Optical flow evaluation results: A75 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

A75 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
RAFT-it+_RVC [198]	3.7	2.35 10	5.14 3	1.49 1	1.33 2	3.88 1	1.41 2	1.30 2	2.55 2	1.45 5	0.66 1	1.28 1	0.59 1	2.09 4	3.03 2	1.39 3	0.89 1	2.36 1	0.90 1	1.38 1	3.15 2	0.80 2	0.91 23	1.37 9	0.74 8
RAFT-it [194]	8.3	2.52 14	5.72 11	1.88 7	1.45 5	4.36 3	1.49 4	1.33 3	2.75 4	1.41 2	0.77 2	1.42 2	0.64 2	2.50 9	3.71 11	1.43 4	1.16 4	2.74 3	1.13 3	1.54 4	4.78 67	0.78 1	0.88 13	1.35 8	0.84 14
MS_RAFT+_RVC [195]	13.6	2.61 19	5.14 3	1.61 3	2.45 77	4.73 6	2.84 97	1.47 9	2.80 5	1.72 20	0.84 4	1.72 3	0.71 6	2.00 1	3.01 1	1.25 1	1.07 3	2.58 2	1.20 4	1.48 2	3.08 1	1.19 8	0.95 33	1.28 4	0.85 15
NNF-Local [75]	19.9	2.17 4	5.35 7	1.92 8	1.56 8	6.39 25	1.67 13	1.51 10	3.67 12	1.61 11	1.20 39	4.36 22	1.02 41	2.30 6	3.18 5	1.73 10	2.16 46	6.35 13	2.39 72	2.54 34	4.18 16	2.17 41	0.81 9	1.50 21	0.67 4
NN-field [71]	21.4	2.31 8	5.94 16	1.98 9	1.83 27	7.21 45	1.97 34	1.54 12	3.55 10	1.68 18	0.96 13	3.04 8	0.75 9	2.30 6	3.25 6	1.69 8	1.72 23	3.81 4	1.65 11	3.12 71	4.76 65	2.60 70	0.79 7	1.58 31	0.59 2
TC/T-Flow [77]	24.6	2.06 1	7.42 34	1.55 2	1.61 14	6.77 34	1.52 6	1.46 7	4.33 25	1.56 8	0.88 6	6.96 54	0.69 4	2.91 23	4.35 34	1.88 14	1.47 8	6.12 12	1.61 10	2.22 14	3.98 6	4.00 116	1.06 45	1.99 54	1.19 60
ProFlow_ROB [142]	25.0	2.44 12	7.85 43	2.01 10	1.54 6	7.07 39	1.55 7	1.53 11	7.16 64	1.43 3	0.81 3	5.26 33	0.67 3	3.48 51	4.95 57	1.69 8	1.46 7	8.54 42	1.53 7	1.92 8	4.48 38	2.01 31	0.93 28	2.14 60	0.94 30
ComponentFusion [94]	25.2	2.12 3	6.18 18	1.80 5	1.67 19	4.82 8	1.91 29	1.34 4	4.01 16	1.47 6	0.88 6	4.74 26	0.72 7	2.99 27	4.35 34	1.96 17	2.03 37	11.2 89	1.96 32	2.90 60	4.62 58	1.90 26	0.93 28	1.56 30	0.89 20
RAFT-TF_RVC [179]	28.4	3.13 47	8.58 58	1.87 6	2.05 42	5.71 17	2.07 38	1.81 45	4.53 29	1.89 33	0.98 15	2.13 4	0.85 21	2.99 27	4.30 27	2.05 21	1.55 10	4.60 5	1.60 8	1.53 3	4.72 64	1.15 7	1.13 55	1.97 52	1.02 48
ALD-Flow [66]	28.5	2.26 6	5.81 13	2.07 11	1.56 8	5.71 17	1.66 11	1.46 7	4.64 32	1.66 16	0.95 12	7.15 58	0.80 15	3.18 41	4.57 45	1.76 11	1.51 9	7.63 28	1.60 8	2.61 37	4.27 22	3.90 112	1.04 42	2.22 67	1.18 57
WLIF-Flow [91]	28.6	2.63 23	5.51 8	2.41 22	2.14 50	7.08 40	2.32 50	1.63 16	4.19 19	1.84 26	1.05 20	4.21 19	0.88 28	2.92 25	4.37 36	2.30 37	2.02 36	7.21 23	1.89 28	2.73 47	4.27 22	2.78 79	0.84 11	1.37 9	0.83 13
nLayers [57]	29.6	2.33 9	5.14 3	2.17 14	2.75 101	7.22 47	3.07 104	1.69 27	4.04 17	2.21 71	0.88 6	2.83 6	0.70 5	2.08 3	3.25 6	1.30 2	1.88 27	6.06 11	1.85 18	2.89 59	4.59 52	2.28 48	0.92 25	1.48 19	0.94 30
OFLAF [78]	30.3	2.77 38	5.70 10	2.49 25	1.76 22	5.35 14	1.84 26	1.54 12	2.69 3	1.72 20	1.30 46	3.55 15	1.12 57	2.30 6	3.62 9	1.64 7	2.23 52	5.93 8	2.06 42	2.81 53	4.29 25	2.99 85	1.15 59	1.69 36	1.18 57
MDP-Flow2 [68]	30.8	3.08 46	6.23 19	2.73 55	1.55 7	4.80 7	1.64 10	1.63 16	3.27 7	1.61 11	1.37 59	5.15 31	1.15 64	2.91 23	4.19 23	2.20 25	2.24 54	6.43 14	2.17 56	2.62 38	4.35 30	1.88 25	1.08 48	1.66 35	0.95 36
RNLOD-Flow [119]	31.5	2.19 5	4.96 2	2.19 15	1.79 24	7.20 44	1.76 20	1.42 5	4.31 23	1.56 8	0.97 14	3.42 14	0.84 20	2.75 18	4.16 20	2.01 19	1.86 26	7.24 24	1.95 31	4.02 110	6.41 126	4.48 131	0.90 19	1.51 22	0.85 15
OAR-Flow [123]	33.2	2.55 16	7.57 36	2.36 19	1.81 25	7.94 53	1.94 33	1.72 34	8.40 71	1.95 35	0.94 11	5.90 44	0.79 12	3.49 53	4.83 54	1.84 13	1.16 4	7.84 33	1.22 5	1.93 9	3.63 3	2.26 45	1.10 51	2.16 63	1.34 74
AGIF+OF [84]	34.1	2.60 17	6.24 20	2.45 23	2.49 79	9.30 77	2.63 78	1.68 25	4.79 38	2.08 56	1.05 20	4.34 21	0.81 16	2.77 20	4.05 17	2.10 23	1.92 30	7.48 26	1.74 16	2.69 43	4.48 38	2.69 76	0.87 12	1.40 11	0.95 36
Layers++ [37]	34.5	2.70 34	6.40 22	2.83 62	2.33 67	6.62 31	2.54 74	1.65 21	3.24 6	2.02 45	0.92 9	2.48 5	0.75 9	2.12 5	3.11 3	1.50 6	2.06 40	8.25 36	1.94 30	3.59 95	5.41 95	3.21 88	0.89 16	1.32 6	0.90 23
CoT-AMFlow [174]	34.8	3.03 42	6.45 23	2.72 53	1.64 18	5.17 10	1.80 22	1.63 16	3.56 11	1.66 16	1.34 49	5.43 37	1.12 57	3.03 30	4.20 24	2.52 52	2.18 49	6.96 19	2.15 52	2.78 50	4.53 44	2.29 49	1.06 45	1.69 36	0.94 30
LME [70]	35.8	2.90 40	5.83 14	2.30 18	1.60 11	4.45 4	1.74 19	1.71 31	4.14 18	2.00 41	1.35 53	6.61 49	1.13 59	3.07 34	4.32 32	2.57 55	2.08 43	8.09 35	2.00 38	2.78 50	4.53 44	2.29 49	1.06 45	1.74 38	0.96 40
HAST [107]	36.4	2.09 2	4.28 1	1.69 4	1.60 11	5.31 13	1.55 7	1.28 1	2.09 1	1.40 1	0.92 9	3.39 12	0.78 11	2.01 2	3.14 4	1.48 5	2.40 68	8.62 44	2.41 74	4.08 112	7.33 148	7.69 151	1.23 66	1.59 33	1.73 93
TC-Flow [46]	37.3	2.45 13	6.60 25	2.39 21	1.25 1	5.24 11	1.32 1	1.45 6	4.40 28	1.50 7	1.15 36	8.13 67	1.04 43	3.22 42	4.77 52	2.06 22	1.94 31	8.65 45	2.09 46	2.33 27	4.51 41	3.82 110	1.24 67	2.18 65	1.50 88
PH-Flow [99]	39.0	2.62 20	7.58 38	2.53 32	2.13 48	8.78 63	2.37 54	1.70 28	4.39 27	2.06 52	1.08 23	7.06 57	0.85 21	2.72 15	3.91 14	2.04 20	2.06 40	8.33 37	1.96 32	3.48 89	4.62 58	4.03 117	0.90 19	1.41 14	0.88 18
NNF-EAC [101]	39.3	3.07 44	6.73 27	2.70 52	1.62 17	5.30 12	1.72 17	1.71 31	3.89 15	1.79 23	1.36 56	6.36 48	1.15 64	3.02 29	4.37 36	2.28 35	2.44 71	6.90 18	2.28 66	2.90 60	4.51 41	2.19 42	1.12 53	1.83 44	0.98 42
Classic+CPF [82]	39.6	2.65 29	7.22 32	2.53 32	2.37 69	9.14 74	2.51 71	1.67 24	5.05 42	2.03 47	1.01 16	5.38 35	0.79 12	2.90 22	4.17 21	2.33 41	1.88 27	8.44 39	1.70 13	3.19 74	4.60 55	3.72 103	0.92 25	1.40 11	0.95 36
FC-2Layers-FF [74]	39.8	2.63 23	5.87 15	2.68 50	2.19 60	8.07 55	2.39 58	1.65 21	3.42 8	2.05 49	1.10 28	3.11 9	0.88 28	2.57 10	3.49 8	2.30 37	2.26 57	7.68 30	2.17 56	3.70 98	5.18 89	3.73 104	0.90 19	1.41 14	0.93 28
IROF++ [58]	39.9	2.66 30	6.82 28	2.58 40	2.17 54	9.07 71	2.41 60	1.75 40	5.03 41	2.06 52	1.11 30	7.65 61	0.90 34	2.92 25	4.18 22	2.25 32	2.13 44	9.85 67	1.98 35	2.53 33	4.53 44	1.43 14	0.97 39	1.58 31	0.94 30
Sparse-NonSparse [56]	39.9	2.62 20	7.58 38	2.60 42	2.18 56	8.74 61	2.46 67	1.68 25	4.86 39	2.00 41	1.04 18	7.97 65	0.81 16	3.13 38	4.45 40	2.42 47	1.98 34	8.53 41	1.87 22	3.13 72	4.32 29	3.51 96	0.88 13	1.41 14	0.91 24
JOF [136]	42.6	2.52 14	6.01 17	2.37 20	2.40 73	9.13 73	2.66 80	1.63 16	3.82 14	2.17 69	1.02 17	5.46 39	0.79 12	2.69 14	3.93 15	2.24 29	2.16 46	8.05 34	2.20 58	3.97 108	5.74 109	5.45 137	0.82 10	1.33 7	0.82 12
UnDAF [187]	42.6	3.07 44	7.26 33	2.72 53	1.61 14	5.77 19	1.71 16	1.66 23	4.22 20	1.63 13	1.37 59	7.83 63	1.13 59	3.07 34	4.30 27	2.30 37	2.32 61	9.86 68	2.15 52	2.79 52	4.54 48	2.26 45	1.14 58	2.85 95	0.94 30
FESL [72]	42.9	2.63 23	5.15 6	2.77 59	2.62 94	9.27 76	2.73 85	1.72 34	4.77 36	2.07 55	1.15 36	3.36 11	0.98 39	2.75 18	3.93 15	2.20 25	1.95 32	7.12 21	1.98 35	3.40 84	5.71 108	2.89 81	0.88 13	1.55 27	0.87 17
COFM [59]	43.7	2.28 7	7.19 30	2.08 13	1.78 23	6.57 28	1.93 31	1.56 15	5.33 47	2.19 70	0.86 5	4.90 27	0.73 8	3.76 64	4.80 53	3.87 108	2.03 37	7.67 29	1.72 14	2.76 48	4.21 18	4.04 119	1.62 100	1.87 46	2.04 108
Efficient-NL [60]	44.1	2.38 11	5.67 9	2.07 11	2.45 77	8.54 58	2.55 75	1.64 20	4.63 31	1.95 35	1.04 18	5.76 42	0.81 16	2.74 16	4.14 19	1.94 16	2.87 88	8.58 43	2.23 60	3.30 79	5.12 86	3.05 86	1.15 59	1.83 44	1.19 60
PMMST [112]	44.8	3.55 71	6.48 24	3.33 82	2.18 56	6.49 27	2.47 70	1.93 53	4.28 21	2.09 57	1.60 81	2.84 7	1.43 90	2.60 11	3.72 12	1.91 15	2.22 51	6.05 10	2.13 51	2.70 45	4.48 38	2.08 36	1.18 65	1.91 48	1.09 53
