97	1.25 8	2.53 9	1.34 16
Classic+CPF [83]	32.9	3.14 21	8.60 27	2.63 28	3.03 57	10.6 54	2.33 43	3.66 34	9.58 33	2.20 39	2.61 18	14.1 32	1.34 19	2.68 18	3.53 19	2.21 31	2.85 18	7.95 9	2.38 14	2.44 56	3.49 32	2.90 88	1.67 26	3.40 24	2.43 50
Sparse-NonSparse [56]	34.6	3.14 21	8.75 32	2.76 41	3.02 55	10.6 54	2.43 50	3.45 29	8.96 28	2.36 44	2.66 23	13.7 27	1.42 27	2.85 31	3.75 35	2.33 37	3.28 37	9.40 26	2.73 35	2.42 53	3.31 14	2.69 72	1.47 17	3.07 19	1.66 23
TC-Flow [46]	35.9	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 49	16.6 69	1.46 35	2.78 25	3.73 34	1.96 11	3.08 29	11.4 46	2.66 28	1.94 20	3.43 22	3.20 102	3.06 68	7.04 69	4.08 92
3DFlow [135]	36.3	3.44 44	8.63 29	2.46 16	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 12	2.86 33	3.72 32	2.16 28	4.52 85	11.6 52	4.20 92	3.16 97	4.02 74	4.44 122	1.13 5	2.14 2	0.89 4
LSM [39]	37.0	3.12 19	8.62 28	2.75 40	3.00 53	10.5 53	2.44 52	3.43 27	8.85 26	2.35 43	2.66 23	13.6 25	1.44 30	2.82 27	3.68 29	2.36 39	3.38 41	9.41 27	2.81 42	2.69 72	3.52 35	2.84 81	1.59 21	3.38 23	1.80 32
Ramp [62]	37.9	3.18 27	8.83 34	2.73 37	2.89 46	10.1 45	2.44 52	3.27 24	8.43 24	2.38 47	2.74 30	14.2 33	1.46 35	2.82 27	3.69 31	2.29 35	3.37 40	9.31 24	2.93 48	2.62 68	3.38 20	3.19 101	1.54 20	3.21 20	2.24 42
Correlation Flow [75]	38.0	3.38 41	8.40 23	2.64 29	2.23 10	7.54 14	1.56 3	5.14 69	13.1 68	1.60 7	2.09 7	8.15 5	1.35 21	3.12 52	4.09 57	2.34 38	4.01 72	11.5 50	4.00 87	2.59 64	3.61 48	3.00 93	1.49 19	3.04 16	1.42 19
SVFilterOh [111]	38.0	3.63 50	8.82 33	2.86 45	2.60 29	8.06 18	2.05 27	2.95 15	7.09 14	2.03 28	2.80 34	13.8 30	1.41 26	2.63 15	3.42 12	1.75 7	3.49 50	10.3 35	3.23 63	3.63 111	5.75 129	4.47 123	1.09 4	2.45 8	0.92 6
ProbFlowFields [128]	38.5	4.18 69	12.4 84	3.40 75	2.43 19	8.16 20	2.19 33	3.65 33	9.72 35	2.86 68	2.22 9	9.42 8	1.42 27	3.01 44	3.96 47	2.36 39	2.73 14	10.9 38	2.51 20	1.89 18	3.39 21	1.82 29	2.59 55	6.21 62	2.75 58
COFM [59]	38.9	3.17 25	9.90 54	2.46 16	2.41 16	8.34 23	1.92 21	3.77 39	10.5 42	2.54 56	2.71 28	14.9 43	1.19 8	3.08 49	3.92 45	3.25 90	3.83 64	10.9 38	3.15 55	2.20 44	3.35 15	2.91 90	1.62 25	2.56 10	2.09 38
PMF [73]	39.0	3.61 48	9.07 38	2.62 26	2.40 14	8.05 17	1.83 16	2.61 9	6.27 10	1.65 11	3.35 63	15.4 51	1.58 47	2.54 8	3.27 8	1.71 6	3.59 54	11.1 43	3.46 69	4.07 121	6.18 135	4.02 118	1.06 3	2.38 6	1.25 14
FMOF [94]	40.2	3.12 19	8.23 21	2.73 37	3.25 68	10.7 61	2.52 59	3.01 18	7.61 18	2.20 39	2.56 15	13.4 21	1.33 16	2.75 23	3.61 23	2.24 32	3.66 56	8.50 16	2.78 40	2.62 68	3.84 62	3.27 105	2.66 59	5.69 53	1.95 36
JOF [141]	40.4	3.08 17	8.56 26	2.51 18	3.27 72	10.2 48	2.81 81	3.02 19	7.55 17	2.42 51	2.64 21	14.2 33	1.34 19	2.62 13	3.42 12	2.08 20	3.26 35	8.96 21	2.56 21	3.12 96	4.26 83	4.09 120	2.11 45	4.58 41	2.18 40
OAR-Flow [125]	41.2	3.37 39	9.87 53	2.67 32	4.22 92	12.8 87	2.87 83	4.95 65	13.4 71	2.66 60	3.23 55	16.4 68	1.37 22	2.83 29	3.82 38	1.97 14	2.49 6	10.9 38	1.87 3	1.52 3	2.82 1	1.86 34	1.85 33	4.35 37	1.68 25
Classic+NL [31]	41.5	3.20 30	8.72 31	2.81 44	3.02 55	10.6 54	2.44 52	3.46 30	8.84 25	2.38 47	2.78 33	14.3 36	1.46 35	2.83 29	3.68 29	2.31 36	3.40 43	9.09 23	2.76 39	2.87 81	3.82 61	2.86 85	1.67 26	3.53 28	2.26 45
TV-L1-MCT [64]	42.5	3.16 24	8.48 25	2.71 34	3.28 73	10.8 65	2.60 69	3.95 45	10.5 42	2.38 47	2.69 26	13.9 31	1.45 34	2.94 40	3.79 36	2.63 68	3.50 51	9.75 31	3.06 52	2.08 30	3.35 15	2.29 59	1.95 36	3.89 31	2.71 57
PWC-Net_ROB [148]	45.2	4.86 101	12.4 84	3.56 84	3.14 59	10.3 50	2.60 69	4.38 55	11.6 55	3.18 75	2.56 15	10.6 11	1.52 42	3.25 68	4.18 61	2.46 50	3.10 31	10.6 37	2.75 37	1.44 2	3.56 41	1.01 2	1.60 22	3.41 25	1.14 10
IIOF-NLDP [131]	46.0	3.65 51	9.81 52	2.56 22	2.79 36	9.36 37	2.00 23	4.28 53	11.3 53	1.69 13	2.02 5	7.52 4	1.38 25	3.36 75	4.52 90	2.40 46	3.82 62	11.2 44	3.67 78	2.07 28	3.79 58	1.88 38	2.91 65	5.30 52	4.17 93
