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]	5.8	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 4	9.14 8	1.06 4	2.28 2	2.94 1	1.57 2	2.39 5	6.78 2	2.15 9	2.00 27	3.36 18	1.62 21	0.99 1	2.16 3	0.57 2
NN-field [71]	11.2	2.89 8	8.13 16	2.11 5	2.10 7	7.15 9	1.77 16	2.27 4	5.59 5	1.61 9	1.58 1	8.52 7	0.79 1	2.35 4	3.05 5	1.60 3	1.89 1	5.20 1	1.37 1	2.43 58	3.70 56	1.95 45	1.01 2	2.25 4	0.53 1
OFLAF [77]	14.4	3.04 15	7.80 10	2.40 14	2.14 8	7.02 5	1.72 10	2.25 3	5.32 2	1.56 6	2.62 21	13.7 28	1.37 23	2.35 4	3.13 6	1.62 4	2.98 24	7.73 7	2.57 23	2.08 33	3.27 12	2.05 50	1.33 13	2.43 7	1.40 17
PMMST [114]	15.5	3.42 44	7.60 5	2.65 33	2.32 12	6.39 1	2.20 35	2.63 11	6.08 8	2.03 29	2.06 7	6.07 3	1.44 31	2.60 10	3.27 8	1.91 10	2.56 7	6.78 2	2.09 5	2.06 29	3.53 39	1.63 22	1.27 10	2.29 5	1.02 7
nLayers [57]	17.9	2.80 6	7.42 3	2.20 8	2.71 32	7.24 10	2.55 62	2.61 9	6.24 9	2.45 55	2.30 13	12.7 15	1.16 8	2.30 3	3.02 3	1.70 5	2.62 11	6.95 4	2.09 5	2.29 50	3.46 28	1.89 42	1.38 15	3.06 18	1.29 15
MDP-Flow2 [68]	20.8	3.23 32	7.93 13	2.60 25	1.92 2	6.64 2	1.52 1	2.46 7	5.91 7	1.56 6	3.05 48	15.8 61	1.51 42	2.77 25	3.50 18	2.16 29	2.86 20	8.58 18	2.70 34	2.00 27	3.50 36	1.59 19	1.28 11	2.67 12	0.89 4
ComponentFusion [96]	21.0	2.78 5	8.20 17	2.05 4	2.04 5	7.31 11	1.66 9	2.55 8	6.78 13	1.61 9	2.24 12	13.1 18	1.01 3	2.71 21	3.56 21	2.10 24	3.55 55	12.4 63	3.22 61	2.19 44	3.60 48	1.54 18	1.32 12	2.91 14	1.13 9
TC/T-Flow [76]	23.3	2.69 3	7.75 9	1.87 2	2.76 35	10.2 49	1.73 11	3.33 26	9.01 32	1.49 2	2.86 37	16.7 71	1.21 10	2.60 10	3.49 17	1.90 9	2.21 2	7.65 5	2.04 4	1.84 14	3.23 9	3.14 102	2.03 40	4.53 40	1.49 21
FC-2Layers-FF [74]	27.4	3.02 14	7.87 12	2.61 26	2.72 33	9.35 37	2.29 43	2.36 5	5.47 4	2.15 36	2.48 14	12.6 14	1.28 14	2.49 7	3.19 7	2.03 17	3.39 43	8.92 20	2.83 45	2.83 82	3.92 72	2.80 81	1.25 8	2.57 11	1.20 12
WLIF-Flow [93]	28.6	2.96 10	7.67 6	2.40 14	2.41 17	7.70 15	2.10 29	2.98 18	7.63 20	1.97 28	2.71 29	13.5 24	1.33 17	3.01 46	4.00 52	2.40 48	3.03 27	8.32 12	2.44 17	2.09 35	3.36 18	2.04 49	2.26 48	4.97 50	2.59 57
Layers++ [37]	29.0	3.11 18	8.22 20	2.79 45	2.43 20	7.02 5	2.24 38	2.43 6	5.77 6	2.18 39	2.13 9	9.71 10	1.15 7	2.35 4	3.02 3	1.96 11	3.81 63	11.4 47	3.22 61	2.74 77	4.01 77	2.35 64	1.45 16	3.05 17	1.79 32
HAST [109]	29.6	2.58 1	7.12 1	1.81 1	2.41 17	7.05 7	2.10 29	1.83 1	4.19 1	1.17 1	2.84 36	15.5 55	1.08 5	2.23 1	2.97 2	1.40 1	3.72 60	10.0 33	3.92 87	3.40 105	4.90 111	5.66 134	1.20 7	2.09 1	1.24 13
AGIF+OF [85]	30.7	3.06 16	8.20 17	2.55 23	3.17 61	10.6 56	2.46 56	3.46 31	8.97 31	2.24 42	2.61 19	13.7 28	1.33 17	2.63 15	3.46 15	2.11 25	2.88 22	8.34 14	2.35 13	2.10 37	3.56 43	2.09 52	1.80 30	3.68 30	2.24 43
Efficient-NL [60]	30.9	2.99 13	8.23 21	2.28 9	2.72 33	8.95 33	2.25 41	3.81 41	9.87 38	2.07 33	2.77 33	14.3 37	1.46 37	2.61 12	3.48 16	1.96 11	3.31 39	8.33 13	2.59 25	2.60 68	3.75 57	2.54 71	1.60 22	3.02 15	1.66 24
FESL [72]	31.0	2.96 10	7.70 7	2.54 21	3.26 72	10.4 53	2.56 63	3.25 24	8.39 24	2.17 37	2.56 16	13.2 19	1.31 16	2.57 9	3.40 11	2.12 27	2.60 9	7.65 5	2.30 11	2.64 73	4.22 86	2.47 68	1.75 28	3.49 27	1.71 27
LME [70]	31.0	3.15 23	8.04 15	2.31 11	1.95 3	6.65 3	1.59 4	4.03 47	9.31 33	4.57 100	2.69 27	13.6 26	1.42 28	2.85 32	3.61 24	2.42 50	3.47 51	12.8 70	3.17 57	2.12 39	3.53 39	1.73 24	1.34 14	2.75 13	1.18 11
ALD-Flow [66]	31.3	2.82 7	7.86 11	2.16 6	2.84 42	10.1 46	1.86 19	3.73 39	10.4 42	1.67 13	3.10 50	16.8 72	1.28 14	2.69 20	3.60 23	1.85 8	2.79 15	11.3 46	2.32 12	2.07 31	3.25 11	3.10 99	2.03 40	5.11 51	1.94 35
RNLOD-Flow [121]	32.3	2.66 2	7.33 2	2.17 7	2.53 28	9.46 39	1.86 19	3.94 45	10.7 48	1.95 25	2.50 15	13.5 24	1.21 10	2.68 18	3.62 26	2.05 19	2.99 25	8.59 19	2.75 38	3.00 92	4.54 98	3.25 107	1.48 18	3.24 21	1.76 31
IROF++ [58]	32.8	3.17 26	8.69 31	2.61 26	2.79 37	9.61 40	2.33 44	3.43 28	8.86 28	2.38 49	2.87 40	14.8 42	1.52 44	2.74 23	3.57 22	2.19 31	3.20 35	9.70 30	2.71 35	1.96 25	3.45 27	1.22 9	1.80 30	4.06 32	2.50 53
ProFlow_ROB [146]	33.2	3.29 33	9.91 57	2.35 13	2.50 26	10.0 45	1.83 17	4.04 48	11.6 56	1.96 27	2.86 37	15.0 45	1.22 12	2.87 35	3.89 43	1.97 14	2.60 9	10.5 37	2.20 10	1.53 4	3.54 41	1.53 17	2.50 55	6.37 67	2.33 48
NNF-EAC [103]	33.3	3.31 36	8.21 19	2.68 35	2.19 10	7.49 13	1.76 14	2.73 13	6.62 12	1.70 15	3.18 55	15.8 61	1.64 54	2.87 35	3.66 29	2.24 33	3.02 26	8.07 10	2.59 25	2.19 44	3.48 32	1.74 25	2.85 66	6.52 68	3.12 69
PH-Flow [101]	33.5	3.19 29	8.87 36	2.71 36	2.84 42	9.33 36	2.37 46	2.85 15	7.20 15	2.36 46	2.92 43	15.4 52	1.51 42	2.63 15	3.42 12	2.04 18	3.03 27	8.52 17	2.49 19	2.69 75	3.60 48	3.13 101	1.25 8	2.53 9	1.34 16
Classic+CPF [83]	34.0	3.14 21	8.60 28	2.63 30	3.03 58	10.6 56	2.33 44	3.66 35	9.58 34	2.20 40	2.61 19	14.1 33	1.34 20	2.68 18	3.53 19	2.21 32	2.85 19	7.95 9	2.38 14	2.44 60	3.49 34	2.90 92	1.67 26	3.40 24	2.43 51
Sparse-NonSparse [56]	35.8	3.14 21	8.75 33	2.76 43	3.02 56	10.6 56	2.43 51	3.45 30	8.96 29	2.36 46	2.66 24	13.7 28	1.42 28	2.85 32	3.75 37	2.33 38	3.28 38	9.40 26	2.73 36	2.42 57	3.31 14	2.69 76	1.47 17	3.07 19	1.66 24
TC-Flow [46]	37.3	2.91 9	8.00 14	2.34 12	2.18 9	8.77 28	1.52 1	3.84 43	10.7 48	1.49 2	3.13 51	16.6 70	1.46 37	2.78 26	3.73 36	1.96 11	3.08 30	11.4 47	2.66 29	1.94 23	3.43 24	3.20 106	3.06 71	7.04 73	4.08 95