LSM [39]	45.5	2.60 17	7.70 42	2.61 44	2.19 60	8.77 62	2.44 65	1.70 28	4.78 37	2.06 52	1.08 23	8.13 67	0.86 24	3.05 32	4.30 27	2.47 48	2.18 49	8.66 48	2.08 44	3.56 92	4.68 63	3.74 105	0.90 19	1.43 17	0.93 28
Classic+NL [31]	47.1	2.63 23	7.57 36	2.64 47	2.18 56	9.04 69	2.41 60	1.71 31	4.70 33	2.09 57	1.08 23	7.69 62	0.88 28	3.04 31	4.31 30	2.41 46	2.27 58	8.65 45	2.09 46	3.79 102	5.12 86	3.81 108	0.89 16	1.44 18	0.89 20
FMOF [92]	47.2	2.71 36	6.71 26	2.62 46	2.64 95	9.19 75	2.77 86	1.73 37	4.37 26	2.22 72	1.06 22	5.18 32	0.81 16	2.89 21	4.25 26	2.40 45	2.31 60	7.76 32	1.96 32	3.35 82	4.88 78	3.81 108	0.93 28	1.55 27	0.92 26
Ramp [62]	47.4	2.64 28	7.64 41	2.56 36	2.20 63	8.90 66	2.46 67	1.73 37	4.74 35	2.09 57	1.11 30	6.81 53	0.88 28	3.07 34	4.46 41	2.38 44	2.28 59	8.52 40	2.15 52	3.40 84	4.25 19	4.16 127	0.94 31	1.53 24	0.97 41
PRAFlow_RVC [177]	48.6	4.04 98	9.30 64	2.91 67	3.03 108	8.22 56	3.10 105	2.43 81	6.50 60	2.65 90	1.29 44	3.33 10	1.06 44	3.28 44	4.32 32	2.30 37	2.07 42	4.95 6	2.15 52	1.91 7	4.55 49	0.82 3	0.96 36	1.54 25	0.73 7
ProbFlowFields [126]	49.1	3.31 58	13.8 96	2.85 64	2.03 38	6.67 33	2.23 45	1.89 51	6.06 53	2.29 76	1.23 42	5.14 30	0.95 37	3.70 60	5.08 60	2.29 36	1.60 14	7.44 25	1.85 18	2.43 32	4.30 26	2.45 63	1.29 72	2.32 71	1.38 78
2DHMM-SAS [90]	50.6	2.62 20	7.61 40	2.53 32	2.17 54	10.1 87	2.38 56	1.83 46	6.16 56	2.10 61	1.09 26	8.07 66	0.86 24	3.06 33	4.42 39	2.37 43	2.16 46	9.30 56	2.01 39	3.50 90	4.64 60	4.14 126	0.96 36	1.64 34	0.99 45
SVFilterOh [109]	51.1	3.48 67	5.72 11	3.45 88	2.38 71	6.06 22	2.41 60	1.93 53	3.46 9	2.05 49	1.53 77	3.71 16	1.27 77	2.65 13	4.10 18	2.00 18	2.47 73	7.08 20	2.28 66	4.60 123	7.10 141	5.92 142	0.73 4	1.16 2	0.70 6
Adaptive [20]	51.1	2.63 23	8.08 48	2.23 16	2.18 56	8.66 60	2.27 48	2.04 62	9.57 79	2.09 57	1.12 33	10.6 88	0.87 26	4.47 112	5.30 79	4.44 124	1.55 10	8.65 45	1.43 6	3.32 80	5.51 97	2.14 40	0.77 5	1.52 23	0.75 10
PMF [73]	52.3	3.22 55	6.34 21	2.60 42	1.95 34	6.66 32	1.92 30	1.85 47	4.58 30	1.83 25	1.62 82	4.27 20	1.37 84	2.61 12	3.74 13	1.83 12	3.18 97	9.94 71	3.34 103	5.29 140	8.26 155	5.58 141	0.68 3	1.21 3	0.67 4
TV-L1-MCT [64]	53.2	2.68 32	6.83 29	2.61 44	2.68 96	10.3 90	2.80 90	1.78 43	5.24 44	2.24 73	1.13 34	5.44 38	0.87 26	3.39 49	4.69 50	2.96 77	2.45 72	9.14 53	2.31 70	2.64 40	4.37 32	2.04 33	1.08 48	1.74 38	1.36 76
S2D-Matching [83]	53.4	2.69 33	7.86 45	2.68 50	2.19 60	9.11 72	2.44 65	1.77 42	6.11 55	2.04 48	1.13 34	5.86 43	0.91 35	3.17 40	4.41 38	2.50 50	2.41 69	9.09 52	2.25 64	4.00 109	5.16 88	4.07 120	0.91 23	1.40 11	0.95 36
SimpleFlow [49]	55.2	2.74 37	8.28 53	2.73 55	2.50 80	9.73 85	2.83 96	1.89 51	6.81 62	2.35 79	1.11 30	10.4 85	0.89 33	3.27 43	4.47 42	2.63 58	3.03 91	8.91 51	2.39 72	3.10 70	4.25 19	2.76 78	0.89 16	1.49 20	0.89 20
IROF-TV [53]	56.0	2.89 39	8.67 59	2.81 61	2.25 65	9.54 83	2.51 71	1.79 44	5.50 49	2.15 66	1.53 77	11.5 96	1.27 77	3.33 45	4.62 46	2.85 67	2.78 83	13.5 112	2.57 79	2.15 11	4.14 14	1.37 13	0.94 31	1.55 27	0.94 30
Occlusion-TV-L1 [63]	56.0	3.15 49	8.42 55	2.50 26	2.03 38	7.42 49	2.14 42	2.24 73	9.79 81	2.16 67	1.35 53	9.59 76	1.11 53	4.10 90	5.77 109	3.22 88	1.68 22	9.21 55	2.08 44	2.69 43	4.59 52	1.70 21	1.05 43	2.36 74	0.98 42
PBOFVI [189]	57.1	4.11 100	8.18 51	3.41 87	2.04 40	7.12 41	2.02 36	1.75 40	3.81 13	1.65 14	1.51 74	3.84 17	1.16 67	3.65 56	5.10 63	2.59 57	2.58 77	8.83 50	2.91 91	3.02 66	4.53 44	4.11 122	1.12 53	1.91 48	1.21 63
MDP-Flow [26]	57.7	3.14 48	9.81 68	2.83 62	2.06 43	6.10 23	2.43 63	1.87 49	6.10 54	2.10 61	1.44 65	8.90 72	1.15 64	3.37 47	4.62 46	2.54 54	2.35 64	10.4 77	2.23 60	2.88 58	4.83 71	1.94 29	1.27 71	2.62 82	1.09 53
Correlation Flow [76]	58.0	3.18 51	7.85 43	2.85 64	1.74 20	5.77 19	1.69 15	1.94 55	5.25 45	1.70 19	1.47 69	5.67 41	1.26 75	3.66 57	5.20 72	2.53 53	3.06 93	9.57 60	3.10 97	3.42 87	4.94 81	4.03 117	1.17 63	1.80 41	1.16 55
3DFlow [133]	58.3	3.21 53	7.43 35	2.64 47	1.92 32	7.04 36	1.85 27	2.03 61	4.31 23	1.84 26	1.65 88	3.41 13	1.33 80	3.14 39	4.51 43	2.24 29	3.66 105	11.8 96	3.87 118	4.19 115	4.93 80	5.46 138	1.05 43	1.54 25	1.02 48
AggregFlow [95]	60.2	3.29 57	8.49 56	3.14 75	2.70 98	12.2 110	2.68 82	2.32 77	9.03 73	2.88 99	1.44 65	4.19 18	1.25 74	3.48 51	5.09 61	2.19 24	1.55 10	5.36 7	1.68 12	2.56 36	4.78 67	1.77 23	1.54 96	2.15 61	2.16 114
HCFN [157]	61.0	2.92 41	7.95 46	2.56 36	1.39 3	4.71 5	1.47 3	1.55 14	4.29 22	1.44 4	1.51 74	6.05 46	1.32 79	3.11 37	4.31 30	2.33 41	2.64 79	10.7 82	2.67 81	6.60 154	7.99 154	7.44 148	1.53 95	2.63 85	1.96 106
IIOF-NLDP [129]	61.1	3.19 52	10.4 72	2.50 26	2.43 76	9.32 79	2.32 50	1.98 58	5.55 50	1.81 24	1.48 71	6.12 47	1.23 72	3.75 62	5.55 97	2.25 32	3.03 91	9.30 56	3.02 93	2.66 42	4.83 71	2.60 70	1.24 67	1.97 52	1.17 56
OFH [38]	63.4	3.60 79	10.3 71	3.80 99	1.58 10	7.05 37	1.66 11	1.70 28	9.23 75	1.58 10	1.19 38	10.1 81	1.08 49	3.98 71	5.22 74	3.57 96	2.80 84	12.6 103	3.12 98	2.30 22	4.60 55	2.35 52	1.41 88	2.90 97	1.75 94
CostFilter [40]	63.5	3.59 76	8.35 54	3.26 79	2.12 46	6.60 29	2.16 43	2.00 60	5.56 51	2.01 43	2.04 102	7.05 56	1.89 103	2.74 16	3.70 10	2.27 34	3.29 98	10.3 76	3.33 102	5.22 138	9.79 160	6.16 144	0.38 1	1.08 1	0.35 1
Classic++ [32]	64.2	2.66 30	8.18 51	2.65 49	2.13 48	7.96 54	2.43 63	1.85 47	9.39 78	2.10 61	1.09 26	10.4 85	0.88 28	3.97 69	5.60 102	2.89 70	2.36 65	13.6 115	2.10 48	4.03 111	5.20 90	4.33 128	0.99 41	2.05 56	0.92 26
DeepFlow2 [106]	64.9	3.44 62	12.6 85	3.36 85	1.98 35	8.60 59	2.10 40	2.38 80	11.1 86	2.60 87	1.34 49	14.6 108	1.11 53	3.53 54	5.09 61	2.23 28	1.66 21	9.90 70	1.77 17	2.76 48	4.06 11	3.40 93	1.72 105	3.21 109	2.13 112
S2F-IF [121]	65.4	3.54 70	19.2 127	2.58 40	2.41 74	10.4 91	2.59 76	2.57 88	10.6 85	2.59 85	1.29 44	10.5 87	0.98 39	4.07 86	5.38 84	2.90 71	1.65 20	9.94 71	1.85 18	2.27 16	4.26 21	2.35 52	1.33 76	2.49 78	1.32 70
FlowFields+ [128]	67.0	3.58 74	19.0 122	2.56 36	2.57 86	10.8 96	2.78 87	2.72 94	11.9 93	2.78 97	1.32 47	10.9 91	1.03 42	3.97 69	5.34 81	2.74 59	1.64 19	9.79 65	1.87 22	2.26 15	4.30 26	2.35 52	1.35 78	2.62 82	1.34 74
CPM-Flow [114]	67.7	3.47 64	19.0 122	2.52 28	2.59 88	11.0 102	2.82 92	2.56 86	11.3 88	2.75 92	1.34 49	15.7 113	1.06 44	4.02 78	5.42 86	2.78 61	1.59 13	9.39 58	1.87 22	2.30 22	4.17 15	2.36 55	1.35 78	2.69 89	1.39 80
PGM-C [118]	68.5	3.48 67	19.0 122	2.52 28	2.59 88	10.8 96	2.82 92	2.59 89	11.8 92	2.75 92	1.34 49	16.5 119	1.06 44	4.03 80	5.46 90	2.78 61	1.60 14	9.63 62	1.88 25	2.28 18	3.98 6	2.36 55	1.37 83	2.69 89	1.45 84
RFlow [88]	69.1	3.62 81	9.91 69	3.53 92	1.83 27	5.50 15	1.93 31	2.14 68	9.57 79	1.86 29	1.32 47	6.75 50	1.14 62	3.98 71	5.35 82	3.24 89	2.39 67	11.7 94	2.24 62	3.45 88	4.60 55	3.63 98	1.64 102	2.90 97	1.91 103
SegFlow [156]	69.1	3.47 64	19.0 122	2.52 28	2.59 88	10.9 99	2.82 92	2.55 85	11.4 89	2.75 92	1.36 56	16.2 117	1.06 44	4.05 84	5.44 88	2.91 72	1.63 18	9.70 63	1.88 25	2.30 22	4.19 17	2.36 55	1.35 78	2.50 79	1.43 81
EpicFlow [100]	70.4	3.47 64	18.9 120	2.52 28	2.59 88	10.9 99	2.82 92	2.64 91	14.2 104	2.75 92	1.35 53	15.5 111	1.06 44	4.04 82	5.48 91	2.88 69	1.62 17	9.70 63	1.91 29	2.28 18	4.08 13	2.36 55	1.39 87	2.71 91	1.51 89
FlowFields [108]	71.2	3.56 73	19.0 122	2.54 35	2.57 86	10.6 94	2.79 88	2.72 94	11.7 91	2.76 96	1.42 62	10.9 91	1.13 59	4.08 88	5.43 87	2.92 74	1.60 14	10.5 79	1.86 21	2.28 18	4.35 30	2.46 64	1.38 86	2.62 82	1.36 76
MLDP_OF [87]	71.3	4.16 101	10.4 72	4.04 101	2.04 40	6.61 30	2.04 37	2.36 79	6.60 61	2.05 49	1.43 63	5.65 40	1.18 69	3.75 62	4.86 55	2.96 77	2.96 89	8.71 49	3.47 107	4.20 116	5.51 97	7.24 147	1.16 62	1.87 46	1.21 63