SimpleFlow [49]	46.8	3.35 36	9.20 41	2.98 52	3.18 63	10.7 61	2.71 75	5.06 67	12.6 66	2.70 62	2.95 43	15.1 46	1.58 47	2.91 38	3.79 36	2.47 51	3.59 54	9.49 28	2.99 50	2.39 51	3.46 26	2.24 58	1.60 22	3.56 29	1.57 22
CostFilter [40]	47.2	3.84 54	9.64 48	3.06 54	2.55 28	8.09 19	2.03 25	2.69 12	6.47 11	1.88 20	3.66 74	16.8 71	1.88 64	2.62 13	3.34 10	1.99 16	4.05 73	11.0 42	3.65 77	4.16 123	7.18 142	4.66 125	1.16 6	3.36 22	0.87 3
2DHMM-SAS [92]	49.3	3.19 28	8.89 36	2.71 34	3.20 66	11.5 75	2.38 46	5.19 70	12.2 62	2.73 64	2.92 41	15.2 47	1.53 44	2.79 26	3.65 27	2.27 34	3.45 47	9.34 25	2.78 40	2.66 71	3.56 41	3.07 94	2.34 50	5.12 50	2.97 65
S2D-Matching [84]	50.2	3.36 37	9.66 49	2.86 45	3.19 65	11.1 69	2.46 55	4.86 64	12.9 67	2.47 54	2.67 25	13.2 18	1.44 30	2.87 34	3.72 32	2.38 42	3.45 47	9.76 32	2.95 49	3.05 90	3.79 58	3.30 107	1.95 36	4.16 35	3.00 66
FlowFields+ [130]	50.3	4.57 87	13.7 98	3.35 67	2.94 51	10.1 45	2.58 66	4.05 48	10.6 44	3.26 78	2.90 40	13.2 18	1.81 62	3.18 56	4.20 65	2.54 57	2.68 13	11.4 46	2.40 16	1.84 12	3.62 49	1.77 25	2.48 51	5.86 55	2.77 59
MLDP_OF [89]	50.4	4.13 65	10.3 62	3.60 85	2.34 12	7.70 15	1.88 20	4.23 52	10.9 50	1.87 19	2.74 30	14.6 40	1.37 22	3.10 50	3.91 44	2.48 55	3.40 43	9.00 22	3.79 82	3.46 104	4.20 80	5.55 129	2.31 48	4.64 43	1.98 37
MDP-Flow [26]	50.9	3.48 46	9.46 45	3.10 56	2.45 22	7.36 12	2.41 47	3.21 22	8.31 22	2.78 66	3.18 53	17.8 78	1.70 57	3.03 46	3.87 39	2.60 64	3.43 45	12.6 64	2.81 42	2.19 41	3.88 65	1.60 19	4.13 88	9.96 95	3.86 87
AggregFlow [97]	51.2	4.25 75	11.9 81	3.26 59	4.46 98	13.7 99	3.43 94	4.76 62	12.4 63	3.93 94	3.28 58	15.6 56	1.68 54	2.89 37	3.89 41	2.08 20	2.32 3	7.75 8	2.14 7	2.06 26	3.77 56	1.48 14	2.07 43	4.11 33	2.36 48
IROF-TV [53]	51.5	3.40 42	9.29 43	2.95 51	2.99 52	11.1 69	2.53 60	3.81 40	9.81 36	2.44 52	3.25 57	16.9 73	1.78 61	3.27 72	4.10 58	2.93 82	4.47 82	16.0 97	3.53 71	1.70 6	3.21 7	1.12 4	1.91 35	4.75 45	2.19 41
CombBMOF [113]	52.6	3.94 58	10.6 66	2.74 39	2.80 38	8.55 25	2.16 31	3.10 21	7.99 21	1.76 15	2.99 44	13.4 21	1.95 68	3.04 47	3.89 41	2.49 56	5.64 108	12.3 58	6.74 123	3.54 107	5.16 115	2.81 78	1.85 33	4.60 42	1.10 8
S2F-IF [123]	53.0	4.51 85	13.6 97	3.31 63	2.90 47	10.4 51	2.48 58	4.07 50	10.8 49	3.15 73	3.31 59	15.7 59	1.90 65	3.17 54	4.19 63	2.55 60	2.81 17	11.6 52	2.60 26	1.86 15	3.67 51	1.87 35	2.11 45	4.64 43	2.54 54
FlowFields [110]	55.4	4.57 87	13.7 98	3.38 70	3.01 54	10.6 54	2.59 67	4.19 51	11.1 51	3.30 79	3.17 52	15.0 44	1.96 69	3.21 63	4.24 72	2.61 67	2.91 22	12.4 60	2.66 28	1.84 12	3.46 26	1.84 32	2.50 52	6.15 60	2.79 60
NL-TV-NCC [25]	56.9	3.89 56	9.16 40	2.98 52	2.87 45	9.69 40	1.99 22	4.44 58	11.6 55	1.76 15	2.64 21	11.8 12	1.48 39	3.49 87	4.60 96	2.47 51	4.67 92	13.5 72	4.26 96	2.83 79	4.57 96	2.84 81	2.62 57	6.00 59	2.25 44
Sparse Occlusion [54]	56.9	3.62 49	9.12 39	2.90 47	2.92 49	9.08 33	2.56 62	4.49 59	11.8 60	2.11 34	3.14 50	15.8 60	1.57 46	3.26 69	4.22 68	2.36 39	3.52 52	10.9 38	2.66 28	5.10 138	6.32 136	3.15 99	2.02 38	4.92 46	1.71 26
EPPM w/o HM [88]	57.4	4.25 75	11.1 70	3.13 57	2.36 13	8.35 24	1.76 13	3.72 37	10.2 40	1.81 17	3.24 56	14.5 39	1.94 67	3.16 53	3.94 46	2.82 77	4.78 95	12.9 68	4.32 97	3.64 113	4.54 94	5.73 131	1.76 29	4.11 33	1.94 34
OFH [38]	57.6	3.90 57	9.77 51	3.62 88	2.84 41	11.0 68	2.04 26	5.52 77	14.4 79	1.89 21	3.52 66	20.5 97	1.60 50	3.18 56	4.06 55	2.82 77	3.86 65	14.1 81	3.59 73	1.77 8	3.62 49	1.81 28	2.64 58	7.08 72	2.15 39
PGM-C [120]	58.0	4.62 92	14.0 103	3.39 72	3.29 75	12.3 80	2.70 74	4.39 57	11.7 58	3.43 82	4.00 82	19.8 86	2.15 74	3.19 58	4.23 69	2.54 57	2.79 15	11.9 55	2.45 18	1.83 10	3.21 7	1.83 30	2.31 48	5.87 56	1.82 33