3DFlow [135]	37.7	3.44 45	8.63 30	2.46 17	2.43 20	8.59 27	1.75 13	3.71 37	9.93 40	1.64 11	1.61 3	4.58 1	1.23 13	2.86 34	3.72 34	2.16 29	4.52 88	11.6 53	4.20 95	3.16 100	4.02 78	4.44 126	1.13 5	2.14 2	0.89 4
LSM [39]	38.2	3.12 19	8.62 29	2.75 42	3.00 54	10.5 55	2.44 53	3.43 28	8.85 27	2.35 45	2.66 24	13.6 26	1.44 31	2.82 28	3.68 30	2.36 41	3.38 42	9.41 27	2.81 43	2.69 75	3.52 37	2.84 85	1.59 21	3.38 23	1.80 33
SVFilterOh [111]	39.0	3.63 51	8.82 34	2.86 47	2.60 30	8.06 18	2.05 28	2.95 16	7.09 14	2.03 29	2.80 35	13.8 31	1.41 27	2.63 15	3.42 12	1.75 7	3.49 52	10.3 35	3.23 64	3.63 114	5.75 133	4.47 127	1.09 4	2.45 8	0.92 6
Ramp [62]	39.2	3.18 28	8.83 35	2.73 39	2.89 47	10.1 46	2.44 53	3.27 25	8.43 25	2.38 49	2.74 31	14.2 34	1.46 37	2.82 28	3.69 33	2.29 36	3.37 41	9.31 24	2.93 49	2.62 71	3.38 22	3.19 105	1.54 20	3.21 20	2.24 43
Correlation Flow [75]	39.3	3.38 42	8.40 23	2.64 31	2.23 11	7.54 14	1.56 3	5.14 71	13.1 70	1.60 8	2.09 8	8.15 6	1.35 22	3.12 54	4.09 59	2.34 39	4.01 74	11.5 51	4.00 89	2.59 67	3.61 50	3.00 97	1.49 19	3.04 16	1.42 19
ProbFlowFields [128]	40.1	4.18 71	12.4 86	3.40 78	2.43 20	8.16 20	2.19 34	3.65 34	9.72 36	2.86 70	2.22 10	9.42 9	1.42 28	3.01 46	3.96 49	2.36 41	2.73 14	10.9 39	2.51 20	1.89 21	3.39 23	1.82 30	2.59 58	6.21 65	2.75 60
PMF [73]	40.2	3.61 49	9.07 39	2.62 28	2.40 15	8.05 17	1.83 17	2.61 9	6.27 10	1.65 12	3.35 65	15.4 52	1.58 49	2.54 8	3.27 8	1.71 6	3.59 56	11.1 44	3.46 71	4.07 124	6.18 140	4.02 122	1.06 3	2.38 6	1.25 14
COFM [59]	40.4	3.17 26	9.90 56	2.46 17	2.41 17	8.34 24	1.92 22	3.77 40	10.5 43	2.54 58	2.71 29	14.9 44	1.19 9	3.08 51	3.92 47	3.25 94	3.83 66	10.9 39	3.15 56	2.20 47	3.35 16	2.91 94	1.62 25	2.56 10	2.09 39
JOF [140]	41.5	3.08 17	8.56 26	2.51 20	3.27 73	10.2 49	2.81 84	3.02 20	7.55 17	2.42 53	2.64 22	14.2 34	1.34 20	2.62 13	3.42 12	2.08 20	3.26 36	8.96 21	2.56 21	3.12 99	4.26 87	4.09 124	2.11 46	4.58 42	2.18 41
FMOF [94]	41.7	3.12 19	8.23 21	2.73 39	3.25 69	10.7 63	2.52 60	3.01 19	7.61 18	2.20 40	2.56 16	13.4 22	1.33 17	2.75 24	3.61 24	2.24 33	3.66 58	8.50 16	2.78 41	2.62 71	3.84 65	3.27 109	2.66 63	5.69 56	1.95 37
OAR-Flow [125]	42.5	3.37 40	9.87 55	2.67 34	4.22 95	12.8 92	2.87 86	4.95 67	13.4 73	2.66 62	3.23 57	16.4 69	1.37 23	2.83 30	3.82 40	1.97 14	2.49 6	10.9 39	1.87 3	1.52 3	2.82 1	1.86 36	1.85 33	4.35 37	1.68 26
Classic+NL [31]	42.9	3.20 31	8.72 32	2.81 46	3.02 56	10.6 56	2.44 53	3.46 31	8.84 26	2.38 49	2.78 34	14.3 37	1.46 37	2.83 30	3.68 30	2.31 37	3.40 44	9.09 23	2.76 40	2.87 84	3.82 64	2.86 89	1.67 26	3.53 28	2.26 47
TV-L1-MCT [64]	44.0	3.16 25	8.48 25	2.71 36	3.28 74	10.8 67	2.60 71	3.95 46	10.5 43	2.38 49	2.69 27	13.9 32	1.45 36	2.94 42	3.79 38	2.63 71	3.50 53	9.75 31	3.06 53	2.08 33	3.35 16	2.29 61	1.95 36	3.89 31	2.71 59
HCFN [163]	44.2	3.15 23	8.58 27	2.42 16	2.09 6	8.31 23	1.63 7	2.81 14	7.61 18	1.54 5	2.86 37	15.3 49	1.44 31	2.73 22	3.55 20	2.08 20	3.42 46	10.4 36	3.28 65	4.88 139	6.08 138	5.70 135	2.45 53	5.24 54	3.47 78
PWC-Net_ROB [147]	46.7	4.86 104	12.4 86	3.56 87	3.14 60	10.3 52	2.60 71	4.38 56	11.6 56	3.18 77	2.56 16	10.6 12	1.52 44	3.25 71	4.18 63	2.46 52	3.10 32	10.6 38	2.75 38	1.44 2	3.56 43	1.01 3	1.60 22	3.41 25	1.14 10
IIOF-NLDP [131]	47.8	3.65 52	9.81 54	2.56 24	2.79 37	9.36 38	2.00 24	4.28 54	11.3 54	1.69 14	2.02 6	7.52 5	1.38 26	3.36 78	4.52 93	2.40 48	3.82 64	11.2 45	3.67 80	2.07 31	3.79 61	1.88 40	2.91 68	5.30 55	4.17 96
SimpleFlow [49]	48.4	3.35 37	9.20 42	2.98 54	3.18 64	10.7 63	2.71 77	5.06 69	12.6 68	2.70 64	2.95 45	15.1 47	1.58 49	2.91 40	3.79 38	2.47 53	3.59 56	9.49 28	2.99 51	2.39 55	3.46 28	2.24 60	1.60 22	3.56 29	1.57 22
CostFilter [40]	48.5	3.84 56	9.64 50	3.06 56	2.55 29	8.09 19	2.03 26	2.69 12	6.47 11	1.88 21	3.66 76	16.8 72	1.88 66	2.62 13	3.34 10	1.99 16	4.05 75	11.0 43	3.65 79	4.16 126	7.18 147	4.66 129	1.16 6	3.36 22	0.87 3
2DHMM-SAS [92]	50.9	3.19 29	8.89 37	2.71 36	3.20 67	11.5 77	2.38 47	5.19 72	12.2 64	2.73 66	2.92 43	15.2 48	1.53 46	2.79 27	3.65 28	2.27 35	3.45 49	9.34 25	2.78 41	2.66 74	3.56 43	3.07 98	2.34 51	5.12 52	2.97 67
S2D-Matching [84]	51.8	3.36 38	9.66 51	2.86 47	3.19 66	11.1 71	2.46 56	4.86 66	12.9 69	2.47 56	2.67 26	13.2 19	1.44 31	2.87 35	3.72 34	2.38 44	3.45 49	9.76 32	2.95 50	3.05 93	3.79 61	3.30 111	1.95 36	4.16 35	3.00 68
FlowFields+ [130]	51.9	4.57 89	13.7 100	3.35 69	2.94 52	10.1 46	2.58 67	4.05 49	10.6 45	3.26 80	2.90 42	13.2 19	1.81 64	3.18 58	4.20 67	2.54 59	2.68 13	11.4 47	2.40 16	1.84 14	3.62 51	1.77 26	2.48 54	5.86 58	2.77 61
MLDP_OF [89]	52.0	4.13 67	10.3 64	3.60 88	2.34 13	7.70 15	1.88 21	4.23 53	10.9 51	1.87 20	2.74 31	14.6 41	1.37 23	3.10 52	3.91 46	2.48 57	3.40 44	9.00 22	3.79 84	3.46 107	4.20 84	5.55 133	2.31 49	4.64 45	1.98 38
AggregFlow [97]	52.9	4.25 77	11.9 83	3.26 61	4.46 101	13.7 103	3.43 97	4.76 64	12.4 65	3.93 97	3.28 60	15.6 57	1.68 56	2.89 38	3.89 43	2.08 20	2.32 3	7.75 8	2.14 7	2.06 29	3.77 59	1.48 15	2.07 44	4.11 33	2.36 49
MDP-Flow [26]	52.9	3.48 47	9.46 47	3.10 58	2.45 23	7.36 12	2.41 48	3.21 23	8.31 23	2.78 68	3.18 55	17.8 80	1.70 59	3.03 48	3.87 41	2.60 66	3.43 47	12.6 67	2.81 43	2.19 44	3.88 69	1.60 20	4.13 92	9.96 100	3.86 90
