Optical flow evaluation results: SD endpoint error

Optical flow evaluation results	Statistics: Average SD R0.5 R1.0 R2.0 A50 A75 A95 Error type: endpoint angle interpolation normalized interpolation
Show images: below table above table

SD endpoint error	avg.	Army (Hidden texture) GT im0 im1			Mequon (Hidden texture) GT im0 im1			Schefflera (Hidden texture) GT im0 im1			Wooden (Hidden texture) GT im0 im1			Grove (Synthetic) GT im0 im1			Urban (Synthetic) GT im0 im1			Yosemite (Synthetic) GT im0 im1			Teddy (Stereo) GT im0 im1
	rank	all	disc	untext	all	disc	untext	all	disc	untext	all	disc	untext	all	disc	untext	all	disc	untext	all	disc	untext	all	disc	untext
ComplexFlow [81]	4.5	0.20 14	0.44 12	0.10 4	0.38 1	0.90 1	0.17 1	0.48 2	0.87 3	0.14 2	0.41 1	1.24 3	0.09 2	0.82 1	1.02 1	0.34 2	0.73 1	1.77 3	0.54 1	0.11 10	0.12 31	0.13 8	0.80 1	1.37 1	0.45 2
NN-field [73]	10.3	0.21 23	0.47 31	0.11 12	0.38 1	0.92 3	0.17 1	0.51 4	0.93 5	0.15 4	0.43 3	1.30 5	0.08 1	0.83 2	1.03 2	0.32 1	1.72 42	1.98 8	1.12 41	0.12 15	0.12 31	0.13 8	0.85 2	1.46 2	0.43 1
MDP-Flow2 [70]	10.6	0.19 6	0.44 12	0.10 4	0.40 4	0.97 4	0.18 5	0.55 9	1.01 9	0.16 5	0.69 26	1.78 35	0.36 16	1.30 17	1.58 20	1.09 20	0.82 3	1.86 6	0.70 4	0.12 15	0.10 8	0.15 15	0.89 3	1.55 4	0.92 4
OFLADF [82]	11.2	0.19 6	0.44 12	0.10 4	0.45 8	1.08 17	0.19 6	0.53 6	0.98 8	0.13 1	0.76 39	2.04 59	0.40 33	1.15 6	1.43 7	0.63 5	0.78 2	1.71 1	0.66 2	0.11 10	0.10 8	0.13 8	1.00 5	1.50 3	1.44 12
Epistemic [84]	13.2	0.19 6	0.44 12	0.10 4	0.47 13	1.15 23	0.20 10	0.58 10	1.06 10	0.20 8	0.51 4	1.52 7	0.15 3	1.50 32	1.81 40	1.29 28	0.95 7	2.13 11	0.80 9	0.13 21	0.10 8	0.16 21	1.05 8	1.72 13	1.29 8
IROF++ [58]	16.8	0.21 23	0.47 31	0.11 12	0.47 13	1.05 10	0.28 19	0.90 21	1.54 21	0.27 14	0.64 13	1.59 14	0.36 16	1.21 10	1.48 10	0.94 12	1.30 16	2.41 17	0.97 23	0.09 5	0.11 18	0.11 6	1.24 22	1.93 26	1.72 32
Correlation Flow [79]	17.0	0.20 14	0.44 12	0.08 1	0.47 13	1.07 14	0.17 1	1.49 53	2.29 61	0.35 31	0.42 2	1.12 2	0.24 5	1.45 28	1.72 29	1.28 26	1.13 8	1.79 4	0.89 15	0.14 27	0.11 18	0.17 26	1.01 6	1.64 8	1.10 5