Occlusion-TV-L1 [63]	59.7	3.59 47	9.61 46	2.64 29	2.93 50	10.6 54	2.41 47	6.16 85	15.2 83	2.70 62	3.32 61	17.0 74	1.68 54	3.38 77	4.44 83	2.82 77	3.10 31	13.2 71	2.68 31	2.17 37	3.52 35	1.46 12	4.63 101	11.1 110	3.53 76
Complementary OF [21]	60.4	4.44 81	11.2 73	4.04 97	2.51 26	9.77 42	1.74 11	3.93 43	10.6 44	2.04 30	3.87 78	18.8 80	2.19 78	3.17 54	4.00 50	2.92 81	4.64 90	13.8 78	3.64 76	2.17 37	3.36 17	2.51 66	3.08 69	7.04 69	3.65 80
Adaptive [20]	61.9	3.29 32	9.43 44	2.28 9	3.10 58	11.4 72	2.46 55	6.58 89	15.7 89	2.52 55	3.14 50	15.6 56	1.56 45	3.67 97	4.46 85	3.48 100	3.32 39	13.0 70	2.38 14	2.76 77	4.39 88	1.93 42	3.58 76	8.18 81	2.88 62
Aniso-Texture [82]	62.6	2.96 10	7.72 8	2.54 19	2.48 24	8.26 22	2.24 37	6.48 87	15.9 94	2.63 58	1.96 4	10.1 10	0.98 2	3.26 69	4.21 66	2.60 64	5.74 110	16.9 106	5.61 113	4.47 130	5.88 132	3.33 108	3.51 75	7.12 73	3.68 82
ACK-Prior [27]	63.0	4.19 71	9.27 42	3.60 85	2.40 14	8.21 21	1.65 7	3.40 26	8.96 28	1.84 18	2.87 38	14.4 38	1.44 30	3.36 75	4.15 59	3.07 85	6.35 119	16.1 99	4.90 107	4.21 125	4.80 102	6.03 133	3.29 72	5.99 58	2.82 61
CPM-Flow [116]	64.1	4.63 93	14.1 106	3.39 72	3.33 76	12.5 84	2.73 76	4.37 54	11.7 58	3.43 82	4.00 82	19.9 89	2.14 73	3.19 58	4.23 69	2.54 57	3.08 29	12.0 56	2.88 46	1.87 16	3.44 23	1.84 32	2.91 65	7.48 78	2.91 64
DPOF [18]	64.4	4.67 96	12.6 90	3.30 61	3.57 82	10.6 54	3.12 90	3.09 20	7.50 16	2.32 42	3.06 47	14.8 41	1.82 63	3.21 63	4.18 61	2.79 76	4.47 82	12.5 62	3.33 64	4.09 122	3.92 68	6.96 135	2.09 44	4.39 38	1.74 28
EpicFlow [102]	64.5	4.61 91	14.0 103	3.39 72	3.33 76	12.5 84	2.74 77	5.37 73	14.8 82	3.46 85	3.94 81	19.2 83	2.13 72	3.20 60	4.23 69	2.58 63	2.87 20	12.2 57	2.64 27	1.83 10	3.28 13	1.83 30	3.21 71	7.12 73	3.61 77
DeepFlow2 [108]	65.8	4.04 62	11.2 73	3.38 70	3.80 85	12.4 83	2.86 82	5.12 68	13.4 71	3.00 69	4.17 88	20.1 91	2.18 77	2.96 41	3.97 48	2.08 20	3.06 28	12.6 64	2.69 32	2.17 37	3.24 10	2.71 73	4.74 103	10.4 103	4.38 100
ROF-ND [107]	66.4	4.12 63	10.0 56	3.37 69	2.78 35	8.82 29	2.12 30	4.61 61	11.9 61	2.09 33	2.23 10	6.56 3	1.69 56	3.60 93	4.75 106	2.85 80	4.92 98	13.6 75	3.75 80	4.59 132	5.18 116	4.10 121	2.67 60	5.19 51	3.46 75
TCOF [69]	66.8	4.17 68	10.4 64	3.71 91	3.17 60	10.7 61	2.59 67	6.58 89	15.7 89	3.82 92	3.69 76	16.1 65	2.37 87	3.78 101	4.95 118	2.47 51	2.59 8	8.47 15	2.58 23	3.66 115	4.83 103	2.67 71	1.83 32	4.20 36	1.46 20
RFlow [90]	68.0	3.82 53	10.0 56	3.44 78	2.61 30	9.73 41	2.02 24	5.66 79	14.5 80	2.05 31	3.93 80	23.1 111	1.90 65	3.24 65	4.19 63	2.66 71	4.12 76	15.2 93	3.34 66	2.61 66	3.56 41	2.65 70	4.48 96	10.5 106	3.93 91
HBM-GC [105]	68.0	5.25 104	10.5 65	4.34 104	3.17 60	8.78 28	2.94 86	4.38 55	10.6 44	2.68 61	3.59 70	12.8 15	2.47 90	2.96 41	3.64 26	2.64 69	3.96 71	8.26 11	3.56 72	4.40 128	5.92 133	3.62 112	2.55 54	6.34 63	3.29 70
Steered-L1 [118]	69.3	3.30 34	8.44 24	2.91 48	1.89 1	7.14 8	1.60 6	3.61 32	9.91 38	1.89 21	3.45 64	19.4 85	1.64 52	3.42 80	4.30 75	3.39 93	5.18 102	14.5 84	4.37 100	5.09 137	5.05 111	10.1 139	5.56 111	10.2 101	6.24 117
DMF_ROB [140]	70.2	4.37 78	12.3 83	3.62 88	3.46 80	12.9 89	2.60 69	5.98 82	15.8 91	3.23 77	4.05 84	19.8 86	2.15 74	3.10 50	4.06 55	2.57 62	3.79 60	14.3 82	3.13 54	1.88 17	3.12 5	1.99 46	4.34 90	10.0 96	3.87 88
SRR-TVOF-NL [91]	70.5	4.47 83	10.9 68	3.32 65	4.04 89	13.2 93	2.90 84	4.81 63	12.5 64	3.15 73	3.33 62	15.3 49	1.61 51	3.24 65	4.03 54	2.70 73	3.94 69	11.8 54	3.33 64	4.16 123	5.21 119	3.44 111	2.06 42	3.48 26	2.42 49
ComplOF-FED-GPU [35]	70.7	4.28 77	11.3 75	3.70 90	3.25 68	13.0 90	2.16 31	4.06 49	11.2 52	1.95 24	3.91 79	19.2 83	2.01 70	3.20 60	4.15 59	2.64 69	4.61 88	16.1 99	3.90 84	2.98 87	3.77 56	3.69 113	2.85 63	7.44 77	2.53 53
FF++_ROB [146]	72.0	4.84 100	14.8 113	3.46 79	3.18 63	11.4 72	2.69 73	5.30 72	14.1 76	3.73 91	3.31 59	14.2 33	2.20 79	3.26 69	4.29 74	2.72 74	4.58 87	12.7 66	3.70 79	1.91 19	3.46 26	2.19 57	3.65 78	7.31 75	5.97 114