IROF-TV [53]	53.2	3.40 43	9.29 44	2.95 53	2.99 53	11.1 71	2.53 61	3.81 41	9.81 37	2.44 54	3.25 59	16.9 74	1.78 63	3.27 75	4.10 60	2.93 85	4.47 85	16.0 103	3.53 73	1.70 6	3.21 7	1.12 6	1.91 35	4.75 47	2.19 42
S2F-IF [123]	54.6	4.51 87	13.6 99	3.31 65	2.90 48	10.4 53	2.48 59	4.07 51	10.8 50	3.15 75	3.31 61	15.7 60	1.90 67	3.17 56	4.19 65	2.55 62	2.81 17	11.6 53	2.60 27	1.86 17	3.67 54	1.87 37	2.11 46	4.64 45	2.54 56
CombBMOF [113]	54.6	3.94 60	10.6 68	2.74 41	2.80 39	8.55 26	2.16 32	3.10 22	7.99 22	1.76 16	2.99 46	13.4 22	1.95 70	3.04 49	3.89 43	2.49 58	5.64 113	12.3 61	6.74 128	3.54 110	5.16 119	2.81 82	1.85 33	4.60 43	1.10 8
WRT [150]	55.0	3.74 54	9.34 45	2.48 19	3.37 80	10.2 49	2.58 67	6.80 96	15.3 88	2.24 42	1.58 1	5.01 2	1.09 6	2.89 38	3.68 30	2.35 40	5.52 111	12.0 57	4.21 97	2.30 51	3.85 66	2.34 63	3.20 74	4.91 48	4.21 97
FlowFields [110]	57.4	4.57 89	13.7 100	3.38 72	3.01 55	10.6 56	2.59 69	4.19 52	11.1 52	3.30 81	3.17 54	15.0 45	1.96 71	3.21 66	4.24 75	2.61 70	2.91 23	12.4 63	2.66 29	1.84 14	3.46 28	1.84 33	2.50 55	6.15 63	2.79 62
Sparse Occlusion [54]	58.8	3.62 50	9.12 40	2.90 49	2.92 50	9.08 34	2.56 63	4.49 61	11.8 62	2.11 35	3.14 52	15.8 61	1.57 48	3.26 72	4.22 70	2.36 41	3.52 54	10.9 39	2.66 29	5.10 143	6.32 141	3.15 103	2.02 39	4.92 49	1.71 27
NL-TV-NCC [25]	59.2	3.89 58	9.16 41	2.98 54	2.87 46	9.69 41	1.99 23	4.44 60	11.6 56	1.76 16	2.64 22	11.8 13	1.48 41	3.49 90	4.60 100	2.47 53	4.67 95	13.5 75	4.26 101	2.83 82	4.57 100	2.84 85	2.62 61	6.00 62	2.25 45
EPPM w/o HM [88]	59.5	4.25 77	11.1 72	3.13 59	2.36 14	8.35 25	1.76 14	3.72 38	10.2 41	1.81 18	3.24 58	14.5 40	1.94 69	3.16 55	3.94 48	2.82 80	4.78 99	12.9 71	4.32 102	3.64 116	4.54 98	5.73 136	1.76 29	4.11 33	1.94 35
PGM-C [120]	59.7	4.62 94	14.0 105	3.39 74	3.29 76	12.3 84	2.70 76	4.39 59	11.7 59	3.43 84	4.00 84	19.8 90	2.15 76	3.19 60	4.23 71	2.54 59	2.79 15	11.9 56	2.45 18	1.83 12	3.21 7	1.83 31	2.31 49	5.87 59	1.82 34
OFH [38]	59.8	3.90 59	9.77 53	3.62 91	2.84 42	11.0 70	2.04 27	5.52 79	14.4 81	1.89 22	3.52 68	20.5 102	1.60 52	3.18 58	4.06 57	2.82 80	3.86 67	14.1 84	3.59 75	1.77 10	3.62 51	1.81 29	2.64 62	7.08 76	2.15 40
SegFlow [161]	60.6	4.62 94	14.1 108	3.39 74	3.35 79	12.6 91	2.73 78	4.38 56	11.7 59	3.45 87	4.06 87	20.2 98	2.15 76	3.20 62	4.23 71	2.60 66	2.83 18	12.0 57	2.56 21	1.86 17	3.36 18	1.84 33	1.96 38	4.63 44	1.60 23
Occlusion-TV-L1 [63]	62.0	3.59 48	9.61 48	2.64 31	2.93 51	10.6 56	2.41 48	6.16 87	15.2 86	2.70 64	3.32 63	17.0 75	1.68 56	3.38 80	4.44 86	2.82 80	3.10 32	13.2 74	2.68 32	2.17 40	3.52 37	1.46 13	4.63 106	11.1 115	3.53 79
Complementary OF [21]	62.6	4.44 83	11.2 75	4.04 100	2.51 27	9.77 43	1.74 12	3.93 44	10.6 45	2.04 31	3.87 80	18.8 82	2.19 81	3.17 56	4.00 52	2.92 84	4.64 93	13.8 81	3.64 78	2.17 40	3.36 18	2.51 69	3.08 72	7.04 73	3.65 83
Adaptive [20]	64.2	3.29 33	9.43 46	2.28 9	3.10 59	11.4 74	2.46 56	6.58 92	15.7 93	2.52 57	3.14 52	15.6 57	1.56 47	3.67 101	4.46 88	3.48 104	3.32 40	13.0 73	2.38 14	2.76 80	4.39 92	1.93 44	3.58 80	8.18 86	2.88 64
Aniso-Texture [82]	65.2	2.96 10	7.72 8	2.54 21	2.48 25	8.26 22	2.24 38	6.48 90	15.9 98	2.63 60	1.96 5	10.1 11	0.98 2	3.26 72	4.21 68	2.60 66	5.74 116	16.9 112	5.61 118	4.47 134	5.88 136	3.33 112	3.51 79	7.12 77	3.68 85
ACK-Prior [27]	65.6	4.19 73	9.27 43	3.60 88	2.40 15	8.21 21	1.65 8	3.40 27	8.96 29	1.84 19	2.87 40	14.4 39	1.44 31	3.36 78	4.15 61	3.07 89	6.35 124	16.1 105	4.90 112	4.21 129	4.80 105	6.03 138	3.29 76	5.99 61	2.82 63
CPM-Flow [116]	66.2	4.63 96	14.1 108	3.39 74	3.33 77	12.5 88	2.73 78	4.37 55	11.7 59	3.43 84	4.00 84	19.9 93	2.14 75	3.19 60	4.23 71	2.54 59	3.08 30	12.0 57	2.88 47	1.87 19	3.44 25	1.84 33	2.91 68	7.48 83	2.91 66
DPOF [18]	66.6	4.67 99	12.6 92	3.30 63	3.57 85	10.6 56	3.12 93	3.09 21	7.50 16	2.32 44	3.06 49	14.8 42	1.82 65	3.21 66	4.18 63	2.79 79	4.47 85	12.5 65	3.33 66	4.09 125	3.92 72	6.96 140	2.09 45	4.39 38	1.74 29
EpicFlow [102]	66.8	4.61 93	14.0 105	3.39 74	3.33 77	12.5 88	2.74 80	5.37 75	14.8 84	3.46 88	3.94 83	19.2 86	2.13 74	3.20 62	4.23 71	2.58 65	2.87 21	12.2 60	2.64 28	1.83 12	3.28 13	1.83 31	3.21 75	7.12 77	3.61 80
DeepFlow2 [108]	68.3	4.04 64	11.2 75	3.38 72	3.80 88	12.4 87	2.86 85	5.12 70	13.4 73	3.00 71	4.17 91	20.1 95	2.18 80	2.96 43	3.97 50	2.08 20	3.06 29	12.6 67	2.69 33	2.17 40	3.24 10	2.71 77	4.74 108	10.4 108	4.38 104
TCOF [69]	68.8	4.17 70	10.4 66	3.71 94	3.17 61	10.7 63	2.59 69	6.58 92	15.7 93	3.82 95	3.69 78	16.1 66	2.37 90	3.78 105	4.95 122	2.47 53	2.59 8	8.47 15	2.58 24	3.66 118	4.83 106	2.67 75	1.83 32	4.20 36	1.46 20
ROF-ND [107]	68.8	4.12 65	10.0 58	3.37 71	2.78 36	8.82 30	2.12 31	4.61 63	11.9 63	2.09 34	2.23 11	6.56 4	1.69 58	3.60 97	4.75 110	2.85 83	4.92 102	13.6 78	3.75 82	4.59 136	5.18 120	4.10 125	2.67 64	5.19 53	3.46 77
HBM-GC [105]	70.2	5.25 107	10.5 67	4.34 107	3.17 61	8.78 29	2.94 89	4.38 56	10.6 45	2.68 63	3.59 72	12.8 16	2.47 93	2.96 43	3.64 27	2.64 72	3.96 73	8.26 11	3.56 74	4.40 132	5.92 137	3.62 116	2.55 57	6.34 66	3.29 72
RFlow [90]	70.7	3.82 55	10.0 58	3.44 81	2.61 31	9.73 42	2.02 25	5.66 81	14.5 82	2.05 32	3.93 82	23.1 116	1.90 67	3.24 68	4.19 65	2.66 74	4.12 78	15.2 99	3.34 68	2.61 69	3.56 43	2.65 74	4.48 101	10.5 111	3.93 94