WRT [146]	71.5	3.48 67	8.79 61	2.57 39	3.21 110	9.36 81	3.18 106	2.76 97	7.40 66	2.30 77	1.64 87	4.61 25	1.23 72	3.41 50	4.56 44	2.48 49	4.89 135	11.0 86	3.31 100	3.03 67	4.82 70	3.25 90	1.10 51	1.75 40	0.99 45
TV-L1-improved [17]	73.4	2.70 34	9.05 62	2.29 17	1.85 29	7.06 38	1.97 34	1.94 55	9.28 77	1.90 34	1.10 28	8.96 73	0.85 21	4.07 86	5.60 102	2.75 60	5.44 142	17.3 133	6.29 145	4.75 131	6.82 132	4.73 134	1.13 55	2.68 88	1.06 52
DMF_ROB [135]	73.5	3.70 83	15.2 105	3.34 83	2.21 64	9.03 68	2.40 59	2.84 101	13.7 103	2.65 90	1.41 61	16.9 123	1.10 51	3.92 67	5.17 70	3.14 85	2.01 35	10.6 80	2.11 50	2.37 30	3.72 5	2.62 73	1.49 94	2.74 92	1.68 92
CVENG22+RIC [199]	73.7	3.26 56	18.0 114	2.47 24	2.51 81	12.6 112	2.62 77	2.52 84	15.4 110	2.62 89	1.22 41	16.6 121	0.91 35	4.43 108	5.92 118	3.75 104	1.78 24	11.7 94	2.10 48	2.27 16	4.01 9	2.36 55	1.32 75	3.14 106	1.27 67
Steered-L1 [116]	73.9	3.21 53	8.15 50	3.11 74	1.39 3	4.13 2	1.51 5	1.73 37	5.20 43	1.65 14	1.28 43	10.3 84	1.11 53	4.05 84	5.35 82	3.55 94	3.10 94	12.6 103	2.59 80	6.15 152	6.90 135	13.1 160	1.73 106	3.04 105	2.39 118
BriefMatch [122]	74.2	3.03 42	7.96 47	2.73 55	1.75 21	6.88 35	1.73 18	1.72 34	4.70 33	1.73 22	1.51 74	5.38 35	1.39 88	4.01 76	5.27 76	3.72 102	5.57 143	15.9 126	6.02 144	4.65 124	6.85 134	8.98 155	0.95 33	2.30 70	1.77 95
PWC-Net_RVC [143]	74.7	4.74 113	14.6 100	3.51 91	2.88 104	8.88 65	2.92 101	2.75 96	9.98 83	3.27 107	1.65 88	4.91 28	1.35 81	4.10 90	5.12 67	2.91 72	2.66 81	10.2 75	2.67 81	1.69 6	4.65 62	1.13 6	1.26 70	2.06 57	1.29 68
CombBMOF [111]	74.9	3.55 71	11.6 80	2.79 60	2.52 82	7.21 45	2.51 71	1.88 50	5.63 52	1.84 26	1.67 91	11.2 94	1.51 95	3.68 58	4.62 46	3.07 83	4.08 115	11.4 92	4.79 134	4.72 128	6.58 129	3.82 110	0.92 25	1.82 43	0.88 18
VCN_RVC [178]	75.0	4.91 114	16.6 108	4.22 108	2.92 105	9.01 67	2.99 102	2.76 97	9.11 74	2.48 82	1.67 91	9.79 79	1.26 75	3.83 65	4.91 56	2.84 66	2.53 75	9.79 65	2.46 76	2.35 28	4.58 50	1.27 10	1.25 69	2.27 68	1.32 70
Sparse Occlusion [54]	75.8	3.36 59	8.08 48	2.90 66	2.61 93	7.68 50	3.01 103	2.10 64	6.40 59	2.13 64	1.45 67	6.80 51	1.14 62	4.01 76	5.31 80	2.81 64	2.55 76	10.4 77	2.21 59	6.70 156	8.26 155	4.34 129	1.15 59	2.08 58	0.99 45
DeepFlow [85]	77.2	3.94 91	12.7 86	4.14 106	2.12 46	9.06 70	2.28 49	2.84 101	12.5 97	3.16 104	1.68 93	15.6 112	1.44 92	3.58 55	5.10 63	2.20 25	1.78 24	11.1 87	1.88 25	2.65 41	4.07 12	3.40 93	2.08 125	3.59 126	3.09 130
EPPM w/o HM [86]	77.8	4.03 96	13.7 95	3.25 78	1.91 31	7.71 51	1.83 24	2.14 68	7.85 69	1.96 37	1.80 95	10.2 82	1.63 99	3.72 61	4.62 46	3.24 89	3.93 112	13.2 110	3.79 116	4.35 120	5.68 107	7.45 149	0.97 39	1.93 51	0.98 42
MCPFlow_RVC [197]	79.7	7.05 129	18.3 116	4.12 105	5.44 127	11.9 108	5.49 123	6.40 128	12.8 100	7.68 126	2.22 106	4.51 23	1.94 105	4.00 73	5.29 78	2.51 51	2.32 61	6.48 15	2.43 75	2.63 39	4.31 28	1.24 9	1.35 78	1.91 48	1.20 62
HBM-GC [103]	80.5	5.52 118	7.21 31	5.03 123	2.96 106	7.15 42	3.23 108	2.79 100	4.90 40	2.88 99	3.12 124	4.92 29	2.97 129	3.37 47	4.23 25	3.46 92	3.80 110	6.63 16	3.52 108	5.86 147	7.23 146	4.53 132	0.64 2	2.02 55	0.64 3
Complementary OF [21]	81.1	4.47 109	12.4 84	4.63 116	1.60 11	6.16 24	1.67 13	2.10 64	6.85 63	2.16 67	2.27 108	9.76 78	2.19 113	4.00 73	5.10 63	3.71 100	3.96 113	12.9 107	3.32 101	2.83 54	4.46 37	3.08 87	2.04 123	3.33 114	2.86 124
FF++_ROB [141]	81.3	3.75 85	20.6 129	2.92 68	2.60 92	10.6 94	2.79 88	2.97 108	13.2 102	3.18 105	1.62 82	11.2 94	1.38 87	4.12 92	5.52 95	2.99 80	2.24 54	9.58 61	2.30 69	2.31 26	4.40 35	2.39 61	1.36 82	2.55 80	1.44 83
GMFlow_RVC [196]	81.7	8.99 141	13.1 88	7.60 142	3.51 112	7.18 43	3.89 113	3.37 112	6.34 58	3.28 108	2.74 119	4.58 24	2.34 119	4.00 73	4.95 57	2.95 76	4.04 114	7.49 27	3.38 105	4.21 118	6.83 133	2.37 60	0.78 6	1.31 5	0.74 8
Rannacher [23]	82.3	3.60 79	11.3 78	3.27 80	2.41 74	9.53 82	2.63 78	2.60 90	11.9 93	2.58 84	1.36 56	12.1 99	1.09 50	4.22 97	5.90 116	3.14 85	3.63 104	16.1 128	2.75 86	3.72 99	5.24 92	3.70 102	0.96 36	2.16 63	0.91 24
TF+OM [98]	83.3	3.58 74	9.07 63	2.75 58	2.07 44	6.43 26	2.37 54	1.99 59	7.56 68	2.78 97	2.07 103	7.02 55	2.07 111	4.19 96	5.12 67	4.32 119	3.15 96	10.1 74	3.00 92	4.10 113	6.00 115	3.92 113	1.54 96	2.98 102	1.94 104
Aniso. Huber-L1 [22]	84.2	3.17 50	9.57 66	3.05 71	3.72 113	11.5 106	4.38 116	2.86 104	10.5 84	3.80 112	1.70 94	11.6 97	1.42 89	4.04 82	5.58 99	2.98 79	2.34 63	9.88 69	2.05 41	4.49 122	5.91 113	3.42 95	1.08 48	2.10 59	1.02 48
F-TV-L1 [15]	84.2	5.69 120	13.3 90	6.62 133	2.71 99	12.0 109	2.86 99	2.76 97	12.6 98	2.43 81	2.41 113	16.3 118	2.02 110	4.17 95	5.27 76	3.74 103	2.41 69	10.8 84	2.49 78	3.04 68	4.84 76	2.26 45	0.79 7	1.81 42	0.76 11
TCOF [69]	84.6	3.95 92	11.0 76	4.20 107	2.56 85	9.31 78	2.68 82	2.71 93	12.8 100	3.34 109	2.30 109	6.80 51	2.33 115	4.50 114	6.28 135	2.58 56	1.89 29	6.02 9	2.06 42	4.72 128	6.30 119	2.58 67	1.37 83	2.63 85	1.22 66
ComplOF-FED-GPU [35]	85.1	4.09 99	12.8 87	4.09 104	1.61 14	9.86 86	1.62 9	2.12 66	8.39 70	1.87 31	1.85 97	12.4 102	1.70 102	3.95 68	5.25 75	3.25 91	3.54 102	15.1 124	3.60 112	3.93 105	4.83 71	4.60 133	1.55 98	2.93 101	1.80 96
NL-TV-NCC [25]	85.7	3.89 89	8.49 56	3.34 83	2.52 82	8.44 57	2.38 56	2.25 74	5.49 48	1.99 39	1.87 98	7.61 60	1.53 96	4.36 104	5.91 117	2.78 61	4.12 119	13.0 108	3.58 111	3.85 103	5.74 109	3.79 107	1.63 101	2.81 94	1.46 85
ROF-ND [105]	86.0	4.03 96	11.1 77	3.48 90	2.33 67	5.09 9	2.22 44	2.19 71	6.22 57	2.02 45	2.30 109	5.92 45	1.68 101	4.23 98	6.03 124	2.94 75	3.70 108	12.2 98	3.05 95	6.21 153	6.93 137	5.53 139	1.43 90	2.21 66	1.32 70
ACK-Prior [27]	86.7	4.28 103	9.53 65	3.85 100	1.87 30	5.68 16	1.83 24	1.97 57	5.25 45	1.96 37	1.98 101	5.26 33	1.65 100	4.08 88	5.12 67	3.79 107	4.53 131	13.0 108	3.61 113	5.63 142	6.40 124	8.50 153	1.92 119	2.90 97	2.64 121
LDOF [28]	91.3	3.72 84	14.9 103	3.59 95	2.38 71	14.0 122	2.46 67	2.69 92	14.4 105	2.55 83	1.48 71	33.9 144	1.10 51	4.24 100	5.59 101	3.75 104	2.04 39	16.4 131	1.99 37	2.83 54	4.83 71	2.43 62	2.28 133	4.02 138	3.38 133
SRR-TVOF-NL [89]	92.1	4.62 112	12.2 83	3.55 93	2.32 66	10.8 96	2.34 52	2.56 86	12.4 96	2.59 85	1.49 73	8.56 70	1.17 68	4.12 92	5.10 63	3.51 93	2.63 78	10.9 85	2.26 65	5.64 144	6.92 136	4.13 125	2.19 129	2.87 96	2.86 124
DPOF [18]	92.2	4.32 104	16.2 107	3.30 81	2.69 97	10.2 88	2.69 84	2.44 83	7.17 65	2.61 88	1.95 100	10.2 82	1.55 97	3.85 66	5.20 72	3.03 82	2.84 86	11.1 87	2.67 81	4.71 127	4.83 71	8.84 154	1.73 106	3.03 104	1.86 100
CRTflow [81]	92.2	3.65 82	14.0 98	3.10 73	2.16 52	7.88 52	2.23 45	2.25 74	11.2 87	1.99 39	1.56 79	12.7 103	1.35 81	4.02 78	5.53 96	3.01 81	6.86 149	19.6 145	8.64 151	3.29 77	5.53 100	3.23 89	2.05 124	3.95 137	2.71 122
LocallyOriented [52]	92.9	3.46 63	14.6 100	3.01 70	2.84 103	13.3 116	2.85 98	2.92 106	17.6 116	3.05 103	1.63 85	10.6 88	1.43 90	4.23 98	5.79 110	3.19 87	2.48 74	7.69 31	2.87 88	3.41 86	5.63 105	3.25 90	1.65 103	3.48 119	1.86 100
SIOF [67]	93.6	4.00 94	8.74 60	3.46 89	2.00 37	13.6 117	2.13 41	3.02 110	15.7 111	3.38 110	2.55 117	13.5 107	2.50 120	4.27 101	5.70 105	3.70 99	3.55 103	11.5 93	4.01 119	3.17 73	4.64 60	2.12 39	1.85 116	3.29 113	2.15 113
Second-order prior [8]	93.8	3.40 60	13.6 92	3.19 76	2.16 52	13.8 121	2.34 52	2.43 81	17.1 114	2.26 74	1.20 39	15.7 113	0.96 38	4.44 109	6.10 129	3.08 84	3.41 101	19.7 146	2.67 81	5.42 141	6.02 117	5.40 136	1.44 91	3.44 118	1.48 86