TF+OM [100]	73.7	3.97 59	10.2 59	2.94 50	2.91 48	9.12 34	2.57 65	5.22 71	11.5 54	6.92 105	3.59 70	16.1 65	2.28 84	3.20 60	3.97 48	3.11 86	4.70 93	14.5 84	4.32 97	3.06 92	4.84 104	2.71 73	3.93 83	8.79 86	4.32 98
Aniso. Huber-L1 [22]	74.2	3.71 52	10.1 58	3.08 55	4.36 97	13.0 90	3.77 98	6.92 93	15.3 85	3.60 88	3.54 67	15.9 63	2.04 71	3.38 77	4.45 84	2.47 51	3.88 66	12.9 68	2.74 36	3.37 101	4.36 86	2.85 84	3.16 70	7.52 79	2.90 63
DeepFlow [86]	75.5	4.49 84	11.7 78	4.14 99	4.26 93	12.8 87	3.36 92	5.96 81	14.2 78	5.10 98	4.89 102	23.1 111	2.67 93	2.98 43	4.00 50	2.11 24	3.26 35	13.5 72	2.84 45	2.09 32	3.10 3	2.77 75	5.83 113	11.4 112	5.45 112
Classic++ [32]	76.2	3.37 39	9.67 50	2.91 48	3.28 73	12.1 78	2.61 72	5.46 76	14.1 76	3.00 69	3.63 72	20.2 94	1.70 57	3.24 65	4.34 77	2.60 64	4.65 91	16.0 97	3.60 74	3.09 93	3.94 71	3.28 106	4.64 102	10.4 103	3.71 83
TV-L1-improved [17]	77.0	3.36 37	9.63 47	2.62 26	2.82 39	10.7 61	2.23 35	6.50 88	15.8 91	2.73 64	3.80 77	21.3 102	1.76 60	3.34 74	4.38 81	2.39 43	5.97 112	18.1 115	5.67 114	3.57 109	4.92 109	3.43 110	4.01 86	9.84 94	3.44 74
LocallyOriented [52]	79.3	4.54 86	12.8 92	3.27 60	4.73 103	14.8 106	3.73 97	7.77 100	18.3 108	3.44 84	3.56 68	15.6 56	2.22 80	3.46 84	4.47 86	2.69 72	3.15 33	10.2 34	3.19 58	2.61 66	4.20 80	2.52 67	4.39 93	8.52 83	5.23 108
SIOF [67]	79.5	4.23 73	10.2 59	3.31 63	3.97 87	14.5 104	2.97 87	7.81 102	16.4 97	7.48 107	4.82 98	20.1 91	2.96 96	3.54 90	4.49 87	3.12 87	4.31 78	13.5 72	4.13 90	2.36 50	3.59 45	1.68 22	3.46 74	7.39 76	3.37 72
LiteFlowNet [143]	81.0	6.29 111	16.5 118	4.45 106	3.68 83	10.8 65	3.13 91	5.43 74	13.7 74	3.60 88	3.57 69	12.8 15	2.25 83	3.85 108	4.78 108	3.61 103	4.37 80	12.5 62	3.63 75	2.55 61	4.51 93	1.52 15	4.05 87	7.05 71	5.16 104
Brox et al. [5]	82.2	4.44 81	12.4 84	4.22 102	3.72 84	13.5 98	3.06 88	4.97 66	13.3 70	3.11 71	4.58 94	22.0 105	2.37 87	3.79 103	4.60 96	4.33 123	3.91 68	17.0 107	3.45 68	2.22 45	3.79 58	1.19 5	4.62 100	10.0 96	3.38 73
TriangleFlow [30]	82.5	4.12 63	10.6 66	3.47 80	3.47 81	13.1 92	2.41 47	6.00 83	15.2 83	2.17 36	2.99 44	16.0 64	1.58 47	4.46 127	5.79 133	4.15 119	5.42 106	13.9 80	5.24 108	3.10 95	5.47 125	2.90 88	3.02 67	6.82 67	3.64 79
CRTflow [80]	82.8	4.18 69	11.8 80	3.20 58	3.22 67	10.8 65	2.43 50	6.20 86	15.5 87	2.63 58	4.21 89	22.0 105	2.24 81	3.32 73	4.34 77	2.44 49	7.43 126	19.3 121	8.15 129	2.55 61	4.09 76	2.59 69	4.60 99	11.2 111	4.45 101
OFRF [134]	84.0	4.77 99	11.6 76	4.03 96	8.72 121	15.3 110	8.51 124	8.49 112	16.7 99	7.32 106	4.55 93	15.3 49	3.16 103	2.92 39	3.87 39	2.13 27	3.76 59	9.69 29	3.22 60	2.98 87	4.50 92	4.04 119	4.59 98	5.76 54	8.61 125
BriefMatch [124]	84.9	3.44 44	9.01 37	2.77 42	2.85 44	9.93 43	2.23 35	2.97 16	7.65 20	1.94 23	3.64 73	20.1 91	1.75 59	4.10 119	4.90 116	5.82 134	7.95 128	17.8 111	8.08 128	4.73 134	5.20 117	12.2 141	7.88 130	12.0 116	13.7 136
Rannacher [23]	84.9	4.13 65	11.0 69	3.61 87	3.39 78	12.3 80	2.80 80	7.26 95	17.4 104	3.59 87	4.40 91	23.1 111	2.24 81	3.43 82	4.54 93	2.56 61	5.41 105	18.5 116	4.23 94	2.92 84	3.91 67	2.82 79	3.45 73	9.14 87	3.27 69
F-TV-L1 [15]	85.9	5.44 107	12.5 89	5.69 114	5.46 107	15.0 109	4.03 101	7.48 97	16.3 96	3.42 81	5.08 104	23.3 114	2.81 95	3.42 80	4.34 77	3.03 83	4.05 73	15.1 91	3.18 57	2.43 54	3.92 68	1.87 35	3.90 82	9.35 91	2.61 56
SuperFlow [81]	87.0	4.16 67	11.1 70	3.32 65	4.80 104	12.2 79	4.68 106	7.80 101	16.0 95	10.6 118	5.16 107	22.4 109	3.24 104	3.39 79	4.24 72	3.71 106	3.44 46	13.7 77	2.91 47	3.19 98	4.62 98	1.87 35	4.74 103	10.6 107	4.24 95
Local-TV-L1 [65]	87.2	5.33 105	12.6 90	5.19 111	6.90 114	15.7 113	6.22 113	10.0 117	18.2 107	8.89 109	5.81 113	24.7 119	3.70 110	3.05 48	4.00 50	2.39 43	4.05 73	14.6 86	3.09 53	1.95 21	3.11 4	2.15 53	5.85 114	10.8 108	7.34 120