Steered-L1 [118]	72.0	3.30 35	8.44 24	2.91 50	1.89 1	7.14 8	1.60 6	3.61 33	9.91 39	1.89 22	3.45 66	19.4 89	1.64 54	3.42 83	4.30 78	3.39 97	5.18 106	14.5 87	4.37 105	5.09 142	5.05 115	10.1 144	5.56 116	10.2 106	6.24 122
SRR-TVOF-NL [91]	72.8	4.47 85	10.9 70	3.32 67	4.04 92	13.2 98	2.90 87	4.81 65	12.5 66	3.15 75	3.33 64	15.3 49	1.61 53	3.24 68	4.03 56	2.70 76	3.94 71	11.8 55	3.33 66	4.16 126	5.21 123	3.44 115	2.06 43	3.48 26	2.42 50
DMF_ROB [139]	72.9	4.37 80	12.3 85	3.62 91	3.46 83	12.9 94	2.60 71	5.98 84	15.8 95	3.23 79	4.05 86	19.8 90	2.15 76	3.10 52	4.06 57	2.57 64	3.79 62	14.3 85	3.13 55	1.88 20	3.12 5	1.99 48	4.34 95	10.0 101	3.87 91
ComplOF-FED-GPU [35]	73.2	4.28 79	11.3 77	3.70 93	3.25 69	13.0 95	2.16 32	4.06 50	11.2 53	1.95 25	3.91 81	19.2 86	2.01 72	3.20 62	4.15 61	2.64 72	4.61 91	16.1 105	3.90 86	2.98 90	3.77 59	3.69 117	2.85 66	7.44 82	2.53 55
FF++_ROB [145]	74.7	4.84 103	14.8 116	3.46 82	3.18 64	11.4 74	2.69 75	5.30 74	14.1 78	3.73 94	3.31 61	14.2 34	2.20 82	3.26 72	4.29 77	2.72 77	4.58 90	12.7 69	3.70 81	1.91 22	3.46 28	2.19 59	3.65 82	7.31 79	5.97 119
TF+OM [100]	76.4	3.97 61	10.2 61	2.94 52	2.91 49	9.12 35	2.57 66	5.22 73	11.5 55	6.92 109	3.59 72	16.1 66	2.28 87	3.20 62	3.97 50	3.11 90	4.70 97	14.5 87	4.32 102	3.06 95	4.84 108	2.71 77	3.93 87	8.79 91	4.32 102
Aniso. Huber-L1 [22]	77.0	3.71 53	10.1 60	3.08 57	4.36 100	13.0 95	3.77 101	6.92 97	15.3 88	3.60 91	3.54 69	15.9 64	2.04 73	3.38 80	4.45 87	2.47 53	3.88 68	12.9 71	2.74 37	3.37 104	4.36 90	2.85 88	3.16 73	7.52 84	2.90 65
DeepFlow [86]	78.3	4.49 86	11.7 80	4.14 102	4.26 96	12.8 92	3.36 95	5.96 83	14.2 80	5.10 101	4.89 105	23.1 116	2.67 96	2.98 45	4.00 52	2.11 25	3.26 36	13.5 75	2.84 46	2.09 35	3.10 3	2.77 79	5.83 118	11.4 117	5.45 116
Classic++ [32]	79.1	3.37 40	9.67 52	2.91 50	3.28 74	12.1 81	2.61 74	5.46 78	14.1 78	3.00 71	3.63 74	20.2 98	1.70 59	3.24 68	4.34 80	2.60 66	4.65 94	16.0 103	3.60 76	3.09 96	3.94 75	3.28 110	4.64 107	10.4 108	3.71 86
TV-L1-improved [17]	80.0	3.36 38	9.63 49	2.62 28	2.82 40	10.7 63	2.23 36	6.50 91	15.8 95	2.73 66	3.80 79	21.3 107	1.76 62	3.34 77	4.38 84	2.39 45	5.97 118	18.1 120	5.67 119	3.57 112	4.92 113	3.43 114	4.01 90	9.84 99	3.44 76
LocallyOriented [52]	82.2	4.54 88	12.8 94	3.27 62	4.73 106	14.8 110	3.73 100	7.77 104	18.3 113	3.44 86	3.56 70	15.6 57	2.22 83	3.46 87	4.47 89	2.69 75	3.15 34	10.2 34	3.19 59	2.61 69	4.20 84	2.52 70	4.39 98	8.52 88	5.23 112
SIOF [67]	82.5	4.23 75	10.2 61	3.31 65	3.97 90	14.5 108	2.97 90	7.81 106	16.4 101	7.48 111	4.82 101	20.1 95	2.96 99	3.54 93	4.49 90	3.12 91	4.31 80	13.5 75	4.13 93	2.36 54	3.59 47	1.68 23	3.46 78	7.39 80	3.37 74
LiteFlowNet [142]	83.9	6.29 114	16.5 122	4.45 109	3.68 86	10.8 67	3.13 94	5.43 76	13.7 76	3.60 91	3.57 71	12.8 16	2.25 86	3.85 112	4.78 112	3.61 107	4.37 82	12.5 65	3.63 77	2.55 64	4.51 97	1.52 16	4.05 91	7.05 75	5.16 108
Brox et al. [5]	85.4	4.44 83	12.4 86	4.22 105	3.72 87	13.5 102	3.06 91	4.97 68	13.3 72	3.11 73	4.58 97	22.0 110	2.37 90	3.79 107	4.60 100	4.33 129	3.91 70	17.0 113	3.45 70	2.22 48	3.79 61	1.19 7	4.62 105	10.0 101	3.38 75
TriangleFlow [30]	85.7	4.12 65	10.6 68	3.47 83	3.47 84	13.1 97	2.41 48	6.00 85	15.2 86	2.17 37	2.99 46	16.0 65	1.58 49	4.46 133	5.79 138	4.15 125	5.42 110	13.9 83	5.24 113	3.10 98	5.47 129	2.90 92	3.02 70	6.82 70	3.64 82
CRTflow [80]	86.0	4.18 71	11.8 82	3.20 60	3.22 68	10.8 67	2.43 51	6.20 88	15.5 91	2.63 60	4.21 92	22.0 110	2.24 84	3.32 76	4.34 80	2.44 51	7.43 131	19.3 126	8.15 134	2.55 64	4.09 80	2.59 73	4.60 104	11.2 116	4.45 105
OFRF [134]	87.1	4.77 102	11.6 78	4.03 99	8.72 126	15.3 115	8.51 129	8.49 117	16.7 103	7.32 110	4.55 96	15.3 49	3.16 106	2.92 41	3.87 41	2.13 28	3.76 61	9.69 29	3.22 61	2.98 90	4.50 96	4.04 123	4.59 103	5.76 57	8.61 130
BriefMatch [124]	88.0	3.44 45	9.01 38	2.77 44	2.85 45	9.93 44	2.23 36	2.97 17	7.65 21	1.94 24	3.64 75	20.1 95	1.75 61	4.10 123	4.90 120	5.82 139	7.95 133	17.8 116	8.08 133	4.73 138	5.20 121	12.2 146	7.88 135	12.0 121	13.7 141
Rannacher [23]	88.4	4.13 67	11.0 71	3.61 90	3.39 81	12.3 84	2.80 83	7.26 99	17.4 109	3.59 90	4.40 94	23.1 116	2.24 84	3.43 85	4.54 96	2.56 63	5.41 109	18.5 121	4.23 98	2.92 87	3.91 71	2.82 83	3.45 77	9.14 92	3.27 71
F-TV-L1 [15]	89.3	5.44 110	12.5 91	5.69 119	5.46 111	15.0 113	4.03 104	7.48 101	16.3 100	3.42 83	5.08 108	23.3 119	2.81 98	3.42 83	4.34 80	3.03 87	4.05 75	15.1 96	3.18 58	2.43 58	3.92 72	1.87 37	3.90 86	9.35 96	2.61 58
SuperFlow [81]	90.4	4.16 69	11.1 72	3.32 67	4.80 107	12.2 82	4.68 110	7.80 105	16.0 99	10.6 122	5.16 112	22.4 114	3.24 108	3.39 82	4.24 75	3.71 111	3.44 48	13.7 80	2.91 48	3.19 101	4.62 102	1.87 37	4.74 108	10.6 112	4.24 99
TriFlow [95]	90.4	4.73 101	12.4 86	3.49 85	4.03 91	12.5 88	3.70 99	8.18 114	17.2 107	10.4 121	3.50 67	15.4 52	2.32 89	3.43 85	4.21 68	3.42 98	3.90 69	12.3 61	3.76 83	7.86 148	5.72 132	16.2 148	2.80 65	5.89 60	2.50 53
DF-Auto [115]	90.8	5.04 106	13.7 100	3.30 63	6.51 116	14.1 107	6.09 117	8.14 110	16.5 102	10.2 120	5.06 107	21.3 107	3.10 105	3.74 103	4.91 121	3.25 94	2.67 12	11.4 47	2.14 7	3.36 103	5.23 125	1.45 12	4.45 100	9.18 93	4.28 101