Brox et al. [5]	94.1	4.01 95	14.7 102	4.49 114	2.75 101	11.5 106	3.21 107	2.33 78	12.2 95	2.34 78	1.46 68	19.9 127	1.19 70	4.62 119	5.71 106	4.89 134	2.13 44	13.3 111	2.28 66	2.87 57	4.78 67	1.55 18	2.30 135	3.68 130	3.31 131
Bartels [41]	94.7	4.23 102	10.7 75	4.70 119	2.37 69	5.83 21	2.66 80	2.21 72	7.42 67	2.42 80	2.59 118	8.46 69	2.53 121	4.33 103	5.50 93	4.37 121	3.69 107	14.6 122	4.80 135	4.75 131	6.30 119	7.59 150	1.13 55	2.33 73	1.32 70
Dynamic MRF [7]	95.7	4.55 111	13.6 92	5.02 121	1.81 25	8.86 64	1.82 23	2.13 67	12.6 98	1.87 31	1.62 82	13.2 105	1.45 93	4.61 117	5.80 113	4.32 119	4.14 120	21.3 148	4.42 125	3.22 76	4.41 36	5.01 135	2.11 126	3.92 136	3.51 134
CLG-TV [48]	97.0	3.59 76	9.91 69	3.24 77	4.16 117	11.1 103	4.96 118	3.12 111	11.5 90	3.97 113	2.31 111	13.0 104	1.99 109	4.56 116	6.11 130	3.95 110	2.85 87	12.2 98	2.78 87	4.23 119	5.87 112	2.86 80	1.17 63	2.45 77	1.04 51
TriangleFlow [30]	97.5	3.96 93	11.5 79	4.08 103	2.14 50	10.2 88	2.07 38	2.16 70	9.80 82	1.86 29	1.47 69	9.22 74	1.11 53	5.37 143	7.25 152	4.72 130	4.49 130	13.7 117	4.62 130	3.78 101	7.33 148	4.11 122	1.73 106	3.48 119	2.30 115
p-harmonic [29]	98.1	4.47 109	14.4 99	4.52 115	2.71 99	9.33 80	2.89 100	3.40 113	15.0 107	3.02 102	1.93 99	24.1 134	1.59 98	4.15 94	5.18 71	3.66 98	3.37 100	16.0 127	3.54 109	3.90 104	5.36 94	2.71 77	1.29 72	2.41 76	1.38 78
Local-TV-L1 [65]	98.4	4.95 115	13.2 89	5.40 124	4.37 119	14.6 124	5.04 119	4.59 120	17.8 118	5.96 122	2.42 114	16.9 123	2.25 114	3.68 58	5.03 59	2.82 65	2.25 56	10.6 80	2.24 62	2.55 35	4.37 32	2.91 84	2.73 142	4.10 140	7.77 148
FlowNetS+ft+v [110]	98.5	3.42 61	13.4 91	3.39 86	2.54 84	11.2 104	2.80 90	2.94 107	18.6 121	4.76 115	1.43 63	27.4 137	1.20 71	4.67 122	6.35 139	3.71 100	1.96 33	12.3 101	2.01 39	4.10 113	6.00 115	4.11 122	1.76 110	3.49 122	2.37 117
CNN-flow-warp+ref [115]	99.1	3.90 90	19.8 128	3.73 98	3.40 111	10.9 99	4.21 114	3.85 117	23.8 134	6.07 123	1.65 88	22.4 132	1.37 84	4.38 107	5.58 99	4.08 113	2.23 52	13.8 118	2.33 71	2.41 31	4.27 22	2.24 43	2.43 139	3.66 129	3.64 137
CBF [12]	99.3	3.59 76	10.5 74	3.68 97	4.72 121	10.4 91	6.02 128	2.28 76	9.24 76	2.96 101	1.63 85	12.2 100	1.36 83	4.48 113	5.75 108	3.99 112	2.70 82	10.7 82	2.48 77	6.13 151	7.02 138	5.92 142	1.45 93	2.65 87	1.66 91
DF-Auto [113]	99.5	3.88 88	17.6 112	2.93 69	5.44 127	14.7 125	6.44 129	4.54 119	16.8 113	9.38 130	2.22 106	15.0 110	1.95 106	4.32 102	6.00 122	3.88 109	1.44 6	7.14 22	1.73 15	4.20 116	6.78 131	1.70 21	2.42 138	4.04 139	3.34 132
OFRF [132]	103.3	4.35 105	9.74 67	4.34 109	5.12 125	13.1 115	5.68 126	3.74 116	14.7 106	5.10 116	2.91 122	11.0 93	2.84 126	3.34 46	4.74 51	2.24 29	3.34 99	9.46 59	3.23 99	3.67 97	5.54 101	5.56 140	3.05 146	3.88 134	9.53 153
StereoFlow [44]	106.3	21.8 162	37.8 157	27.4 162	24.3 160	37.6 162	22.4 158	28.3 162	39.2 157	28.8 157	24.0 160	47.7 154	21.6 159	5.15 136	5.49 92	6.01 150	0.95 2	6.87 17	1.06 2	1.68 5	3.70 4	0.92 4	1.29 72	2.32 71	1.49 87
LiteFlowNet [138]	106.9	6.43 123	24.0 135	4.45 112	3.74 114	10.4 91	3.78 110	4.32 118	15.2 109	3.78 111	2.36 112	8.74 71	1.97 108	4.88 129	6.06 125	4.38 122	4.23 123	14.0 119	3.68 114	3.56 92	5.59 104	1.98 30	1.70 104	2.79 93	1.83 97
TriFlow [93]	107.3	4.44 106	13.8 96	3.62 96	3.16 109	9.65 84	3.81 111	2.89 105	19.6 124	6.36 124	2.48 116	7.88 64	2.33 115	4.37 106	5.44 88	4.28 118	2.98 90	8.42 38	3.07 96	11.7 161	7.70 152	21.5 161	1.76 110	2.98 102	1.94 104
Fusion [6]	108.1	3.76 86	16.9 109	4.07 102	1.99 36	7.37 48	2.26 47	2.07 63	8.51 72	2.28 75	1.59 80	24.8 135	1.37 84	5.00 133	6.36 140	4.98 139	4.70 134	16.2 130	5.01 138	6.00 150	7.50 150	4.38 130	2.97 145	3.74 133	3.55 135
Learning Flow [11]	108.1	3.80 87	11.9 81	3.58 94	3.02 107	13.0 114	3.34 109	2.84 101	17.9 119	3.18 105	1.82 96	34.6 147	1.50 94	5.44 147	7.32 153	4.61 127	3.10 94	18.8 141	3.04 94	3.94 106	6.38 123	3.65 100	1.37 83	3.38 116	1.18 57
C-RAFT_RVC [181]	108.6	7.80 134	25.3 137	6.17 131	6.67 135	16.5 128	6.68 131	6.61 129	15.9 112	7.92 127	2.88 121	7.19 59	2.33 115	5.18 139	6.31 136	4.53 126	3.85 111	9.16 54	4.24 122	3.57 94	5.58 103	2.06 34	1.44 91	2.29 69	1.30 69
Shiralkar [42]	109.9	4.46 107	18.3 116	4.36 110	1.93 33	16.4 127	1.87 28	2.99 109	17.6 116	2.01 43	2.10 104	21.0 129	1.96 107	4.36 104	5.72 107	3.55 94	5.65 144	19.4 143	5.11 141	4.90 136	5.57 102	7.14 146	2.11 126	4.71 146	2.53 119
ContinualFlow_ROB [148]	109.9	7.09 130	26.0 140	5.87 128	6.48 134	13.6 117	7.04 135	7.43 132	21.2 129	9.67 131	3.12 124	10.8 90	2.57 124	5.41 145	6.38 141	4.71 128	6.48 148	15.7 125	7.64 149	2.20 12	4.02 10	1.33 12	1.42 89	2.40 75	1.64 90
StereoOF-V1MT [117]	113.0	4.46 107	18.0 114	4.46 113	2.09 45	18.6 134	1.79 21	3.70 115	20.6 127	2.13 64	2.18 105	25.0 136	1.91 104	5.52 149	6.98 150	4.82 132	5.01 140	25.8 153	4.73 132	3.21 75	5.27 93	3.64 99	2.32 136	4.64 144	2.83 123
EAI-Flow [147]	114.1	7.60 132	21.3 130	6.38 132	4.08 115	15.8 126	4.21 114	5.17 122	18.4 120	5.60 120	3.05 123	15.7 113	2.94 128	4.45 110	5.81 114	3.60 97	4.33 125	12.6 103	4.10 120	5.63 142	6.30 119	3.58 97	1.33 76	2.55 80	1.43 81
SegOF [10]	114.6	5.62 119	17.1 110	3.08 72	8.33 141	20.9 138	10.1 145	7.44 133	21.7 130	13.3 139	5.42 143	21.0 129	4.47 138	4.81 128	5.51 94	5.74 149	4.97 138	17.1 132	4.83 136	2.12 10	4.38 34	1.46 15	2.17 128	3.23 110	3.74 139
CompactFlow_ROB [155]	115.3	9.64 146	29.9 147	5.40 124	6.23 133	12.8 113	6.77 133	8.77 139	20.9 128	16.5 145	3.26 126	11.9 98	2.83 125	5.24 140	6.31 136	4.71 128	4.38 127	14.5 120	4.74 133	2.21 13	4.89 79	1.06 5	1.86 118	3.34 115	1.83 97
WOLF_ROB [144]	116.0	5.28 117	22.2 132	4.65 118	4.15 116	21.9 142	3.81 111	6.02 126	23.6 133	5.35 119	2.47 115	16.5 119	2.33 115	4.50 114	5.65 104	4.12 115	4.15 121	14.8 123	3.83 117	3.00 65	4.84 76	2.67 75	2.25 132	4.11 141	3.66 138
Ad-TV-NDC [36]	118.0	8.75 139	15.3 106	12.3 153	10.5 149	24.2 148	12.3 149	8.96 141	28.2 140	11.5 133	5.31 142	22.8 133	5.55 143	4.03 80	5.79 110	2.86 68	2.80 84	10.0 73	2.87 88	3.04 68	4.52 43	2.66 74	4.62 153	5.79 153	30.9 161
AugFNG_ROB [139]	119.3	7.79 133	28.5 145	5.02 121	9.56 146	18.5 133	11.3 148	8.78 140	26.2 137	17.3 148	3.46 130	9.97 80	2.86 127	5.26 141	6.24 134	4.77 131	4.44 128	14.5 120	4.15 121	2.99 64	5.22 91	1.30 11	1.85 116	3.18 108	2.10 111
LSM_FLOW_RVC [182]	120.2	9.44 145	33.6 152	8.15 144	5.61 130	18.8 135	5.66 125	9.75 143	25.6 136	9.07 129	3.27 127	18.6 126	2.55 122	5.14 135	6.44 143	4.22 117	4.26 124	17.3 133	4.70 131	2.70 45	4.99 83	1.92 28	1.74 109	3.57 124	1.85 99
Filter Flow [19]	122.0	6.76 125	17.6 112	4.37 111	5.01 123	17.6 130	5.49 123	5.98 125	26.3 138	18.4 150	7.23 145	29.9 141	6.91 146	5.12 134	6.23 132	5.36 143	5.23 141	11.9 97	4.95 137	6.64 155	8.75 158	3.75 106	0.95 33	2.15 61	1.21 63
Modified CLG [34]	123.0	6.79 126	24.7 136	6.63 134	7.09 137	17.4 129	9.40 141	10.1 144	29.2 142	16.6 146	4.48 139	27.5 138	3.86 134	4.80 126	6.31 136	4.48 125	2.65 80	17.6 136	2.69 85	2.92 62	4.94 81	2.07 35	3.19 148	5.17 149	5.78 144
LFNet_ROB [145]	123.5	8.41 138	29.9 147	5.80 127	5.03 124	13.7 120	5.06 121	7.93 136	22.4 132	5.30 118	3.31 128	14.9 109	2.56 123	5.26 141	6.39 142	4.98 139	4.56 133	17.8 137	4.51 129	3.73 100	5.99 114	2.59 69	1.82 115	3.26 112	2.08 110