TriFlow [95]	87.2	4.73 98	12.4 84	3.49 82	4.03 88	12.5 84	3.70 96	8.18 109	17.2 102	10.4 117	3.50 65	15.4 51	2.32 86	3.43 82	4.21 66	3.42 94	3.90 67	12.3 58	3.76 81	7.86 143	5.72 128	16.2 143	2.80 62	5.89 57	2.50 51
DF-Auto [115]	87.4	5.04 103	13.7 98	3.30 61	6.51 111	14.1 103	6.09 111	8.14 106	16.5 98	10.2 116	5.06 103	21.3 102	3.10 102	3.74 99	4.91 117	3.25 90	2.67 12	11.4 46	2.14 7	3.36 100	5.23 121	1.45 11	4.45 95	9.18 88	4.28 97
CLG-TV [48]	88.1	4.00 60	10.3 62	3.40 75	4.33 96	12.3 80	4.08 102	6.78 91	15.5 87	3.64 90	4.07 85	17.7 77	2.39 89	3.79 103	4.86 111	3.23 89	4.48 84	16.5 104	3.80 83	3.55 108	4.65 99	2.89 87	4.00 85	10.1 99	3.18 68
CBF [12]	89.0	3.88 55	10.2 59	3.50 83	4.60 100	11.3 71	5.06 107	5.43 74	13.1 68	3.39 80	4.09 86	21.2 101	2.16 76	3.80 106	4.72 105	3.52 101	4.33 79	14.4 83	3.01 51	4.97 135	5.51 126	4.93 127	3.99 84	9.27 90	3.91 90
Bartels [41]	91.3	4.43 79	11.1 70	4.17 101	2.83 40	8.84 30	2.56 62	4.54 60	12.5 64	2.80 67	4.87 99	22.1 107	3.05 100	3.58 92	4.35 80	4.15 119	5.55 107	17.5 109	5.78 115	3.74 116	5.02 110	5.98 132	5.21 110	11.9 115	5.20 107
Fusion [6]	91.7	4.43 79	13.7 98	4.08 98	2.47 23	8.91 31	2.24 37	3.70 35	9.68 34	3.12 72	3.68 75	19.8 86	2.54 92	4.26 124	5.16 125	4.31 122	6.32 116	16.8 105	6.15 119	4.55 131	5.78 130	3.10 95	7.12 124	13.6 125	7.86 124
p-harmonic [29]	91.9	4.64 94	13.0 93	4.43 105	3.41 79	11.9 76	2.93 85	7.60 98	18.1 106	3.96 95	4.65 95	21.0 99	2.97 98	3.46 84	4.33 76	3.34 92	4.75 94	17.5 109	4.60 104	3.05 90	4.17 78	2.15 53	5.09 109	10.9 109	3.77 85
CNN-flow-warp+ref [117]	92.8	4.93 102	14.5 110	4.29 103	4.18 91	11.9 76	4.24 104	8.23 110	19.7 116	6.35 104	5.13 105	24.4 118	2.96 96	3.55 91	4.40 82	3.85 109	3.82 62	15.0 88	3.39 67	1.96 22	3.44 23	2.14 52	10.0 134	14.8 131	10.8 132
Dynamic MRF [7]	93.8	4.58 89	12.4 84	4.14 99	3.25 68	13.9 100	2.27 41	6.02 84	16.8 100	2.36 44	4.39 90	22.6 110	2.51 91	3.61 94	4.55 94	3.46 96	6.81 121	22.2 131	6.78 125	2.41 52	3.48 30	3.69 113	9.26 132	17.8 135	10.2 129
SegOF [10]	95.0	5.85 109	13.5 96	3.98 95	7.40 115	14.9 107	8.13 122	8.55 113	17.3 103	9.01 110	6.50 118	18.1 79	5.14 120	3.90 112	4.53 91	4.81 128	6.57 120	21.7 129	6.81 126	1.65 5	3.49 32	1.08 3	3.71 79	9.23 89	3.63 78
FlowNetS+ft+v [112]	95.0	4.22 72	12.1 82	3.48 81	4.50 99	13.4 95	3.85 99	8.29 111	18.4 109	6.20 103	4.87 99	21.6 104	3.01 99	3.93 113	5.04 121	3.47 99	3.71 57	15.3 94	3.21 59	3.32 99	5.12 113	3.87 115	3.76 80	9.44 92	3.74 84
ResPWCR_ROB [145]	95.4	7.29 119	16.3 117	6.15 117	4.28 94	11.4 72	3.95 100	5.85 80	13.6 73	5.20 100	4.75 97	17.5 76	3.50 107	3.80 106	4.53 91	4.12 118	4.96 101	15.0 88	4.81 106	3.52 106	5.22 120	2.40 62	3.61 77	6.77 66	4.27 96
LDOF [28]	95.6	4.60 90	13.0 93	3.77 92	4.67 101	15.5 112	3.67 95	5.63 78	14.0 75	4.21 96	5.80 112	27.1 128	3.43 106	3.52 89	4.50 89	3.46 96	4.84 97	17.8 111	4.04 88	2.46 58	4.14 77	3.25 103	4.85 106	12.0 116	3.78 86
Second-order prior [8]	96.3	4.03 61	11.6 76	3.35 67	3.88 86	14.0 102	3.08 89	7.21 94	17.6 105	3.57 86	4.14 87	19.9 89	2.31 85	3.66 96	4.86 111	2.73 75	7.32 124	21.2 127	6.76 124	4.02 119	4.58 97	4.01 117	4.27 89	10.4 103	5.12 103
WOLF_ROB [149]	97.1	5.79 108	16.6 119	4.49 107	7.62 116	21.2 130	5.10 109	9.70 116	21.0 120	5.66 102	5.32 109	19.0 81	3.78 112	3.61 94	4.49 87	3.54 102	4.63 89	13.6 75	4.34 99	2.30 48	3.89 66	2.16 56	4.37 91	7.52 79	6.03 115
AugFNG_ROB [144]	97.6	8.29 125	19.2 126	5.66 113	7.67 117	16.0 115	8.01 121	10.1 118	20.5 118	11.0 120	5.13 105	15.5 54	3.64 109	4.11 120	4.97 119	3.93 110	4.45 81	15.1 91	4.20 92	2.27 46	4.37 87	1.23 8	3.80 81	6.87 68	4.34 99
ContFlow_ROB [150]	98.1	9.09 129	19.9 129	6.50 122	6.19 110	13.4 95	6.15 112	9.17 115	18.8 111	9.23 111	5.18 108	15.2 47	3.74 111	4.69 131	5.58 129	4.78 127	6.30 115	17.2 108	6.52 122	2.47 59	4.66 100	1.34 9	2.67 60	4.94 47	2.35 47