ADF [67]	19.5	0.19 6	0.41 6	0.11 12	0.48 19	1.16 29	0.29 23	0.95 24	1.68 29	0.30 21	0.78 43	1.96 48	0.35 10	1.46 29	1.72 29	1.33 32	1.18 11	1.84 5	0.89 15	0.12 15	0.10 8	0.15 15	1.09 12	1.68 10	1.48 17
Layers++ [37]	20.7	0.20 14	0.44 12	0.11 12	0.41 6	0.98 5	0.24 14	0.53 6	0.96 7	0.25 12	0.75 37	1.82 38	0.43 42	1.12 3	1.37 3	0.88 9	1.39 21	2.27 13	1.09 39	0.16 38	0.13 48	0.18 31	1.25 25	1.87 22	1.80 39
LME [72]	20.8	0.21 23	0.48 44	0.11 12	0.40 4	0.99 7	0.17 1	0.89 19	1.50 18	0.68 61	0.68 24	1.63 19	0.50 54	1.33 20	1.56 17	1.29 28	1.17 10	2.77 32	0.83 12	0.13 21	0.11 18	0.17 26	1.07 9	1.68 10	1.39 11
NL-TV-NCC [25]	21.0	0.20 14	0.44 12	0.09 2	0.47 13	1.07 14	0.19 6	1.16 38	1.95 42	0.31 23	0.53 6	1.42 6	0.24 5	1.37 24	1.61 23	1.14 23	2.07 53	2.39 16	1.47 54	0.16 38	0.09 2	0.19 34	1.24 22	1.93 26	1.29 8
FESL [75]	21.9	0.20 14	0.46 26	0.10 4	0.54 34	1.16 29	0.31 30	0.82 15	1.43 14	0.27 14	0.64 13	1.60 16	0.34 9	1.23 11	1.49 11	0.96 14	1.38 20	2.51 23	0.92 19	0.16 38	0.13 48	0.22 40	1.33 33	1.98 31	1.53 19
FC-2Layers-FF [77]	22.2	0.20 14	0.45 22	0.11 12	0.51 25	1.18 34	0.28 19	0.53 6	0.94 6	0.24 11	0.79 46	2.00 51	0.43 42	1.18 7	1.43 7	0.89 10	1.44 25	2.63 27	0.99 27	0.16 38	0.12 31	0.19 34	1.09 12	1.69 12	1.45 14
nLayers [57]	23.2	0.20 14	0.46 26	0.11 12	0.43 7	0.98 5	0.25 15	0.67 12	1.18 12	0.29 19	0.90 57	2.34 74	0.52 57	1.25 13	1.53 16	0.93 11	1.33 17	2.21 12	0.94 22	0.14 27	0.12 31	0.18 31	1.22 19	1.96 29	1.51 18
LSM [39]	23.6	0.20 14	0.45 22	0.12 26	0.54 34	1.16 29	0.32 32	0.91 22	1.53 20	0.34 27	0.62 9	1.55 10	0.36 16	1.31 19	1.57 18	1.07 18	1.42 23	2.41 17	0.99 27	0.17 50	0.11 18	0.22 40	1.25 25	1.83 19	1.72 32
Sparse-NonSparse [56]	24.6	0.21 23	0.46 26	0.12 26	0.54 34	1.17 33	0.32 32	0.93 23	1.56 22	0.34 27	0.64 13	1.60 16	0.36 16	1.33 20	1.59 21	1.07 18	1.43 24	2.48 21	0.99 27	0.17 50	0.10 8	0.22 40	1.24 22	1.82 18	1.70 30
EP-PM [83]	25.5	0.22 40	0.44 12	0.11 12	0.46 11	1.07 14	0.19 6	0.81 13	1.43 14	0.20 8	0.66 20	1.72 27	0.36 16	1.18 7	1.45 9	0.64 6	2.02 52	2.80 34	1.44 52	0.28 79	0.13 48	0.37 73	1.19 16	1.80 16	1.66 27
SCR [74]	25.8	0.21 23	0.48 44	0.11 12	0.53 30	1.15 23	0.28 19	0.88 18	1.50 18	0.35 31	0.65 17	1.65 21	0.35 10	1.26 15	1.52 13	0.99 15	1.56 36	2.81 35	1.02 35	0.19 58	0.12 31	0.28 60	1.20 17	1.77 15	1.60 24