ResPWCR_ROB [140]	124.0	8.23 136	22.9 133	6.93 135	4.20 118	12.3 111	4.43 117	5.27 123	15.1 108	5.64 121	3.74 132	17.2 125	3.36 131	4.79 125	5.55 97	5.34 142	4.99 139	13.6 115	5.09 140	4.72 128	6.59 130	2.89 81	2.38 137	3.59 126	2.92 126
IAOF2 [51]	124.1	5.05 116	13.6 92	4.64 117	4.90 122	14.5 123	5.78 127	3.68 114	18.6 121	5.15 117	12.3 154	34.1 146	13.8 154	4.65 120	6.21 131	3.78 106	4.47 129	13.5 112	3.70 115	5.73 145	7.13 143	3.98 115	1.96 121	3.53 123	2.35 116
TVL1_RVC [175]	125.8	13.5 153	26.6 142	16.1 157	14.6 153	23.7 147	16.6 154	16.9 152	36.4 153	25.4 155	11.9 153	33.8 143	12.8 152	4.66 121	6.23 132	3.96 111	2.36 65	16.1 128	2.89 90	2.30 22	4.59 52	1.48 16	5.62 157	6.37 154	12.6 156
BlockOverlap [61]	126.0	6.80 127	12.1 82	5.94 129	5.51 129	13.6 117	6.58 130	5.32 124	22.2 131	7.30 125	4.20 133	16.7 122	4.06 136	4.45 110	5.39 85	5.11 141	4.91 136	12.5 102	4.34 124	6.77 157	7.13 143	9.52 156	2.02 122	3.24 111	9.49 152
FlowNet2 [120]	126.1	8.99 141	25.8 138	7.01 136	9.84 147	19.0 136	10.7 146	7.98 137	20.1 125	13.5 140	4.47 138	9.41 75	4.21 137	5.17 137	6.08 127	4.92 136	4.10 117	11.2 89	4.43 126	5.98 149	7.71 153	2.90 83	1.78 112	2.92 100	1.89 102
EPMNet [131]	126.5	8.88 140	26.2 141	7.20 139	9.32 145	18.2 131	10.0 144	7.14 130	18.8 123	12.3 136	4.79 140	12.3 101	4.62 141	5.17 137	6.08 127	4.92 136	4.10 117	11.2 89	4.43 126	4.88 135	7.05 140	2.56 66	1.93 120	3.57 124	2.07 109
IRR-PWC_RVC [180]	126.9	10.2 148	33.8 153	5.99 130	8.45 142	19.0 136	9.43 142	9.62 142	24.4 135	14.7 141	4.25 134	9.71 77	3.53 133	5.42 146	6.06 125	5.64 147	3.68 106	12.2 98	3.37 104	4.84 134	7.66 151	2.25 44	2.23 130	3.62 128	2.59 120
HBpMotionGpu [43]	127.1	5.92 121	15.0 104	4.79 120	7.78 139	22.4 144	9.04 140	7.17 131	39.2 157	17.3 148	3.31 128	13.4 106	3.14 130	4.71 123	5.88 115	4.84 133	3.74 109	13.5 112	3.54 109	5.96 148	7.17 145	3.68 101	2.24 131	3.43 117	4.65 140
2D-CLG [1]	128.1	9.69 147	37.7 156	7.18 138	11.1 150	21.9 142	13.9 152	19.0 157	34.8 148	28.7 156	13.0 155	46.7 152	12.8 152	4.97 131	5.79 110	5.47 146	4.08 115	21.2 147	4.32 123	2.29 21	4.00 8	1.64 19	4.47 152	5.51 152	6.55 146
GraphCuts [14]	128.4	6.34 122	17.1 110	5.55 126	5.30 126	20.9 138	5.26 122	6.05 127	20.4 126	12.4 137	2.85 120	20.9 128	2.15 112	4.74 124	5.95 120	4.90 135	8.69 153	12.6 103	5.19 142	5.79 146	6.40 124	6.80 145	2.45 140	3.48 119	3.59 136
SPSA-learn [13]	128.5	6.87 128	21.3 130	7.92 143	6.02 132	21.1 140	6.96 134	7.55 134	27.5 139	12.7 138	4.44 136	29.2 139	4.59 140	4.80 126	5.92 118	4.93 138	4.94 137	17.3 133	5.02 139	3.37 83	5.01 84	2.29 49	4.14 151	4.97 148	6.49 145
GroupFlow [9]	129.4	9.15 144	25.8 138	10.5 151	11.6 152	30.0 155	12.3 149	10.2 145	35.4 150	11.9 134	3.50 131	15.8 116	3.39 132	5.48 148	6.56 145	4.42 123	9.25 154	24.8 150	10.8 156	2.35 28	4.58 50	1.67 20	2.93 144	5.22 150	4.99 141
Black & Anandan [4]	130.2	7.19 131	18.9 120	8.40 145	5.96 131	22.6 145	6.69 132	8.73 138	28.7 141	12.1 135	4.46 137	29.4 140	4.52 139	4.91 130	6.59 146	4.09 114	4.18 122	19.4 143	4.44 128	4.69 125	6.36 122	2.01 31	3.13 147	4.46 142	5.06 142
IAOF [50]	131.2	6.54 124	18.3 116	7.13 137	6.99 136	18.4 132	7.90 138	7.71 135	32.3 145	8.44 128	8.21 148	31.8 142	9.78 150	4.61 117	6.01 123	4.14 116	4.35 126	18.9 142	3.43 106	4.69 125	6.08 118	3.31 92	3.23 149	4.69 145	15.9 159
2bit-BM-tele [96]	134.2	8.99 141	18.6 119	10.2 148	4.45 120	11.3 105	5.04 119	4.66 121	17.3 115	4.41 114	5.23 141	21.7 131	5.04 142	4.99 132	5.96 121	5.46 145	6.47 147	18.3 138	7.49 148	7.77 159	8.57 157	12.5 159	2.29 134	3.89 135	2.99 129
Nguyen [33]	137.4	8.16 135	23.0 134	7.57 141	16.5 156	22.7 146	19.3 156	16.8 151	36.0 151	20.7 153	13.8 156	39.5 148	14.7 156	5.40 144	6.44 143	6.70 151	4.54 132	18.5 140	5.42 143	3.50 90	5.02 85	2.08 36	4.00 150	5.50 151	8.53 150
UnFlow [127]	137.9	19.4 161	44.0 161	10.2 148	11.3 151	21.2 141	12.4 151	18.1 154	36.0 151	15.5 143	7.47 147	34.0 145	6.40 145	7.10 157	7.11 151	8.76 156	8.31 152	24.8 150	9.26 152	5.13 137	6.50 127	1.52 17	1.57 99	3.14 106	2.01 107
Heeger++ [102]	140.7	18.3 160	32.1 151	10.5 151	9.98 148	34.3 161	7.90 138	16.0 149	32.7 146	11.0 132	9.23 149	47.6 153	7.86 148	5.95 151	6.74 147	5.71 148	23.4 161	49.5 162	24.5 161	3.61 96	6.53 128	2.58 67	1.78 112	3.68 130	2.96 127
SILK [80]	141.2	10.7 149	31.4 150	13.1 155	8.77 143	26.6 150	9.80 143	13.6 147	34.9 149	16.7 147	6.53 144	45.4 150	6.08 144	6.11 152	7.36 155	6.71 152	6.96 150	29.4 156	7.39 147	2.97 63	4.77 66	3.96 114	5.00 154	6.99 155	10.7 154
Horn & Schunck [3]	141.9	8.40 137	27.2 143	9.62 146	7.28 138	28.3 152	7.55 137	13.3 146	31.9 144	15.8 144	7.35 146	48.5 155	7.69 147	5.84 150	7.34 154	5.45 144	5.80 145	25.8 153	6.79 146	5.25 139	7.11 142	2.11 38	5.21 155	8.30 157	6.66 147
H+S_RVC [176]	146.5	14.7 155	45.1 162	10.3 150	14.7 154	29.7 154	15.8 153	23.2 160	40.1 160	29.6 160	31.3 161	52.9 159	32.8 161	6.81 155	6.83 149	10.4 160	13.8 159	34.0 159	16.9 159	2.84 56	5.51 97	2.50 65	8.19 160	8.91 158	8.01 149
FFV1MT [104]	146.7	17.0 159	35.1 155	10.1 147	8.30 140	33.0 159	7.40 136	17.2 153	40.0 159	15.3 142	9.57 150	55.8 161	8.75 149	7.99 161	8.46 161	10.1 159	21.8 160	36.1 160	23.3 160	4.43 121	7.02 138	4.09 121	1.78 112	3.68 130	2.96 127
TI-DOFE [24]	147.0	16.4 157	34.0 154	21.2 161	21.5 159	31.9 156	25.3 160	24.4 161	41.0 161	33.0 161	22.8 159	46.3 151	25.2 160	6.25 153	7.67 157	6.82 153	6.37 146	25.6 152	7.87 150	3.94 106	5.78 111	1.78 24	8.49 161	9.86 160	12.5 155
Periodicity [79]	147.1	12.3 151	51.4 198	7.39 140	9.23 144	38.3 163	11.1 147	34.7 163	48.1 163	36.0 162	4.27 135	57.7 162	3.99 135	24.4 163	73.2 163	16.2 162	29.6 163	74.3 163	29.4 163	3.29 77	5.67 106	1.90 26	6.64 158	44.8 163	21.5 160
SLK [47]	148.0	12.3 151	43.0 160	16.5 158	19.8 158	32.9 158	22.4 158	21.4 158	38.4 155	29.3 159	41.6 163	51.6 157	44.5 163	6.87 156	7.63 156	8.94 157	8.09 151	31.2 158	9.56 153	3.34 81	5.41 95	2.60 70	8.13 159	9.23 159	13.9 158
Adaptive flow [45]	154.2	16.4 157	28.7 146	16.7 159	17.2 157	25.5 149	19.6 157	18.8 156	37.6 154	36.5 163	11.2 152	43.6 149	11.9 151	7.11 158	7.79 158	7.88 154	10.1 157	24.1 149	10.1 155	16.1 162	14.2 162	22.1 162	2.92 143	4.89 147	5.22 143
HCIC-L [97]	154.9	24.1 163	31.3 149	12.9 154	27.6 162	28.7 153	69.9 163	16.0 149	30.6 143	23.1 154	18.1 158	55.4 160	17.8 158	7.39 159	8.35 160	8.32 155	12.6 158	18.3 138	14.4 158	25.6 163	23.8 163	23.6 163	2.62 141	4.51 143	9.36 151
PGAM+LK [55]	155.8	14.0 154	40.6 158	18.8 160	14.9 155	33.1 160	17.8 155	14.4 148	32.9 147	19.3 151	15.7 157	63.6 163	14.9 157	6.36 154	6.81 148	9.14 158	9.83 156	30.7 157	9.83 154	10.4 160	12.2 161	10.3 157	5.30 156	7.26 156	13.0 157
FOLKI [16]	156.2	11.0 150	41.0 159	14.5 156	24.9 161	32.3 157	36.7 161	18.7 155	43.8 162	20.5 152	10.9 151	50.5 156	13.8 154	7.42 160	8.28 159	10.6 161	9.75 155	36.9 161	12.1 157	4.77 133	7.29 147	11.0 158	12.2 162	11.4 161	36.4 162
Pyramid LK [2]	159.0	15.8 156	28.2 144	30.4 163	35.8 163	28.0 151	49.6 162	22.3 159	38.6 156	29.1 158	31.8 162	51.7 158	39.0 162	18.3 162	24.8 162	24.1 163	26.7 162	28.6 155	26.7 162	7.19 158	8.98 159	7.70 152	32.7 163	40.6 162	57.0 163
AdaConv-v1 [124]	164.1	45.2 164	50.1 163	46.0 164	78.3 164	79.6 164	76.9 164	78.3 164	73.0 164	77.6 164	79.2 164	80.8 164	79.6 164	83.7 164	84.3 164	83.6 164	82.1 164	80.6 164	81.5 164	69.6 165	58.5 165	75.3 165	84.4 164	84.7 164	83.9 164