FlowNet2 [122]	101.0	8.58 128	18.6 123	6.31 118	9.39 126	17.6 119	9.09 127	8.06 105	15.8 91	9.81 114	5.61 111	16.2 67	4.12 114	4.04 116	4.88 113	3.79 107	4.92 98	16.2 101	4.50 101	4.28 126	6.73 138	2.84 81	2.05 41	4.54 40	1.41 18
StereoFlow [44]	101.5	17.1 145	28.1 145	17.9 144	18.7 142	29.7 143	16.5 137	20.1 142	30.9 141	17.5 137	21.2 142	38.3 144	17.9 140	4.60 128	5.05 122	5.52 130	2.38 4	11.5 50	1.77 2	1.25 1	2.92 2	0.71 1	4.49 97	10.3 102	4.23 94
EPMNet [133]	102.0	8.37 127	18.8 125	6.44 120	9.35 125	18.4 121	8.78 126	7.42 96	14.7 81	8.61 108	5.98 115	20.4 96	4.27 116	4.04 116	4.88 113	3.79 107	4.92 98	16.2 101	4.50 101	3.65 114	6.14 134	2.42 64	2.60 56	6.15 60	1.74 28
Ad-TV-NDC [36]	103.1	8.36 126	14.0 103	11.1 137	12.9 133	19.9 127	12.8 133	14.4 129	23.1 122	12.1 123	7.40 121	20.6 98	6.33 121	3.47 86	4.66 101	2.39 43	3.95 70	13.8 78	3.51 70	2.48 60	3.75 54	2.05 48	9.75 133	12.1 118	16.7 140
LFNet_ROB [151]	103.8	7.69 120	19.8 127	5.72 115	4.70 102	13.3 94	4.13 103	8.15 108	20.0 117	5.42 101	4.73 96	17.1 75	3.42 105	4.15 121	5.10 124	4.05 114	5.28 104	18.0 113	4.64 105	2.87 81	4.74 101	1.98 45	4.92 107	11.4 112	5.01 102
Shiralkar [42]	105.6	4.64 94	14.1 106	3.94 93	4.29 95	16.9 117	2.77 78	7.75 99	18.8 111	3.19 76	5.54 110	25.0 121	3.56 108	3.51 88	4.55 94	3.04 84	7.41 125	20.1 125	6.41 120	3.76 117	4.35 85	5.28 128	6.56 120	14.4 130	5.30 110
Learning Flow [11]	106.0	4.23 73	11.7 78	3.41 77	4.16 90	15.3 110	3.42 93	6.78 91	16.9 101	3.83 93	6.41 117	25.3 122	4.25 115	4.66 130	6.01 138	4.00 113	6.33 118	20.7 126	5.30 109	3.09 93	4.84 104	2.91 90	7.08 123	15.0 132	5.27 109
StereoOF-V1MT [119]	106.5	4.71 97	14.1 106	3.95 94	5.10 106	20.3 129	2.78 79	7.98 104	20.7 119	2.57 57	4.48 92	21.1 100	2.79 94	4.20 123	5.29 127	4.10 116	6.85 123	22.3 132	6.42 121	2.45 57	4.17 78	3.15 99	10.5 135	18.4 138	10.5 130
IAOF2 [51]	107.6	5.38 106	13.7 98	4.50 108	5.95 109	14.6 105	5.61 110	8.80 114	18.8 111	9.40 112	12.2 131	23.8 117	13.1 135	3.86 109	4.89 115	3.12 87	5.21 103	14.9 87	4.54 103	4.33 127	5.15 114	3.93 116	4.39 93	8.57 84	3.87 88
TVL1_ROB [139]	108.9	11.3 134	19.8 127	13.0 139	12.9 133	19.6 126	13.7 135	17.4 136	27.8 135	18.0 138	12.6 133	28.9 130	11.8 133	3.71 98	4.78 108	3.46 96	4.21 77	18.0 113	3.99 86	1.79 9	3.54 39	1.21 6	7.58 128	13.9 128	8.92 127
Modified CLG [34]	109.7	7.17 118	17.1 122	6.47 121	6.85 113	14.9 107	7.48 117	14.0 125	24.8 126	15.7 133	8.35 124	27.3 129	6.36 122	3.96 114	4.99 120	4.08 115	4.54 86	19.3 121	4.15 91	2.33 49	3.86 64	2.40 62	6.00 115	13.8 127	5.40 111
GraphCuts [14]	110.5	6.25 110	14.3 109	5.53 112	8.60 120	20.1 128	6.61 115	7.91 103	15.4 86	10.9 119	4.88 101	19.0 81	3.05 100	3.78 101	4.71 103	3.94 111	8.74 133	16.4 103	5.39 111	4.04 120	4.87 106	4.85 126	6.35 118	12.2 119	6.05 116
2D-CLG [1]	110.6	10.1 131	22.6 136	7.59 127	9.84 128	16.9 117	11.1 132	16.9 135	28.2 136	18.8 141	14.1 135	31.1 134	13.1 135	3.86 109	4.62 99	4.53 124	5.98 113	21.2 127	5.97 117	1.76 7	3.14 6	1.46 12	6.29 117	12.9 124	5.81 113
Filter Flow [19]	110.6	6.48 112	14.6 111	4.96 109	5.73 108	15.7 113	5.07 108	10.1 118	18.6 110	14.3 129	9.04 126	23.3 114	7.80 126	3.98 115	4.71 103	4.21 121	5.86 111	15.0 88	5.41 112	4.98 136	6.87 139	2.78 76	4.82 105	8.66 85	3.65 80
SPSA-learn [13]	111.4	6.84 117	16.7 120	6.74 123	8.47 119	19.4 124	7.49 118	12.5 121	23.1 122	13.1 127	8.40 125	25.8 125	7.08 124	3.87 111	4.66 101	4.10 116	6.32 116	18.8 117	6.89 127	2.56 63	3.85 63	1.79 26	7.29 125	12.5 121	7.47 122
HBpMotionGpu [43]	112.8	6.57 114	15.0 114	5.17 110	8.29 118	18.0 120	8.29 123	14.1 126	26.5 129	13.2 128	6.12 116	25.3 122	3.94 113	3.79 103	4.62 99	3.97 112	4.80 96	15.7 95	4.11 89	4.40 128	5.20 117	2.87 86	6.28 116	11.7 114	7.31 119