ContinualFlow_ROB [152]	90.8	7.36 123	17.7 127	5.46 116	5.94 114	12.2 82	5.98 116	8.16 113	18.3 113	7.89 112	5.11 109	19.3 88	3.18 107	4.15 126	5.04 126	3.68 109	5.65 114	15.1 96	6.17 125	1.72 7	3.34 15	1.11 5	2.34 51	4.48 39	2.25 45
Local-TV-L1 [65]	90.8	5.33 108	12.6 92	5.19 114	6.90 119	15.7 118	6.22 118	10.0 122	18.2 112	8.89 114	5.81 118	24.7 124	3.70 116	3.05 50	4.00 52	2.39 45	4.05 75	14.6 89	3.09 54	1.95 24	3.11 4	2.15 55	5.85 119	10.8 113	7.34 125
CLG-TV [48]	91.4	4.00 62	10.3 64	3.40 78	4.33 99	12.3 84	4.08 105	6.78 94	15.5 91	3.64 93	4.07 88	17.7 79	2.39 92	3.79 107	4.86 115	3.23 93	4.48 87	16.5 110	3.80 85	3.55 111	4.65 103	2.89 91	4.00 89	10.1 104	3.18 70
CBF [12]	92.2	3.88 57	10.2 61	3.50 86	4.60 103	11.3 73	5.06 111	5.43 76	13.1 70	3.39 82	4.09 89	21.2 106	2.16 79	3.80 110	4.72 109	3.52 105	4.33 81	14.4 86	3.01 52	4.97 140	5.51 130	4.93 131	3.99 88	9.27 95	3.91 93
Bartels [41]	94.7	4.43 81	11.1 72	4.17 104	2.83 41	8.84 31	2.56 63	4.54 62	12.5 66	2.80 69	4.87 102	22.1 112	3.05 103	3.58 96	4.35 83	4.15 125	5.55 112	17.5 114	5.78 120	3.74 119	5.02 114	5.98 137	5.21 115	11.9 120	5.20 111
Fusion [6]	95.2	4.43 81	13.7 100	4.08 101	2.47 24	8.91 32	2.24 38	3.70 36	9.68 35	3.12 74	3.68 77	19.8 90	2.54 95	4.26 130	5.16 131	4.31 128	6.32 121	16.8 111	6.15 124	4.55 135	5.78 134	3.10 99	7.12 129	13.6 130	7.86 129
p-harmonic [29]	95.5	4.64 97	13.0 95	4.43 108	3.41 82	11.9 78	2.93 88	7.60 102	18.1 111	3.96 98	4.65 98	21.0 104	2.97 101	3.46 87	4.33 79	3.34 96	4.75 98	17.5 114	4.60 109	3.05 93	4.17 82	2.15 55	5.09 114	10.9 114	3.77 88
CNN-flow-warp+ref [117]	96.5	4.93 105	14.5 113	4.29 106	4.18 94	11.9 78	4.24 107	8.23 115	19.7 121	6.35 108	5.13 110	24.4 123	2.96 99	3.55 94	4.40 85	3.85 115	3.82 64	15.0 93	3.39 69	1.96 25	3.44 25	2.14 54	10.0 139	14.8 136	10.8 137
CompactFlow_ROB [160]	96.5	8.85 134	18.7 130	5.45 115	5.55 112	12.0 80	5.64 115	8.73 119	17.0 106	11.7 126	5.19 113	17.5 77	3.62 114	4.11 124	4.99 124	3.72 112	4.37 82	14.6 89	4.01 90	1.75 8	3.64 53	0.96 2	4.14 93	7.40 81	5.55 117
EAI-Flow [151]	97.0	7.40 124	16.3 120	6.04 122	5.29 110	15.0 113	4.27 108	6.28 89	15.0 85	5.22 104	4.99 106	19.1 85	3.49 111	3.55 94	4.55 97	3.01 86	4.69 96	14.8 91	4.25 100	4.16 126	4.83 106	2.55 72	2.61 60	6.99 72	2.48 52
Dynamic MRF [7]	97.3	4.58 91	12.4 86	4.14 102	3.25 69	13.9 104	2.27 42	6.02 86	16.8 104	2.36 46	4.39 93	22.6 115	2.51 94	3.61 98	4.55 97	3.46 100	6.81 126	22.2 136	6.78 130	2.41 56	3.48 32	3.69 117	9.26 137	17.8 140	10.2 134
FlowNetS+ft+v [112]	98.7	4.22 74	12.1 84	3.48 84	4.50 102	13.4 100	3.85 102	8.29 116	18.4 115	6.20 107	4.87 102	21.6 109	3.01 102	3.93 117	5.04 126	3.47 103	3.71 59	15.3 100	3.21 60	3.32 102	5.12 117	3.87 119	3.76 84	9.44 97	3.74 87
SegOF [10]	98.8	5.85 112	13.5 98	3.98 98	7.40 120	14.9 111	8.13 127	8.55 118	17.3 108	9.01 115	6.50 123	18.1 81	5.14 125	3.90 116	4.53 94	4.81 133	6.57 125	21.7 134	6.81 131	1.65 5	3.49 34	1.08 4	3.71 83	9.23 94	3.63 81
ResPWCR_ROB [144]	98.9	7.29 122	16.3 120	6.15 123	4.28 97	11.4 74	3.95 103	5.85 82	13.6 75	5.20 103	4.75 100	17.5 77	3.50 112	3.80 110	4.53 94	4.12 124	4.96 105	15.0 93	4.81 111	3.52 109	5.22 124	2.40 65	3.61 81	6.77 69	4.27 100
LDOF [28]	99.2	4.60 92	13.0 95	3.77 95	4.67 104	15.5 117	3.67 98	5.63 80	14.0 77	4.21 99	5.80 117	27.1 133	3.43 110	3.52 92	4.50 92	3.46 100	4.84 101	17.8 116	4.04 91	2.46 62	4.14 81	3.25 107	4.85 111	12.0 121	3.78 89
Second-order prior [8]	100.0	4.03 63	11.6 78	3.35 69	3.88 89	14.0 106	3.08 92	7.21 98	17.6 110	3.57 89	4.14 90	19.9 93	2.31 88	3.66 100	4.86 115	2.73 78	7.32 129	21.2 132	6.76 129	4.02 122	4.58 101	4.01 121	4.27 94	10.4 108	5.12 107
WOLF_ROB [148]	101.1	5.79 111	16.6 123	4.49 110	7.62 121	21.2 135	5.10 113	9.70 121	21.0 125	5.66 106	5.32 114	19.0 83	3.78 117	3.61 98	4.49 90	3.54 106	4.63 92	13.6 78	4.34 104	2.30 51	3.89 70	2.16 58	4.37 96	7.52 84	6.03 120
AugFNG_ROB [143]	101.9	8.29 130	19.2 132	5.66 118	7.67 122	16.0 120	8.01 126	10.1 123	20.5 123	11.0 124	5.13 110	15.5 55	3.64 115	4.11 124	4.97 123	3.93 116	4.45 84	15.1 96	4.20 95	2.27 49	4.37 91	1.23 10	3.80 85	6.87 71	4.34 103
FlowNet2 [122]	105.0	8.58 133	18.6 128	6.31 124	9.39 131	17.6 124	9.09 132	8.06 109	15.8 95	9.81 118	5.61 116	16.2 68	4.12 119	4.04 120	4.88 117	3.79 113	4.92 102	16.2 107	4.50 106	4.28 130	6.73 143	2.84 85	2.05 42	4.54 41	1.41 18
StereoFlow [44]	105.3	17.1 150	28.1 150	17.9 149	18.7 147	29.7 148	16.5 142	20.1 147	30.9 146	17.5 142	21.2 147	38.3 149	17.9 145	4.60 134	5.05 128	5.52 135	2.38 4	11.5 51	1.77 2	1.25 1	2.92 2	0.71 1	4.49 102	10.3 107	4.23 98
EPMNet [133]	106.4	8.37 132	18.8 131	6.44 126	9.35 130	18.4 126	8.78 131	7.42 100	14.7 83	8.61 113	5.98 120	20.4 101	4.27 121	4.04 120	4.88 117	3.79 113	4.92 102	16.2 107	4.50 106	3.65 117	6.14 139	2.42 67	2.60 59	6.15 63	1.74 29
Ad-TV-NDC [36]	107.1	8.36 131	14.0 105	11.1 142	12.9 138	19.9 132	12.8 138	14.4 134	23.1 127	12.1 128	7.40 126	20.6 103	6.33 126	3.47 89	4.66 105	2.39 45	3.95 72	13.8 81	3.51 72	2.48 63	3.75 57	2.05 50	9.75 138	12.1 123	16.7 145