SepConv-v1 [125]	164.1	45.2 164	50.1 163	46.0 164	78.3 164	79.6 164	76.9 164	78.3 164	73.0 164	77.6 164	79.2 164	80.8 164	79.6 164	83.7 164	84.3 164	83.6 164	82.1 164	80.6 164	81.5 164	69.6 165	58.5 165	75.3 165	84.4 164	84.7 164	83.9 164
SuperSlomo [130]	164.1	45.2 164	50.1 163	46.0 164	78.3 164	79.6 164	76.9 164	78.3 164	73.0 164	77.6 164	79.2 164	80.8 164	79.6 164	83.7 164	84.3 164	83.6 164	82.1 164	80.6 164	81.5 164	69.6 165	58.5 165	75.3 165	84.4 164	84.7 164	83.9 164
CtxSyn [134]	164.1	45.2 164	50.1 163	46.0 164	78.3 164	79.6 164	76.9 164	78.3 164	73.0 164	77.6 164	79.2 164	80.8 164	79.6 164	83.7 164	84.3 164	83.6 164	82.1 164	80.6 164	81.5 164	69.6 165	58.5 165	75.3 165	84.4 164	84.7 164	83.9 164
CyclicGen [149]	164.1	45.2 164	50.1 163	46.0 164	78.3 164	79.6 164	76.9 164	78.3 164	73.0 164	77.6 164	79.2 164	80.8 164	79.6 164	83.7 164	84.3 164	83.6 164	82.1 164	80.6 164	81.5 164	69.6 165	58.5 165	75.3 165	84.4 164	84.7 164	83.9 164
TOF-M [150]	164.1	45.2 164	50.1 163	46.0 164	78.3 164	79.6 164	76.9 164	78.3 164	73.0 164	77.6 164	79.2 164	80.8 164	79.6 164	83.7 164	84.3 164	83.6 164	82.1 164	80.6 164	81.5 164	69.6 165	58.5 165	75.3 165	84.4 164	84.7 164	83.9 164
MPRN [151]	164.1	45.2 164	50.1 163	46.0 164	78.3 164	79.6 164	76.9 164	78.3 164	73.0 164	77.6 164	79.2 164	80.8 164	79.6 164	83.7 164	84.3 164	83.6 164	82.1 164	80.6 164	81.5 164	69.6 165	58.5 165	75.3 165	84.4 164	84.7 164	83.9 164
DAIN [152]	164.1	45.2 164	50.1 163	46.0 164	78.3 164	79.6 164	76.9 164	78.3 164	73.0 164	77.6 164	79.2 164	80.8 164	79.6 164	83.7 164	84.3 164	83.6 164	82.1 164	80.6 164	81.5 164	69.6 165	58.5 165	75.3 165	84.4 164	84.7 164	83.9 164
FRUCnet [153]	164.1	45.2 164	50.1 163	46.0 164	78.3 164	79.6 164	76.9 164	78.3 164	73.0 164	77.6 164	79.2 164	80.8 164	79.6 164	83.7 164	84.3 164	83.6 164	82.1 164	80.6 164	81.5 164	69.6 165	58.5 165	75.3 165	84.4 164	84.7 164	83.9 164
OFRI [154]	164.1	45.2 164	50.1 163	46.0 164	78.3 164	79.6 164	76.9 164	78.3 164	73.0 164	77.6 164	79.2 164	80.8 164	79.6 164	83.7 164	84.3 164	83.6 164	82.1 164	80.6 164	81.5 164	69.6 165	58.5 165	75.3 165	84.4 164	84.7 164	83.9 164
FGME [158]	164.1	45.2 164	50.1 163	46.0 164	78.3 164	79.6 164	76.9 164	78.3 164	73.0 164	77.6 164	79.2 164	80.8 164	79.6 164	83.7 164	84.3 164	83.6 164	82.1 164	80.6 164	81.5 164	69.6 165	58.5 165	75.3 165	84.4 164	84.7 164	83.9 164
MS-PFT [159]	164.1	45.2 164	50.1 163	46.0 164	78.3 164	79.6 164	76.9 164	78.3 164	73.0 164	77.6 164	79.2 164	80.8 164	79.6 164	83.7 164	84.3 164	83.6 164	82.1 164	80.6 164	81.5 164	69.6 165	58.5 165	75.3 165	84.4 164	84.7 164	83.9 164
MEMC-Net+ [160]	164.1	45.2 164	50.1 163	46.0 164	78.3 164	79.6 164	76.9 164	78.3 164	73.0 164	77.6 164	79.2 164	80.8 164	79.6 164	83.7 164	84.3 164	83.6 164	82.1 164	80.6 164	81.5 164	69.6 165	58.5 165	75.3 165	84.4 164	84.7 164	83.9 164
ADC [161]	164.1	45.2 164	50.1 163	46.0 164	78.3 164	79.6 164	76.9 164	78.3 164	73.0 164	77.6 164	79.2 164	80.8 164	79.6 164	83.7 164	84.3 164	83.6 164	82.1 164	80.6 164	81.5 164	69.6 165	58.5 165	75.3 165	84.4 164	84.7 164	83.9 164
DSepConv [162]	164.1	45.2 164	50.1 163	46.0 164	78.3 164	79.6 164	76.9 164	78.3 164	73.0 164	77.6 164	79.2 164	80.8 164	79.6 164	83.7 164	84.3 164	83.6 164	82.1 164	80.6 164	81.5 164	69.6 165	58.5 165	75.3 165	84.4 164	84.7 164	83.9 164
MAF-net [163]	164.1	45.2 164	50.1 163	46.0 164	78.3 164	79.6 164	76.9 164	78.3 164	73.0 164	77.6 164	79.2 164	80.8 164	79.6 164	83.7 164	84.3 164	83.6 164	82.1 164	80.6 164	81.5 164	69.6 165	58.5 165	75.3 165	84.4 164	84.7 164	83.9 164
STAR-Net [164]	164.1	45.2 164	50.1 163	46.0 164	78.3 164	79.6 164	76.9 164	78.3 164	73.0 164	77.6 164	79.2 164	80.8 164	79.6 164	83.7 164	84.3 164	83.6 164	82.1 164	80.6 164	81.5 164	69.6 165	58.5 165	75.3 165	84.4 164	84.7 164	83.9 164
AdaCoF [165]	164.1	45.2 164	50.1 163	46.0 164	78.3 164	79.6 164	76.9 164	78.3 164	73.0 164	77.6 164	79.2 164	80.8 164	79.6 164	83.7 164	84.3 164	83.6 164	82.1 164	80.6 164	81.5 164	69.6 165	58.5 165	75.3 165	84.4 164	84.7 164	83.9 164
TC-GAN [166]	164.1	45.2 164	50.1 163	46.0 164	78.3 164	79.6 164	76.9 164	78.3 164	73.0 164	77.6 164	79.2 164	80.8 164	79.6 164	83.7 164	84.3 164	83.6 164	82.1 164	80.6 164	81.5 164	69.6 165	58.5 165	75.3 165	84.4 164	84.7 164	83.9 164
FeFlow [167]	164.1	45.2 164	50.1 163	46.0 164	78.3 164	79.6 164	76.9 164	78.3 164	73.0 164	77.6 164	79.2 164	80.8 164	79.6 164	83.7 164	84.3 164	83.6 164	82.1 164	80.6 164	81.5 164	69.6 165	58.5 165	75.3 165	84.4 164	84.7 164	83.9 164
DAI [168]	164.1	45.2 164	50.1 163	46.0 164	78.3 164	79.6 164	76.9 164	78.3 164	73.0 164	77.6 164	79.2 164	80.8 164	79.6 164	83.7 164	84.3 164	83.6 164	82.1 164	80.6 164	81.5 164	69.6 165	58.5 165	75.3 165	84.4 164	84.7 164	83.9 164
SoftSplat [169]	164.1	45.2 164	50.1 163	46.0 164	78.3 164	79.6 164	76.9 164	78.3 164	73.0 164	77.6 164	79.2 164	80.8 164	79.6 164	83.7 164	84.3 164	83.6 164	82.1 164	80.6 164	81.5 164	69.6 165	58.5 165	75.3 165	84.4 164	84.7 164	83.9 164
STSR [170]	164.1	45.2 164	50.1 163	46.0 164	78.3 164	79.6 164	76.9 164	78.3 164	73.0 164	77.6 164	79.2 164	80.8 164	79.6 164	83.7 164	84.3 164	83.6 164	82.1 164	80.6 164	81.5 164	69.6 165	58.5 165	75.3 165	84.4 164	84.7 164	83.9 164
BMBC [171]	164.1	45.2 164	50.1 163	46.0 164	78.3 164	79.6 164	76.9 164	78.3 164	73.0 164	77.6 164	79.2 164	80.8 164	79.6 164	83.7 164	84.3 164	83.6 164	82.1 164	80.6 164	81.5 164	69.6 165	58.5 165	75.3 165	84.4 164	84.7 164	83.9 164
GDCN [172]	164.1	45.2 164	50.1 163	46.0 164	78.3 164	79.6 164	76.9 164	78.3 164	73.0 164	77.6 164	79.2 164	80.8 164	79.6 164	83.7 164	84.3 164	83.6 164	82.1 164	80.6 164	81.5 164	69.6 165	58.5 165	75.3 165	84.4 164	84.7 164	83.9 164
EDSC [173]	164.1	45.2 164	50.1 163	46.0 164	78.3 164	79.6 164	76.9 164	78.3 164	73.0 164	77.6 164	79.2 164	80.8 164	79.6 164	83.7 164	84.3 164	83.6 164	82.1 164	80.6 164	81.5 164	69.6 165	58.5 165	75.3 165	84.4 164	84.7 164	83.9 164
MV_VFI [183]	164.1	45.2 164	50.1 163	46.0 164	78.3 164	79.6 164	76.9 164	78.3 164	73.0 164	77.6 164	79.2 164	80.8 164	79.6 164	83.7 164	84.3 164	83.6 164	82.1 164	80.6 164	81.5 164	69.6 165	58.5 165	75.3 165	84.4 164	84.7 164	83.9 164
DistillNet [184]	164.1	45.2 164	50.1 163	46.0 164	78.3 164	79.6 164	76.9 164	78.3 164	73.0 164	77.6 164	79.2 164	80.8 164	79.6 164	83.7 164	84.3 164	83.6 164	82.1 164	80.6 164	81.5 164	69.6 165	58.5 165	75.3 165	84.4 164	84.7 164	83.9 164
SepConv++ [185]	164.1	45.2 164	50.1 163	46.0 164	78.3 164	79.6 164	76.9 164	78.3 164	73.0 164	77.6 164	79.2 164	80.8 164	79.6 164	83.7 164	84.3 164	83.6 164	82.1 164	80.6 164	81.5 164	69.6 165	58.5 165	75.3 165	84.4 164	84.7 164	83.9 164
EAFI [186]	164.1	45.2 164	50.1 163	46.0 164	78.3 164	79.6 164	76.9 164	78.3 164	73.0 164	77.6 164	79.2 164	80.8 164	79.6 164	83.7 164	84.3 164	83.6 164	82.1 164	80.6 164	81.5 164	69.6 165	58.5 165	75.3 165	84.4 164	84.7 164	83.9 164
FLAVR [188]	164.1	45.2 164	50.1 163	46.0 164	78.3 164	79.6 164	76.9 164	78.3 164	73.0 164	77.6 164	79.2 164	80.8 164	79.6 164	83.7 164	84.3 164	83.6 164	82.1 164	80.6 164	81.5 164	69.6 165	58.5 165	75.3 165	84.4 164	84.7 164	83.9 164
SoftsplatAug [190]	164.1	45.2 164	50.1 163	46.0 164	78.3 164	79.6 164	76.9 164	78.3 164	73.0 164	77.6 164	79.2 164	80.8 164	79.6 164	83.7 164	84.3 164	83.6 164	82.1 164	80.6 164	81.5 164	69.6 165	58.5 165	75.3 165	84.4 164	84.7 164	83.9 164