Ramp [62]	25.9	0.21 23	0.46 26	0.12 26	0.50 22	1.10 18	0.31 30	0.87 17	1.49 17	0.34 27	0.63 11	1.57 11	0.35 10	1.30 17	1.57 18	1.09 20	1.52 33	2.75 30	1.02 35	0.20 63	0.12 31	0.33 68	1.22 19	1.81 17	1.72 32
PMF [76]	26.4	0.21 23	0.47 31	0.11 12	0.45 8	1.03 8	0.20 10	0.48 2	0.85 2	0.14 2	0.80 49	2.12 64	0.38 25	1.12 3	1.38 5	0.54 3	3.68 62	2.46 20	2.72 63	0.21 67	0.21 83	0.28 60	1.04 7	1.55 4	1.55 20
TC/T-Flow [80]	26.4	0.17 1	0.38 1	0.11 12	0.60 47	1.24 45	0.33 36	1.00 31	1.72 32	0.20 8	0.75 37	2.02 55	0.36 16	1.44 27	1.66 25	1.38 35	0.94 6	2.11 10	0.81 10	0.15 35	0.13 48	0.24 51	1.27 27	1.89 24	1.45 14
IROF-TV [53]	26.4	0.21 23	0.46 26	0.13 37	0.51 25	1.13 19	0.33 36	0.98 29	1.60 24	0.30 21	0.71 29	1.77 34	0.40 33	1.33 20	1.60 22	1.10 22	1.51 32	3.56 61	0.99 27	0.08 3	0.10 8	0.10 4	1.31 31	2.07 33	1.74 35
CostFilter [40]	26.7	0.21 23	0.47 31	0.11 12	0.47 13	1.05 10	0.22 12	0.43 1	0.75 1	0.18 6	0.76 39	1.95 47	0.38 25	1.12 3	1.37 3	0.56 4	3.23 58	2.45 19	2.50 60	0.22 68	0.20 82	0.31 66	1.20 17	1.85 21	1.55 20
Classic+NL [31]	27.0	0.21 23	0.47 31	0.12 26	0.53 30	1.15 23	0.32 32	0.96 27	1.62 25	0.35 31	0.65 17	1.63 19	0.36 16	1.27 16	1.52 13	1.03 16	1.53 34	2.77 32	0.98 25	0.17 50	0.12 31	0.23 45	1.27 27	1.87 22	1.78 38
Levin3 [90]	27.2	0.21 23	0.47 31	0.11 12	0.54 34	1.16 29	0.28 19	0.97 28	1.63 26	0.34 27	0.64 13	1.58 13	0.35 10	1.23 11	1.50 12	0.85 8	1.47 29	2.53 24	0.98 25	0.25 76	0.14 59	0.40 76	1.23 21	1.83 19	1.69 29
Efficient-NL [60]	27.3	0.21 23	0.47 31	0.11 12	0.47 13	1.06 13	0.27 17	1.07 34	1.79 35	0.31 23	0.66 20	1.66 23	0.37 23	1.25 13	1.52 13	0.94 12	4.42 66	3.42 53	2.99 66	0.18 55	0.12 31	0.26 56	1.07 9	1.60 7	1.19 7
Sparse Occlusion [54]	27.6	0.20 14	0.44 12	0.13 37	0.45 8	1.03 8	0.26 16	1.26 40	2.12 50	0.35 31	0.71 29	1.80 36	0.37 23	1.41 25	1.69 26	1.05 17	0.90 5	2.03 9	0.67 3	0.19 58	0.22 86	0.23 45	1.31 31	2.07 33	1.55 20
MDP-Flow [26]	27.8	0.18 3	0.38 1	0.12 26	0.39 3	0.90 1	0.29 23	0.62 11	1.11 11	0.33 26	0.63 11	1.73 29	0.31 8	1.63 53	1.72 29	1.99 75	1.73 43	1.86 6	1.40 51	0.13 21	0.13 48	0.15 15	2.01 55	2.98 59	2.17 60