LFNet_ROB [149]	108.0	7.69 125	19.8 133	5.72 120	4.70 105	13.3 99	4.13 106	8.15 112	20.0 122	5.42 105	4.73 99	17.1 76	3.42 109	4.15 126	5.10 130	4.05 120	5.28 108	18.0 118	4.64 110	2.87 84	4.74 104	1.98 47	4.92 112	11.4 117	5.01 106
Shiralkar [42]	109.6	4.64 97	14.1 108	3.94 96	4.29 98	16.9 122	2.77 81	7.75 103	18.8 117	3.19 78	5.54 115	25.0 126	3.56 113	3.51 91	4.55 97	3.04 88	7.41 130	20.1 130	6.41 126	3.76 120	4.35 89	5.28 132	6.56 125	14.4 135	5.30 114
Learning Flow [11]	110.2	4.23 75	11.7 80	3.41 80	4.16 93	15.3 115	3.42 96	6.78 94	16.9 105	3.83 96	6.41 122	25.3 127	4.25 120	4.66 136	6.01 143	4.00 119	6.33 123	20.7 131	5.30 114	3.09 96	4.84 108	2.91 94	7.08 128	15.0 137	5.27 113
StereoOF-V1MT [119]	110.8	4.71 100	14.1 108	3.95 97	5.10 109	20.3 134	2.78 82	7.98 108	20.7 124	2.57 59	4.48 95	21.1 105	2.79 97	4.20 129	5.29 133	4.10 122	6.85 128	22.3 137	6.42 127	2.45 61	4.17 82	3.15 103	10.5 140	18.4 143	10.5 135
IAOF2 [51]	111.9	5.38 109	13.7 100	4.50 111	5.95 115	14.6 109	5.61 114	8.80 120	18.8 117	9.40 116	12.2 136	23.8 122	13.1 140	3.86 113	4.89 119	3.12 91	5.21 107	14.9 92	4.54 108	4.33 131	5.15 118	3.93 120	4.39 98	8.57 89	3.87 91
TVL1_ROB [138]	113.2	11.3 139	19.8 133	13.0 144	12.9 138	19.6 131	13.7 140	17.4 141	27.8 140	18.0 143	12.6 138	28.9 135	11.8 138	3.71 102	4.78 112	3.46 100	4.21 79	18.0 118	3.99 88	1.79 11	3.54 41	1.21 8	7.58 133	13.9 133	8.92 132
Modified CLG [34]	114.1	7.17 121	17.1 126	6.47 127	6.85 118	14.9 111	7.48 122	14.0 130	24.8 131	15.7 138	8.35 129	27.3 134	6.36 127	3.96 118	4.99 124	4.08 121	4.54 89	19.3 126	4.15 94	2.33 53	3.86 68	2.40 65	6.00 120	13.8 132	5.40 115
GraphCuts [14]	114.7	6.25 113	14.3 112	5.53 117	8.60 125	20.1 133	6.61 120	7.91 107	15.4 90	10.9 123	4.88 104	19.0 83	3.05 103	3.78 105	4.71 107	3.94 117	8.74 138	16.4 109	5.39 116	4.04 123	4.87 110	4.85 130	6.35 123	12.2 124	6.05 121
2D-CLG [1]	115.1	10.1 136	22.6 141	7.59 132	9.84 133	16.9 122	11.1 137	16.9 140	28.2 141	18.8 146	14.1 140	31.1 139	13.1 140	3.86 113	4.62 103	4.53 130	5.98 119	21.2 132	5.97 122	1.76 9	3.14 6	1.46 13	6.29 122	12.9 129	5.81 118
Filter Flow [19]	115.2	6.48 115	14.6 114	4.96 112	5.73 113	15.7 118	5.07 112	10.1 123	18.6 116	14.3 134	9.04 131	23.3 119	7.80 131	3.98 119	4.71 107	4.21 127	5.86 117	15.0 93	5.41 117	4.98 141	6.87 144	2.78 80	4.82 110	8.66 90	3.65 83
SPSA-learn [13]	115.9	6.84 120	16.7 124	6.74 128	8.47 124	19.4 129	7.49 123	12.5 126	23.1 127	13.1 132	8.40 130	25.8 130	7.08 129	3.87 115	4.66 105	4.10 122	6.32 121	18.8 122	6.89 132	2.56 66	3.85 66	1.79 27	7.29 130	12.5 126	7.47 127
HBpMotionGpu [43]	117.3	6.57 117	15.0 117	5.17 113	8.29 123	18.0 125	8.29 128	14.1 131	26.5 134	13.2 133	6.12 121	25.3 127	3.94 118	3.79 107	4.62 103	3.97 118	4.80 100	15.7 101	4.11 92	4.40 132	5.20 121	2.87 90	6.28 121	11.7 119	7.31 124
IAOF [50]	118.2	6.49 116	14.6 114	6.42 125	9.22 129	18.5 127	7.94 125	16.4 139	27.4 138	13.0 131	8.22 127	22.2 113	7.73 130	3.77 104	4.76 111	3.42 98	6.84 127	18.8 122	4.23 98	3.59 113	4.46 94	2.83 84	7.51 132	10.1 104	10.6 136
GroupFlow [9]	118.8	8.00 127	18.6 128	8.09 134	11.1 136	23.7 140	10.3 135	12.6 127	25.6 132	12.8 130	5.84 119	20.3 100	4.39 122	4.69 137	5.81 139	3.67 108	9.29 139	22.4 138	10.1 141	2.11 38	3.99 76	2.29 61	5.75 117	10.0 101	7.39 126
Black & Anandan [4]	119.3	6.81 119	15.4 118	7.43 130	8.77 127	19.5 130	7.35 121	13.0 128	22.9 126	12.5 129	8.29 128	26.1 131	6.77 128	4.18 128	5.28 132	3.69 110	6.19 120	20.0 129	5.34 115	3.63 114	5.05 115	1.79 27	6.45 124	12.2 124	5.17 110
BlockOverlap [61]	122.6	6.67 118	13.1 97	5.87 121	6.62 117	13.9 104	6.53 119	10.6 125	19.5 120	10.1 119	6.97 125	24.9 125	5.13 124	4.38 131	4.61 102	6.37 142	7.47 132	15.7 101	6.05 123	6.23 144	6.41 142	13.0 147	6.92 127	9.60 98	12.2 139
Nguyen [33]	123.1	7.88 126	16.8 125	7.02 129	13.4 140	19.0 128	15.3 141	17.6 142	28.9 142	17.2 141	12.0 135	26.9 132	11.6 137	4.38 131	5.07 129	5.58 138	5.69 115	19.7 128	5.93 121	2.75 78	4.02 78	1.91 43	6.59 126	12.5 126	6.52 123
UnFlow [129]	123.9	14.6 148	25.8 146	9.09 138	9.40 132	16.8 121	9.89 134	14.2 132	26.9 135	11.2 125	10.0 132	25.4 129	8.67 133	5.43 143	5.90 140	6.72 143	8.64 136	24.0 140	9.41 139	3.51 108	4.90 111	1.37 11	4.37 96	12.6 128	3.33 73
2bit-BM-tele [98]	124.6	8.00 127	15.8 119	8.40 136	4.91 108	13.4 100	4.67 109	8.14 110	19.0 119	5.12 102	6.62 124	23.5 121	5.04 123	4.08 122	4.78 112	4.61 132	8.68 137	18.8 122	8.31 135	6.46 146	7.08 146	9.47 143	7.36 131	14.1 134	9.62 133
Horn & Schunck [3]	129.6	8.01 129	19.9 135	8.38 135	9.13 128	23.2 139	7.71 124	14.2 132	25.9 133	14.6 136	12.4 137	30.6 137	11.3 136	4.64 135	5.64 135	4.60 131	8.21 135	24.4 141	8.45 136	4.01 121	5.41 126	1.95 45	9.16 136	17.5 138	8.86 131
SILK [79]	131.1	9.34 135	20.4 136	10.5 141	10.4 134	21.9 136	10.3 135	16.0 138	27.5 139	14.5 135	10.3 133	29.0 136	8.54 132	4.81 138	5.65 136	5.56 137	9.41 140	25.4 143	8.74 137	2.79 81	3.68 55	4.62 128	10.9 141	17.8 140	12.3 140
Heeger++ [104]	132.7	11.9 142	21.8 139	8.08 133	12.5 137	29.7 148	9.42 133	14.8 135	27.1 136	9.68 117	14.3 141	31.0 138	12.7 139	4.98 140	5.74 137	4.97 134	17.5 148	34.1 149	18.4 148	2.75 78	5.44 127	2.15 55	12.3 143	18.8 144	14.8 143