IAOF [50]	113.7	6.49 113	14.6 111	6.42 119	9.22 124	18.5 122	7.94 120	16.4 134	27.4 133	13.0 126	8.22 122	22.2 108	7.73 125	3.77 100	4.76 107	3.42 94	6.84 122	18.8 117	4.23 94	3.59 110	4.46 90	2.83 80	7.51 127	10.1 99	10.6 131
GroupFlow [9]	114.0	8.00 122	18.6 123	8.09 129	11.1 131	23.7 135	10.3 130	12.6 122	25.6 127	12.8 125	5.84 114	20.3 95	4.39 117	4.69 131	5.81 134	3.67 104	9.29 134	22.4 133	10.1 136	2.11 35	3.99 72	2.29 59	5.75 112	10.0 96	7.39 121
Black & Anandan [4]	114.7	6.81 116	15.4 115	7.43 125	8.77 122	19.5 125	7.35 116	13.0 123	22.9 121	12.5 124	8.29 123	26.1 126	6.77 123	4.18 122	5.28 126	3.69 105	6.19 114	20.0 124	5.34 110	3.63 111	5.05 111	1.79 26	6.45 119	12.2 119	5.17 106
BlockOverlap [61]	117.8	6.67 115	13.1 95	5.87 116	6.62 112	13.9 100	6.53 114	10.6 120	19.5 115	10.1 115	6.97 120	24.9 120	5.13 119	4.38 125	4.61 98	6.37 137	7.47 127	15.7 95	6.05 118	6.23 139	6.41 137	13.0 142	6.92 122	9.60 93	12.2 134
Nguyen [33]	118.2	7.88 121	16.8 121	7.02 124	13.4 135	19.0 123	15.3 136	17.6 137	28.9 137	17.2 136	12.0 130	26.9 127	11.6 132	4.38 125	5.07 123	5.58 133	5.69 109	19.7 123	5.93 116	2.75 75	4.02 74	1.91 41	6.59 121	12.5 121	6.52 118
UnFlow [129]	119.3	14.6 143	25.8 141	9.09 133	9.40 127	16.8 116	9.89 129	14.2 127	26.9 130	11.2 121	10.0 127	25.4 124	8.67 128	5.43 138	5.90 135	6.72 138	8.64 131	24.0 135	9.41 134	3.51 105	4.90 107	1.37 10	4.37 91	12.6 123	3.33 71
2bit-BM-tele [98]	120.0	8.00 122	15.8 116	8.40 131	4.91 105	13.4 95	4.67 105	8.14 106	19.0 114	5.12 99	6.62 119	23.5 116	5.04 118	4.08 118	4.78 108	4.61 126	8.68 132	18.8 117	8.31 130	6.46 141	7.08 141	9.47 138	7.36 126	14.1 129	9.62 128
Horn & Schunck [3]	124.8	8.01 124	19.9 129	8.38 130	9.13 123	23.2 134	7.71 119	14.2 127	25.9 128	14.6 131	12.4 132	30.6 132	11.3 131	4.64 129	5.64 130	4.60 125	8.21 130	24.4 136	8.45 131	4.01 118	5.41 122	1.95 43	9.16 131	17.5 133	8.86 126
SILK [79]	126.3	9.34 130	20.4 131	10.5 136	10.4 129	21.9 131	10.3 130	16.0 133	27.5 134	14.5 130	10.3 128	29.0 131	8.54 127	4.81 133	5.65 131	5.56 132	9.41 135	25.4 138	8.74 132	2.79 78	3.68 52	4.62 124	10.9 136	17.8 135	12.3 135
Heeger++ [104]	128.0	11.9 137	21.8 134	8.08 128	12.5 132	29.7 143	9.42 128	14.8 130	27.1 131	9.68 113	14.3 136	31.0 133	12.7 134	4.98 135	5.74 132	4.97 129	17.5 143	34.1 144	18.4 143	2.75 75	5.44 123	2.15 53	12.3 138	18.8 139	14.8 138
TI-DOFE [24]	128.8	13.4 141	23.2 137	16.5 143	16.5 139	24.1 136	18.2 141	20.2 143	31.1 143	20.6 142	19.9 141	32.9 137	20.8 142	4.89 134	5.90 135	5.54 131	8.04 129	23.9 134	8.81 133	2.97 86	4.34 84	1.88 38	10.9 136	17.7 134	11.9 133
H+S_ROB [138]	130.2	13.0 139	27.1 144	9.66 134	13.4 135	24.8 138	13.4 134	18.7 141	30.9 141	18.3 140	25.8 145	35.7 141	26.4 144	7.08 143	8.13 143	9.10 142	14.6 141	31.3 143	16.3 141	2.17 37	4.44 89	2.11 51	15.1 142	19.9 141	14.2 137
HCIC-L [99]	132.9	15.7 144	22.0 135	10.1 135	31.5 145	26.6 141	41.0 145	14.8 130	23.1 122	16.8 135	18.4 140	34.4 139	18.2 141	5.94 139	6.35 139	6.35 136	10.6 138	19.2 120	11.4 138	18.7 145	17.8 145	19.2 144	4.93 108	8.34 82	5.16 104
SLK [47]	133.1	11.6 135	26.0 142	14.6 142	15.3 138	25.0 139	17.5 139	17.8 139	30.1 140	18.1 139	25.4 144	33.6 138	28.0 145	5.25 136	5.90 135	7.03 139	10.3 137	27.4 140	10.6 137	2.89 83	4.47 91	2.94 92	14.9 141	20.7 142	18.8 141
FFV1MT [106]	134.0	12.0 138	23.3 138	8.83 132	10.7 130	26.6 141	8.71 125	15.6 132	29.0 138	12.0 122	16.6 139	36.3 143	15.5 138	6.51 142	6.40 140	10.4 143	16.2 142	30.7 142	17.7 142	3.41 103	5.44 123	3.35 109	12.3 138	18.8 139	14.8 138
Adaptive flow [45]	135.9	13.2 140	20.8 132	14.0 141	17.1 141	22.0 132	17.9 140	18.1 140	27.1 131	22.8 144	11.8 129	31.1 134	10.5 129	6.35 141	7.13 142	6.25 135	9.87 136	21.8 130	9.44 135	12.6 144	11.4 144	20.0 145	7.75 129	13.6 125	7.73 123