TV-L1-MCT [64]	28.8	0.21 23	0.48 44	0.12 26	0.56 41	1.19 36	0.30 26	1.05 33	1.79 35	0.35 31	0.62 9	1.54 8	0.35 10	1.35 23	1.61 23	1.14 23	1.46 28	2.50 22	1.00 33	0.15 35	0.10 8	0.36 71	1.33 33	1.94 28	1.83 41
Direct ZNCC [66]	29.8	0.21 23	0.48 44	0.09 2	0.52 27	1.19 36	0.32 32	1.53 56	2.30 66	0.37 36	0.52 5	1.26 4	0.30 7	1.59 42	1.84 47	1.51 44	1.76 44	2.63 27	1.36 50	0.14 27	0.11 18	0.18 31	1.15 15	1.91 25	1.13 6
COFM [59]	30.2	0.23 46	0.52 61	0.13 37	0.52 27	1.14 20	0.30 26	0.89 19	1.56 22	0.31 23	0.84 55	2.18 68	0.42 40	1.50 32	1.75 33	1.51 44	0.86 4	1.73 2	0.75 6	0.19 58	0.11 18	0.25 54	1.07 9	1.65 9	1.44 12
DPOF [18]	32.9	0.23 46	0.47 31	0.14 47	0.60 47	1.21 41	0.41 53	0.52 5	0.92 4	0.19 7	0.71 29	1.73 29	0.44 47	1.18 7	1.42 6	0.73 7	3.53 61	2.98 39	2.25 58	0.38 84	0.13 48	0.47 80	0.95 4	1.58 6	0.78 3
ALD-Flow [68]	33.1	0.18 3	0.39 4	0.10 4	0.63 52	1.30 48	0.36 40	0.98 29	1.71 31	0.28 17	0.82 52	2.00 51	0.39 28	1.59 42	1.84 47	1.57 53	1.63 40	3.34 49	0.93 20	0.14 27	0.12 31	0.22 40	1.29 29	1.98 31	1.65 26
TCOF [71]	33.4	0.21 23	0.44 12	0.13 37	0.52 27	1.15 23	0.30 26	1.59 60	2.33 70	0.58 54	0.68 24	1.72 27	0.39 28	1.58 40	1.82 43	1.55 50	1.24 14	2.33 14	0.86 13	0.22 68	0.12 31	0.39 75	1.13 14	1.75 14	1.45 14
ACK-Prior [27]	33.4	0.18 3	0.39 4	0.10 4	0.46 11	1.05 10	0.19 6	0.82 15	1.46 16	0.25 12	0.59 8	1.65 21	0.22 4	1.50 32	1.74 32	1.42 38	6.47 87	4.94 84	4.41 87	0.28 79	0.17 72	0.37 73	1.67 40	2.35 39	1.62 25
TC-Flow [46]	34.4	0.17 1	0.38 1	0.10 4	0.50 22	1.15 23	0.27 17	1.09 35	1.88 38	0.29 19	0.77 42	2.01 53	0.39 28	1.54 36	1.80 37	1.43 40	2.11 55	3.56 61	1.17 43	0.15 35	0.12 31	0.25 54	1.69 41	2.50 43	2.24 66
OFH [38]	36.2	0.19 6	0.41 6	0.12 26	0.56 41	1.23 43	0.34 38	1.39 47	2.10 47	0.37 36	0.82 52	2.24 70	0.40 33	1.60 49	1.84 47	1.61 56	1.85 48	3.78 64	1.46 53	0.09 5	0.09 2	0.11 6	1.35 35	2.15 35	1.58 23
Complementary OF [21]	36.4	0.19 6	0.41 6	0.12 26	0.49 20	1.14 20	0.22 12	0.95 24	1.67 28	0.27 14	0.76 39	2.03 56	0.38 25	1.73 68	1.91 64	1.91 71	6.38 86	4.41 80	4.34 86	0.10 8	0.09 2	0.16 21	1.42 36	2.15 35	1.81 40