TI-DOFE [24]	133.6	13.4 146	23.2 142	16.5 148	16.5 144	24.1 141	18.2 146	20.2 148	31.1 148	20.6 147	19.9 146	32.9 142	20.8 147	4.89 139	5.90 140	5.54 136	8.04 134	23.9 139	8.81 138	2.97 89	4.34 88	1.88 40	10.9 141	17.7 139	11.9 138
H+S_ROB [137]	135.0	13.0 144	27.1 149	9.66 139	13.4 140	24.8 143	13.4 139	18.7 146	30.9 146	18.3 145	25.8 150	35.7 146	26.4 149	7.08 148	8.13 148	9.10 147	14.6 146	31.3 148	16.3 146	2.17 40	4.44 93	2.11 53	15.1 147	19.9 146	14.2 142
HCIC-L [99]	137.9	15.7 149	22.0 140	10.1 140	31.5 150	26.6 146	41.0 150	14.8 135	23.1 127	16.8 140	18.4 145	34.4 144	18.2 146	5.94 144	6.35 144	6.35 141	10.6 143	19.2 125	11.4 143	18.7 150	17.8 150	19.2 149	4.93 113	8.34 87	5.16 108
SLK [47]	137.9	11.6 140	26.0 147	14.6 147	15.3 143	25.0 144	17.5 144	17.8 144	30.1 145	18.1 144	25.4 149	33.6 143	28.0 150	5.25 141	5.90 140	7.03 144	10.3 142	27.4 145	10.6 142	2.89 86	4.47 95	2.94 96	14.9 146	20.7 147	18.8 146
FFV1MT [106]	138.9	12.0 143	23.3 143	8.83 137	10.7 135	26.6 146	8.71 130	15.6 137	29.0 143	12.0 127	16.6 144	36.3 148	15.5 143	6.51 147	6.40 145	10.4 148	16.2 147	30.7 147	17.7 147	3.41 106	5.44 127	3.35 113	12.3 143	18.8 144	14.8 143
Adaptive flow [45]	140.9	13.2 145	20.8 137	14.0 146	17.1 146	22.0 137	17.9 145	18.1 145	27.1 136	22.8 149	11.8 134	31.1 139	10.5 134	6.35 146	7.13 147	6.25 140	9.87 141	21.8 135	9.44 140	12.6 149	11.4 149	20.0 150	7.75 134	13.6 130	7.73 128
PGAM+LK [55]	142.2	11.8 141	25.6 144	13.9 145	14.8 142	24.4 142	16.7 143	13.2 129	24.0 130	15.0 137	16.2 143	41.2 150	15.3 142	5.40 142	5.45 134	8.10 145	12.3 145	26.5 144	12.1 144	7.42 147	8.24 148	7.87 141	13.2 145	18.3 142	19.4 147
Periodicity [78]	143.0	11.2 138	27.0 148	7.46 131	16.6 145	29.8 150	18.2 146	25.3 150	31.2 150	24.9 150	12.7 139	35.7 146	11.1 135	31.7 150	41.4 150	25.1 150	23.8 150	41.5 150	23.8 150	2.92 87	5.62 131	6.90 139	18.6 149	33.1 150	22.3 148
FOLKI [16]	143.8	10.5 137	25.6 144	11.9 143	20.9 148	26.2 145	26.1 148	17.6 142	31.1 148	16.5 139	15.4 142	32.6 141	16.0 144	6.16 145	6.53 146	9.07 146	12.2 144	29.7 146	13.0 145	4.67 137	5.83 135	9.41 142	18.2 148	22.8 148	25.1 149
Pyramid LK [2]	146.8	13.9 147	20.9 138	21.4 150	24.1 149	23.1 138	30.2 149	20.9 149	29.5 144	21.9 148	22.2 148	34.6 145	25.0 148	18.7 149	23.1 149	20.2 149	21.2 149	24.5 142	21.0 149	6.41 145	7.02 145	10.8 145	25.6 150	31.5 149	34.5 150
AdaConv-v1 [126]	151.4	39.2 151	39.9 151	41.8 151	73.0 151	74.5 151	71.1 151	70.1 151	67.3 151	71.8 151	64.4 151	66.2 151	65.9 151	76.5 152	78.1 152	72.0 152	68.2 152	64.9 152	66.5 152	52.3 152	45.1 152	70.9 152	81.8 151	81.6 151	82.3 151
SepConv-v1 [127]	151.4	39.2 151	39.9 151	41.8 151	73.0 151	74.5 151	71.1 151	70.1 151	67.3 151	71.8 151	64.4 151	66.2 151	65.9 151	76.5 152	78.1 152	72.0 152	68.2 152	64.9 152	66.5 152	52.3 152	45.1 152	70.9 152	81.8 151	81.6 151	82.3 151
SuperSlomo [132]	151.4	39.2 151	39.9 151	41.8 151	73.0 151	74.5 151	71.1 151	70.1 151	67.3 151	71.8 151	64.4 151	66.2 151	65.9 151	76.5 152	78.1 152	72.0 152	68.2 152	64.9 152	66.5 152	52.3 152	45.1 152	70.9 152	81.8 151	81.6 151	82.3 151
CtxSyn [136]	151.4	39.2 151	39.9 151	41.8 151	73.0 151	74.5 151	71.1 151	70.1 151	67.3 151	71.8 151	64.4 151	66.2 151	65.9 151	76.5 152	78.1 152	72.0 152	68.2 152	64.9 152	66.5 152	52.3 152	45.1 152	70.9 152	81.8 151	81.6 151	82.3 151
CyclicGen [153]	151.4	39.2 151	39.9 151	41.8 151	73.0 151	74.5 151	71.1 151	70.1 151	67.3 151	71.8 151	64.4 151	66.2 151	65.9 151	76.5 152	78.1 152	72.0 152	68.2 152	64.9 152	66.5 152	52.3 152	45.1 152	70.9 152	81.8 151	81.6 151	82.3 151
TOF-M [154]	151.4	39.2 151	39.9 151	41.8 151	73.0 151	74.5 151	71.1 151	70.1 151	67.3 151	71.8 151	64.4 151	66.2 151	65.9 151	76.5 152	78.1 152	72.0 152	68.2 152	64.9 152	66.5 152	52.3 152	45.1 152	70.9 152	81.8 151	81.6 151	82.3 151
MEMC-Net+ [155]	151.4	39.2 151	39.9 151	41.8 151	73.0 151	74.5 151	71.1 151	70.1 151	67.3 151	71.8 151	64.4 151	66.2 151	65.9 151	76.5 152	78.1 152	72.0 152	68.2 152	64.9 152	66.5 152	52.3 152	45.1 152	70.9 152	81.8 151	81.6 151	82.3 151
MPRN [156]	151.4	39.2 151	39.9 151	41.8 151	73.0 151	74.5 151	71.1 151	70.1 151	67.3 151	71.8 151	64.4 151	66.2 151	65.9 151	76.5 152	78.1 152	72.0 152	68.2 152	64.9 152	66.5 152	52.3 152	45.1 152	70.9 152	81.8 151	81.6 151	82.3 151
DAIN [157]	151.4	39.2 151	39.9 151	41.8 151	73.0 151	74.5 151	71.1 151	70.1 151	67.3 151	71.8 151	64.4 151	66.2 151	65.9 151	76.5 152	78.1 152	72.0 152	68.2 152	64.9 152	66.5 152	52.3 152	45.1 152	70.9 152	81.8 151	81.6 151	82.3 151
InterpCNN [158]	151.4	39.2 151	39.9 151	41.8 151	73.0 151	74.5 151	71.1 151	70.1 151	67.3 151	71.8 151	64.4 151	66.2 151	65.9 151	76.5 152	78.1 152	72.0 152	68.2 152	64.9 152	66.5 152	52.3 152	45.1 152	70.9 152	81.8 151	81.6 151	82.3 151
OFRI [159]	151.4	39.2 151	39.9 151	41.8 151	73.0 151	74.5 151	71.1 151	70.1 151	67.3 151	71.8 151	64.4 151	66.2 151	65.9 151	76.5 152	78.1 152	72.0 152	68.2 152	64.9 152	66.5 152	52.3 152	45.1 152	70.9 152	81.8 151	81.6 151	82.3 151
PyrWarp [162]	151.4	39.2 151	39.9 151	41.8 151	73.0 151	74.5 151	71.1 151	70.1 151	67.3 151	71.8 151	64.4 151	66.2 151	65.9 151	76.5 152	78.1 152	72.0 152	68.2 152	64.9 152	66.5 152	52.3 152	45.1 152	70.9 152	81.8 151	81.6 151	82.3 151