ProBoost-Net [191]	164.1	45.2 164	50.1 163	46.0 164	78.3 164	79.6 164	76.9 164	78.3 164	73.0 164	77.6 164	79.2 164	80.8 164	79.6 164	83.7 164	84.3 164	83.6 164	82.1 164	80.6 164	81.5 164	69.6 165	58.5 165	75.3 165	84.4 164	84.7 164	83.9 164
IDIAL [192]	164.1	45.2 164	50.1 163	46.0 164	78.3 164	79.6 164	76.9 164	78.3 164	73.0 164	77.6 164	79.2 164	80.8 164	79.6 164	83.7 164	84.3 164	83.6 164	82.1 164	80.6 164	81.5 164	69.6 165	58.5 165	75.3 165	84.4 164	84.7 164	83.9 164
IFRNet [193]	164.1	45.2 164	50.1 163	46.0 164	78.3 164	79.6 164	76.9 164	78.3 164	73.0 164	77.6 164	79.2 164	80.8 164	79.6 164	83.7 164	84.3 164	83.6 164	82.1 164	80.6 164	81.5 164	69.6 165	58.5 165	75.3 165	84.4 164	84.7 164	83.9 164
AVG_FLOW_ROB [137]	194.6	85.5 199	80.5 199	99.9 199	99.9 199	99.9 199	99.9 199	96.1 199	99.9 199	95.9 199	89.9 199	87.4 199	95.1 199	99.9 199	99.9 199	99.9 199	95.8 199	81.5 199	91.9 199	39.9 164	40.1 164	34.2 164	99.9 199	99.9 199	99.9 199

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	Tarik Arici and Vural Aksakalli. Energy minimization based motion estimation using adaptive smoothness priors. VISAPP 2012.
[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	Duc Dung Nguyen and Jae Wook Jeon. Enhancing accuracy and sharpness of motion field with adaptive scheme and occlusion-aware filter. IET Image Processing 7.2 (2013): 144-153.
[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	Alper Ayvaci, Michalis Raptis, and Stefano Soatto. Sparse occlusion detection with optical flow. IJCV 97(3):322-338, 2012.
[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	Zhuoyuan Chen, Jiang Wang, and Ying Wu. Decomposing and regularizing sparse/non-sparse components for motion field estimation. CVPR 2012.
[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	Michael Santoro, Ghassan AlRegib, and Yucel Altunbasak. Motion estimation using block overlap minimization. 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	Weisheng Dong, Guangming Shi, Xiaocheng Hu, and Yi Ma. Nonlocal sparse and low-rank regularization for optical flow estimation. IEEE TIP 23(10):4527-4538, 2014.
[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] NNF-Local	673	2	color	Zhuoyuan Chen, Hailin Jin, Zhe Lin, Scott Cohen, and Ying Wu. Large displacement optical flow from nearest neighbor fields. CVPR 2013.
[76] Correlation Flow	290	2	color	M. Drulea and S. Nedevschi. Motion estimation using the correlation transform. TIP 2013. Matlab code.
[77] TC/T-Flow	341	5	color	M. Stoll, S. Volz, and A. Bruhn. Joint trilateral filtering for multiframe optical flow. ICIP 2013.
[78] OFLAF	1530	2	color	T. Kim, H. Lee, and K. Lee. Optical flow via locally adaptive fusion of complementary data costs. ICCV 2013.
[79] Periodicity	8000	4	color	Georgii Khachaturov, Silvia Gonzalez-Brambila, and Jesus Gonzalez-Trejo. Periodicity-based computation of optical flow. Computacion y Sistemas (CyS) 2014.
[80] SILK	572	2	gray	Pascal Zille, Thomas Corpetti, Liang Shao, and Xu Chen. Observation model based on scale interactions for optical flow estimation. IEEE TIP 23(8):3281-3293, 2014.
[81] 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.
[82] Classic+CPF	640	2	gray	Zhigang Tu, Nico van der Aa, Coert Van Gemeren, and Remco Veltkamp. A combined post-filtering method to improve accuracy of variational optical flow estimation. Pattern Recognition 47(5):1926-1940, 2014.
[83] S2D-Matching	1200	2	color	Marius Leordeanu, Andrei Zanfir, and Cristian Sminchisescu. Locally affine sparse-to-dense matching for motion and occlusion estimation. ICCV 2013.
[84] AGIF+OF	438	2	gray	Zhigang Tu, Ronald Poppe, and Remco Veltkamp. Adaptive guided image filter for warping in variational optical flow computation. Signal Processing 127:253-265, 2016.
[85] DeepFlow	13	2	color	P. Weinzaepfel, J. Revaud, Z. Harchaoui, and C. Schmid. DeepFlow: large displacement optical flow with deep matching. ICCV 2013.
[86] 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.
[87] 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.
[88] 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.
[89] 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.
[90] 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.
[91] 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.
[92] FMOF	215	2	color	N. Jith, A. Ramakanth, and V. Babu. Optical flow estimation using approximate nearest neighbor field fusion. ICASSP 2014.
[93] TriFlow	150	2	color	TriFlow. Optical flow with geometric occlusion estimation and fusion of multiple frames. ECCV 2014 submission 914.
[94] ComponentFusion	6.5	2	color	Anonymous. Fast optical flow by component fusion. ECCV 2014 submission 941.
[95] 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.
[96] 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.
[97] HCIC-L	330	2	color	Anonymous. Globally-optimal image correspondence using a hierarchical graphical model. NIPS 2014 submission 114.
[98] TF+OM	600	2	color	R. Kennedy and C. Taylor. Optical flow with geometric occlusion estimation and fusion of multiple frames. EMMCVPR 2015.
[99] PH-Flow	800	2	color	J. Yang and H. Li. Dense, accurate optical flow estimation with piecewise parametric model. CVPR 2015.
[100] EpicFlow	16	2	color	J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. EpicFlow: edge-preserving interpolation of correspondences for optical flow. CVPR 2015.
[101] NNF-EAC	380	2	color	Anonymous. Variational method for joint optical flow estimation and edge-aware image restoration. CVPR 2015 submission 2336.
[102] Heeger++	6600	5	gray	Anonymous. A context aware biologically inspired algorithm for optical flow (updated results). CVPR 2015 submission 2238.
[103] HBM-GC	330	2	color	A. Zheng and Y. Yuan. Motion estimation via hierarchical block matching and graph cut. Submitted to ICIP 2015.
[104] 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.
[105] 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.
[106] DeepFlow2	16	2	color	J. Revaud, P. Weinzaepfel, Z. Harchaoui, and C. Schmid. Deep convolutional matching. Submitted to IJCV, 2015.
[107] HAST	2667	2	color	Anonymous. Highly accurate optical flow estimation on superpixel tree. ICCV 2015 submission 2221.
[108] 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.
[109] SVFilterOh	1.56	2	color	Anonymous. Fast estimation of large displacement optical flow using PatchMatch and dominant motion patterns. CVPR 2016 submission 1788.
[110] FlowNetS+ft+v	0.5	2	color	Anonymous. Learning optical flow with convolutional neural networks. ICCV 2015 submission 235.
[111] 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.)
[112] 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.
[113] DF-Auto	70	2	color	N. Monzon, A. Salgado, and J. Sanchez. Regularization strategies for discontinuity-preserving optical flow methods. Submitted to TIP 2015.
[114] CPM-Flow	3	2	color	Anonymous. Efficient coarse-to-fine PatchMatch for large displacement optical flow. CVPR 2016 submission 241.
[115] 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.
[116] Steered-L1	804	2	color	Anonymous. Optical flow estimation via steered-L1 norm. Submitted to WSCG 2016.
[117] 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.
[118] PGM-C	5	2	color	Y. Li. Pyramidal gradient matching for optical flow estimation. Submitted to PAMI 2016.
[119] 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.