PGAM+LK [55]	137.1	11.8 136	25.6 139	13.9 140	14.8 137	24.4 137	16.7 138	13.2 124	24.0 125	15.0 132	16.2 138	41.2 145	15.3 137	5.40 137	5.45 128	8.10 140	12.3 140	26.5 139	12.1 139	7.42 142	8.24 143	7.87 136	13.2 140	18.3 137	19.4 142
Periodicity [78]	138.1	11.2 133	27.0 143	7.46 126	16.6 140	29.8 145	18.2 141	25.3 145	31.2 145	24.9 145	12.7 134	35.7 141	11.1 130	31.7 145	41.4 145	25.1 145	23.8 145	41.5 145	23.8 145	2.92 84	5.62 127	6.90 134	18.6 144	33.1 145	22.3 143
FOLKI [16]	138.9	10.5 132	25.6 139	11.9 138	20.9 143	26.2 140	26.1 143	17.6 137	31.1 143	16.5 134	15.4 137	32.6 136	16.0 139	6.16 140	6.53 141	9.07 141	12.2 139	29.7 141	13.0 140	4.67 133	5.83 131	9.41 137	18.2 143	22.8 143	25.1 144
Pyramid LK [2]	141.8	13.9 142	20.9 133	21.4 145	24.1 144	23.1 133	30.2 144	20.9 144	29.5 139	21.9 143	22.2 143	34.6 140	25.0 143	18.7 144	23.1 144	20.2 144	21.2 144	24.5 137	21.0 144	6.41 140	7.02 140	10.8 140	25.6 145	31.5 144	34.5 145
AdaConv-v1 [126]	146.4	39.2 146	39.9 146	41.8 146	73.0 146	74.5 146	71.1 146	70.1 146	67.3 146	71.8 146	64.4 146	66.2 146	65.9 146	76.5 147	78.1 147	72.0 147	68.2 147	64.9 147	66.5 147	52.3 147	45.1 147	70.9 147	81.8 146	81.6 146	82.3 146
SepConv-v1 [127]	146.4	39.2 146	39.9 146	41.8 146	73.0 146	74.5 146	71.1 146	70.1 146	67.3 146	71.8 146	64.4 146	66.2 146	65.9 146	76.5 147	78.1 147	72.0 147	68.2 147	64.9 147	66.5 147	52.3 147	45.1 147	70.9 147	81.8 146	81.6 146	82.3 146
SuperSlomo [132]	146.4	39.2 146	39.9 146	41.8 146	73.0 146	74.5 146	71.1 146	70.1 146	67.3 146	71.8 146	64.4 146	66.2 146	65.9 146	76.5 147	78.1 147	72.0 147	68.2 147	64.9 147	66.5 147	52.3 147	45.1 147	70.9 147	81.8 146	81.6 146	82.3 146
FGIK [136]	146.4	39.2 146	39.9 146	41.8 146	73.0 146	74.5 146	71.1 146	70.1 146	67.3 146	71.8 146	64.4 146	66.2 146	65.9 146	76.5 147	78.1 147	72.0 147	68.2 147	64.9 147	66.5 147	52.3 147	45.1 147	70.9 147	81.8 146	81.6 146	82.3 146
CtxSyn [137]	146.4	39.2 146	39.9 146	41.8 146	73.0 146	74.5 146	71.1 146	70.1 146	67.3 146	71.8 146	64.4 146	66.2 146	65.9 146	76.5 147	78.1 147	72.0 147	68.2 147	64.9 147	66.5 147	52.3 147	45.1 147	70.9 147	81.8 146	81.6 146	82.3 146
AVG_FLOW_ROB [142]	149.1	62.1 151	56.6 151	61.5 151	99.9 151	96.7 151	99.9 151	81.2 151	81.9 151	80.3 151	65.8 151	68.9 151	67.4 151	68.4 146	75.2 146	67.5 146	62.4 146	55.3 146	59.6 146	31.5 146	28.0 146	29.3 146	86.1 151	96.7 151	87.2 151

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.
[142] AVG_FLOW_ROB	N/A	2	N/A	Average flow field of ROB 2018 training set.
[143] LiteFlowNet	0.06	2	color	T.-W. Hui, X. Tang, and C. C. Loy. LiteFlowNet: A lightweight convolutional neural network for optical flow estimation. CVPR 2018.
[144] AugFNG_ROB	0.10	all	color	Anonymous. FusionNet and AugmentedFlowNet: Selective proxy ground truth for training on unlabeled images. ECCV 2018 submission 2834.
[145] ResPWCR_ROB	0.2	2	color	Anonymous. Learning optical flow with residual connections. ROB 2018 submission.
[146] FF++_ROB	17.43	2	color	R. Schuster, C. Bailer, O. Wasenmueller, D. Stricker. FlowFields++: Accurate optical flow correspondences meet robust interpolation. ICIP 2018. Submitted to ROB 2018.
[147] ProFlow_ROB	76	3	color	Anonymous. ProFlow: Learning to predict optical flow. BMVC 2018 submission 277.
[148] PWC-Net_ROB	0.069	2	color	D. Sun, X. Yang, M.-Y. Liu, and J. Kautz. PWC-Net: CNNs for optical flow using pyramid, warping, and cost volume. CVPR 2018.
[149] WOLF_ROB	0.02	2	color	Anonymous. Reversed deep neural network for optical flow. ROB 2018 submission.
[150] ContFlow_ROB	0.45	all	color	Anonymous. Continual Flow. ROB 2018 submission.
[151] LFNet_ROB	0.068	2	color	Anonymous. Learning a flow network. ROB 2018 submission.

* 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.