FGME [164]	151.4	39.2 151	39.9 151	41.8 151	73.0 151	74.5 151	71.1 151	70.1 151	67.3 151	71.8 151	64.4 151	66.2 151	65.9 151	76.5 152	78.1 152	72.0 152	68.2 152	64.9 152	66.5 152	52.3 152	45.1 152	70.9 152	81.8 151	81.6 151	82.3 151
AVG_FLOW_ROB [141]	159.1	62.1 164	56.6 164	61.5 164	99.9 164	96.7 164	99.9 164	81.2 164	81.9 164	80.3 164	65.8 164	68.9 164	67.4 164	68.4 151	75.2 151	67.5 151	62.4 151	55.3 151	59.6 151	31.5 151	28.0 151	29.3 151	86.1 164	96.7 164	87.2 164

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] CtxSyn	0.07	2	color	S. Niklaus and F. Liu. (Interpolation results only.) Context-aware synthesis for video frame interpolation. CVPR 2018.
[137] H+S_ROB	5	2	color	ROB 2018 baseline submission, based on: E. Meinhardt-Llopis, J. Sanchez, and D. Kondermann. Horn-Schunck optical flow with a multi-scale strategy. Image Processing On Line 3:151–172, 2013.
[138] TVL1_ROB	1	2	color	ROB 2018 baseline submission, based on: J. Sanchez, E. Meinhardt-Llopis, and G. Facciolo. TV-L1 optical flow estimation. Image Processing On Line 3:137-150, 2013.
[139] DMF_ROB	10	2	color	ROB 2018 baseline submission, based on: P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013.
[140] JOF	657	2	gray	C. Zhang, L. Ge, Z. Chen, M. Li, W. Liu, and H. Chen. Refined TV-L1 optical flow estimation using joint filtering. Submitted to IEEE TMM, 2018.
[141] AVG_FLOW_ROB	N/A	2	N/A	Average flow field of ROB 2018 training set.
[142] LiteFlowNet	0.06	2	color	T.-W. Hui, X. Tang, and C. C. Loy. LiteFlowNet: A lightweight convolutional neural network for optical flow estimation. CVPR 2018.
[143] AugFNG_ROB	0.10	all	color	Anonymous. FusionNet and AugmentedFlowNet: Selective proxy ground truth for training on unlabeled images. ECCV 2018 submission 2834.
[144] ResPWCR_ROB	0.2	2	color	Anonymous. Learning optical flow with residual connections. ROB 2018 submission.
[145] FF++_ROB	17.43	2	color	R. Schuster, C. Bailer, O. Wasenmueller, D. Stricker. FlowFields++: Accurate optical flow correspondences meet robust interpolation. ICIP 2018. Submitted to ROB 2018.
[146] ProFlow_ROB	76	3	color	Anonymous. ProFlow: Learning to predict optical flow. BMVC 2018 submission 277.
[147] PWC-Net_ROB	0.069	2	color	D. Sun, X. Yang, M.-Y. Liu, and J. Kautz. PWC-Net: CNNs for optical flow using pyramid, warping, and cost volume. CVPR 2018.
[148] WOLF_ROB	0.02	2	color	Anonymous. Reversed deep neural network for optical flow. ROB 2018 submission.
[149] LFNet_ROB	0.068	2	color	Anonymous. Learning a flow network. ROB 2018 submission.
[150] WRT	9	2	color	L. Mei, J. Lai, X. Xie, J. Zhu, and J. Chen. Illumination-invariance optical flow estimation using weighted regularization transform. Submitted to IEEE TCSVT 2018.
[151] EAI-Flow	2.1	2	color	Anonymous. Hierarchical coherency sensitive hashing and interpolation with RANSAC for large displacement optical flow. CVIU 2018 submission 17-678.
[152] ContinualFlow_ROB	0.5	all	color	M Neoral, J. Sochman, and J. Matas. Continual occlusions and optical flow estimation. ACCV 2018.
[153] CyclicGen	0.088	2	color	Anonymous. (Interpolation results only.) Deep video frame interpolation using cyclic frame generation. AAAI 2019 submission 323.
[154] TOF-M	0.393	2	color	T. Xue, B. Chen, J. Wu, D. Wei, and W. Freeman. Video enhancement with task-oriented flow. arXiv 1711.09078, 2017.
[155] MEMC-Net+	0.16	2	color	W. Bao, W.-S. Lai, X. Zhang, Z. Gao, and M.-H. Yang. (Interpolation results only.) MEMC-Net: Motion estimation and motion compensation driven neural network for video interpolation and enhancement. Submitted to TPAMI 2018.
[156] MPRN	0.32	4	color	Anonymous. (Interpolation results only.) Multi-frame pyramid refinement network for video frame interpolation. CVPR 2019 submission 1361.
[157] DAIN	0.13	2	color	Anonymous. (Interpolation results only.) DAIN: Depth-aware video frame interpolation. CVPR 2019 submission 1769.
[158] InterpCNN	0.65	2	color	Anonymous. (Interpolation results only.) Video frame interpolation with a stack of synthesis networks and intermediate optical flows. CVPR 2019 submission 6533.
[159] OFRI	0.31	2	color	Anonymous. (Interpolation results only.) Efficient video frame interpolation via optical flow refinement. CVPR 2019 submission 6743.
[160] CompactFlow_ROB	0.05	2	color	Anonymous. CompactFlow: spatially shiftable window revisited. CVPR 2019 submission 1387.
[161] SegFlow	3.2	2	color	J. Chen, Z. Cai, J. Lai, and X. Xie. Efficient segmentation-based PatchMatch for large displacement optical flow estimation. IEEE TCSVT 2018.
[162] PyrWarp	0.14	2	color	Anonymous. (Interpolation results only.) Video frame interpolation using differentiable forward-warping of feature pyramids. ICCV 2019 submission 741.
[163] HCFN	0.18	2	color	Anonymous. Practical coarse-to-fine optical flow with deep networks. ICCV 2019 submission 116.
[164] FGME	0.23	2	color	Anonymous. (Interpolation results only.) Fine-grained motion estimation for video frame interpolation. ICCV 2019 submission 4327.

* 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.