[120] FlowNet2	0.091	2	color	Anonymous. FlowNet 2.0: Evolution of optical flow estimation with deep networks. CVPR 2017 submission 900.
[121] S2F-IF	20	2	color	Anonymous. S2F-IF: Slow-to-fast interpolator flow. CVPR 2017 submission 765.
[122] 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.
[123] OAR-Flow	60	2	color	Anonymous. Order-adaptive regularisation for variational optical flow: global, local and in between. SSVM 2017 submission 20.
[124] AdaConv-v1	2.8	2	color	Simon Niklaus, Long Mai, and Feng Liu. (Interpolation results only.) Video frame interpolation via adaptive convolution. CVPR 2017.
[125] SepConv-v1	0.2	2	color	Simon Niklaus, Long Mai, and Feng Liu. (Interpolation results only.) Video frame interpolation via adaptive separable convolution. ICCV 2017.
[126] ProbFlowFields	37	2	color	A. Wannenwetsch, M. Keuper, and S. Roth. ProbFlow: joint optical flow and uncertainty estimation. ICCV 2017.
[127] UnFlow	0.12	2	color	Anonymous. UnFlow: Unsupervised learning of optical flow with a bidirectional census loss. Submitted to AAAI 2018.
[128] 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.
[129] 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.
[130] 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.
[131] EPMNet	0.061	2	color	Anonymous. EPM-convolution multilayer-network for optical flow estimation. ICME 2018 submission 1119.
[132] OFRF	90	2	color	Tan Khoa Mai, Michele Gouiffes, and Samia Bouchafa. Optical flow refinement using iterative propagation under colour, proximity and flow reliability constraints. IET Image Processing 2020.
[133] 3DFlow	328	2	color	J. Chen, Z. Cai, J. Lai, and X. Xie. A filtering based framework for optical flow estimation. IEEE TCSVT 2018.
[134] CtxSyn	0.07	2	color	Simon Niklaus and Feng Liu. (Interpolation results only.) Context-aware synthesis for video frame interpolation. CVPR 2018.
[135] 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.
[136] 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.
[137] AVG_FLOW_ROB	N/A	2	N/A	Average flow field of ROB 2018 training set.
[138] 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.
[139] AugFNG_ROB	0.10	all	color	Anonymous. FusionNet and AugmentedFlowNet: Selective proxy ground truth for training on unlabeled images. ECCV 2018 submission 2834.
[140] ResPWCR_ROB	0.2	2	color	Anonymous. Learning optical flow with residual connections. ROB 2018 submission.
[141] 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.
[142] ProFlow_ROB	76	3	color	Anonymous. ProFlow: Learning to predict optical flow. BMVC 2018 submission 277.
[143] PWC-Net_RVC	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. Also RVC 2020 baseline submission.
[144] WOLF_ROB	0.02	2	color	Anonymous. Reversed deep neural network for optical flow. ROB 2018 submission.
[145] LFNet_ROB	0.068	2	color	Anonymous. Learning a flow network. ROB 2018 submission.
[146] 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.
[147] 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.
[148] ContinualFlow_ROB	0.5	all	color	Michal Neoral, Jan Sochman, and Jiri Matas. Continual occlusions and optical flow estimation. ACCV 2018.
[149] CyclicGen	0.088	2	color	Anonymous. (Interpolation results only.) Deep video frame interpolation using cyclic frame generation. AAAI 2019 submission 323.
[150] TOF-M	0.393	2	color	Tianfan Xue, Baian Chen, Jiajun Wu, Donglai Wei, and William Freeman. Video enhancement with task-oriented flow. arXiv 1711.09078, 2017.
[151] MPRN	0.32	4	color	Anonymous. (Interpolation results only.) Multi-frame pyramid refinement network for video frame interpolation. CVPR 2019 submission 1361.
[152] DAIN	0.13	2	color	Wenbo Bao, Wei-Sheng Lai, Chao Ma, Xiaoyun Zhang, Zhiyong Gao, and Ming-Hsuan Yang. (Interpolation results only.) DAIN: Depth-aware video frame interpolation. CVPR 2019.
[153] FRUCnet	0.65	2	color	Van Thang Nguyen, Kyujoong Lee, and Hyuk-Jae Lee. (Interpolation results only.) A stacked deep MEMC network for frame rate up conversion and its application to HEVC. Submitted to IEEE TCSVT 2019.
[154] OFRI	0.31	2	color	Anonymous. (Interpolation results only.) Efficient video frame interpolation via optical flow refinement. CVPR 2019 submission 6743.
[155] CompactFlow_ROB	0.05	2	color	Anonymous. CompactFlow: spatially shiftable window revisited. CVPR 2019 submission 1387.
[156] SegFlow	3.2	2	color	Jun Chen, Zemin Cai, Jianhuang Lai, and Xiaohua Xie. Efficient segmentation-based PatchMatch for large displacement optical flow estimation. IEEE TCSVT 2018.
[157] HCFN	0.18	2	color	Anonymous. Practical coarse-to-fine optical flow with deep networks. ICCV 2019 submission 116.
[158] FGME	0.23	2	color	Bo Yan, Weimin Tan, Chuming Lin, and Liquan Shen. (Interpolation results only.) Fine-grained motion estimation for video frame interpolation. IEEE Transactions on Broadcasting, 2020.
[159] MS-PFT	0.44	2	color	Xianhang Cheng and Zhenzhong Chen. (Interpolation results only.) A multi-scale position feature transform network for video frame interpolation. IEEE TCSVT 2020.
[160] MEMC-Net+	0.12	2	color	Wenbo Bao, Wei-Sheng Lai, Xiaoyun Zhang, Zhiyong Gao, and Ming-Hsuan Yang. (Interpolation results only.) MEMC-Net: Motion estimation and motion compensation driven neural network for video interpolation and enhancement. Submitted to PAMI 2018.
[161] ADC	0.01	2	color	Anonymous. (Interpolation results only.) Learning spatial transform for video frame interpolation. ICCV 2019 submission 5424.
[162] DSepConv	0.3	2	color	Xianhang Cheng and Zhenzhong Chen. (Interpolation results only.) Video frame interpolation via deformable separable convolution. AAAI 2020.
[163] MAF-net	0.3	2	color	Mengshun Hu, Jing Xiao, Liang Liao, Zheng Wang, Chia-Wen Lin, Mi Wang, and Shinichi Satoh. Capturing small, fast-moving objects: Frame interpolation via recurrent motion enhancement. IEEE TCSVT 2021.
[164] STAR-Net	0.049	2	color	Anonymous. (Interpolation results only.) Space-time-aware multiple resolution for video enhancement. CPVR 2020 submission 430.
[165] AdaCoF	0.03	2	color	Hyeongmin Lee, Taeoh Kim, Tae-young Chung, Daehyun Pak, Yuseok Ban, and Sangyoun Lee. (Interpolation results only.) AdaCoF: Adaptive collaboration of flows for video frame interpolation. CVPR 2020. Code available.
[166] TC-GAN	0.13	2	color	Anonymous. (Interpolation results only.) A temporal and contextual generative adversarial network for video frame interpolation. CVPR 2020 submission 111.
[167] FeFlow	0.52	2	color	Shurui Gui, Chaoyue Wang, Qihua Chen, and Dacheng Tao. (Interpolation results only.) FeatureFlow: Robust video interpolation via structure-to-texture generation. CVPR 2020. Code available.
[168] DAI	0.23	2	color	Anonymous. (Interpolation results only.) Deep animation inbetweening. CVPR 2020 submission 6404.
[169] SoftSplat	0.1	2	color	Simon Niklaus and Feng Liu. (Interpolation results only.) Softmax splatting for video frame interpolation. CVPR 2020.
[170] STSR	5.35	2	color	Anonymous. (Interpolation results only.) Spatial and temporal video super-resolution with a frequency domain loss. ECCV 2020 submission 2340.
[171] BMBC	0.77	2	color	Anonymous. (Interpolation results only.) BMBC: Bilateral motion estimation with bilateral cost volume for video interpolation. ECCV 2020 submission 2095.
[172] GDCN	1.0	2	color	Anonymous. (Interpolation results only.) Video interpolation via generalized deformable convolution. ECCV 2020 submission 4347.
[173] EDSC	0.56	2	color	Xianhang Cheng and Zhenzhong Chen. (Interpolation results only.) Multiple video frame interpolation via enhanced deformable separable convolution. Submitted to PAMI 2020.
[174] CoT-AMFlow	0.04	2	color	Anonymous. CoT-AMFlow: Adaptive modulation network with co-teaching strategy for unsupervised optical flow estimation. CoRL 2020 submission 36.
[175] TVL1_RVC	11.6	2	color	RVC 2020 baseline submission by Toby Weed, based on: Javier Sanchez, Enric Meinhardt-Llopis, and Gabriele Facciolo. TV-L1 optical flow estimation. IPOL 3:137-150, 2013.
[176] H+S_RVC	44.7	2	color	RVC 2020 baseline submission by Toby Weed, based on: Enric Meinhardt-Llopis, Javier Sanchez, and Daniel Kondermann. Horn-Schunck optical flow with a multi-scale strategy. IPOL 3:151–172, 2013.
[177] PRAFlow_RVC	0.34	2	color	Zhexiong Wan, Yuxin Mao, and Yuchao Dai. Pyramid recurrent all-pairs flow. RVC 2020 submission.
[178] VCN_RVC	0.84	2	color	Gengshan Yang and Deva Ramanan. Volumetric correspondence networks for optical flow. NeurIPS 2019. RVC 2020 submission.
[179] RAFT-TF_RVC	1.51	2	color	Deqing Sun, Charles Herrmann, Varun Jampani, Mike Krainin, Forrester Cole, Austin Stone, Rico Jonschkowski, Ramin Zabih, William Freeman, and Ce Liu. A TensorFlow implementation of RAFT (Zachary Teed and Jia Deng. RAFT: Recurrent all-pairs field transforms for optical flow. ECCV 2020.) RVC 2020 submission.
[180] IRR-PWC_RVC	0.18	2	color	Junhwa Hur and Stefan Roth. Iterative residual refinement for joint optical flow and occlusion estimation. CVPR 2019. RVC 2020 submission.
[181] C-RAFT_RVC	0.60	2	color	Henrique Morimitsu and Xiangyang Ji. Classification RAFT. RVC 2020 submission.
[182] LSM_FLOW_RVC	0.2	2	color	Chengzhou Tang, Lu Yuan, and Ping Tan. LSM: Learning subspace minimization for low-level vision. CVPR 2020. RVC 2020 submission.
[183] MV_VFI	0.23	2	color	Zhenfang Wang, Yanjiang Wang, and Baodi Liu. (Interpolation results only.) Multi-view based video interpolation algorithm. ICASSP 2021 submission.
[184] DistillNet	0.12	2	color	Anonymous. (Interpolation results only.) A teacher-student optical-flow distillation framework for video frame interpolation. CVPR 2021 submission 7534.
[185] SepConv++	0.1	2	color	Simon Niklaus, Long Mai, and Oliver Wang. (Interpolation results only.) Revisiting adaptive convolutions for video frame interpolation. WACV 2021.
[186] EAFI	0.18	2	color	Anonymous. (Interpolation results only.) Error-aware spatial ensembles for video frame interpolation. ICCV 2021 submission 8020.
[187] UnDAF	0.04	2	color	Anonymous. UnDAF: A general unsupervised domain adaptation framework for disparity, optical flow or scene flow estimation. CVPR 2021 submission 236.
[188] FLAVR	0.029	all	color	Anonymous. (Interpolation results only.) FLAVR frame interpolation. NeurIPS 2021 submission 1300.
[189] PBOFVI	150	2	color	Zemin Cai, Jianhuang Lai, Xiaoxin Liao, and Xucong Chen. Physics-based optical flow under varying illumination. Submitted to IEEE TCSVT 2021.
[190] SoftsplatAug	0.17	2	color	Anonymous. (Interpolation results only.) Transformation data augmentation for sports video frame interpolation. ICCV 2021 submission 3245.

* 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.