ComplOF-FED-GPU [35]	36.5	0.19 6	0.41 6	0.12 26	0.59 44	1.24 45	0.36 40	0.95 24	1.66 27	0.28 17	0.79 46	2.03 56	0.40 33	1.57 38	1.80 37	1.58 55	4.00 65	3.34 49	2.67 62	0.14 27	0.11 18	0.23 45	1.46 37	2.27 37	1.74 35
SimpleFlow [49]	37.3	0.21 23	0.47 31	0.12 26	0.55 39	1.20 38	0.34 38	1.45 48	2.19 54	0.41 42	0.66 20	1.68 24	0.35 10	1.41 25	1.69 26	1.16 25	5.06 75	4.23 76	3.40 72	0.16 38	0.12 31	0.23 45	1.29 29	1.97 30	1.70 30
Occlusion-TV-L1 [63]	39.5	0.22 40	0.47 31	0.13 37	0.53 30	1.18 34	0.38 45	1.58 57	2.36 76	0.54 51	0.74 33	1.76 33	0.42 40	1.55 37	1.81 40	1.35 33	1.60 37	2.98 39	1.22 44	0.09 5	0.11 18	0.09 2	2.10 60	3.06 67	2.16 59
SegOF [10]	42.5	0.24 57	0.48 44	0.18 68	0.71 62	1.35 57	0.58 65	1.31 43	1.92 40	0.73 62	0.54 7	1.09 1	0.41 37	1.62 52	1.79 36	1.64 58	5.27 77	4.17 75	3.63 77	0.07 1	0.10 8	0.10 4	1.49 38	2.48 42	1.35 10
Aniso. Huber-L1 [22]	42.8	0.23 46	0.48 44	0.15 54	0.60 47	1.26 47	0.39 47	1.66 66	2.29 61	0.50 48	0.69 26	1.59 14	0.39 28	1.59 42	1.82 43	1.55 50	1.21 13	2.86 36	0.72 5	0.19 58	0.14 59	0.29 64	1.72 42	2.64 45	1.84 42
CBF [12]	43.7	0.19 6	0.41 6	0.12 26	0.55 39	1.14 20	0.45 56	1.36 46	2.04 46	0.47 45	0.81 51	2.01 53	0.44 47	1.65 56	1.91 64	1.68 59	1.13 8	2.54 26	0.76 7	0.29 82	0.17 72	0.42 77	1.91 48	2.85 52	2.10 56
Adaptive [20]	44.8	0.23 46	0.50 57	0.14 47	0.57 43	1.30 48	0.39 47	1.72 71	2.49 83	0.56 53	0.74 33	1.71 26	0.43 42	1.49 31	1.76 34	1.30 30	1.45 26	2.53 24	0.99 27	0.17 50	0.17 72	0.20 38	1.91 48	2.83 50	2.00 50
SIOF [69]	45.5	0.24 57	0.52 61	0.13 37	0.68 58	1.40 59	0.48 59	1.50 55	2.15 52	0.83 64	0.82 52	1.94 46	0.49 53	1.66 59	1.88 57	1.80 63	1.35 18	2.87 37	0.97 23	0.12 15	0.11 18	0.15 15	1.72 42	2.55 44	1.99 49
CRTflow [88]	46.1	0.21 23	0.42 11	0.14 47	0.67 56	1.40 59	0.37 42	1.59 60	2.32 69	0.55 52	0.97 62	2.37 77	0.53 59	1.63 53	1.91 64	1.54 49	1.60 37	3.74 63	0.89 15	0.11 10	0.11 18	0.16 21	1.93 51	2.97 57	2.01 51
LocallyOriented [52]	46.5	0.29 70	0.60 74	0.15 54	0.77 65	1.42 62	0.57 64	1.63 64	2.29 61	0.49 47	0.66 20	1.57 11	0.41 37	1.59 42	1.80 37	1.55 50	3.32 59	3.50 57	2.32 59	0.11 10	0.11 18	0.16 21	1.72 42	2.45 40	2.03 52
Brox et al. [5]	48.3	0.22 40	0.45 22	0.15 54	0.68 58	1.58 71	0.40 49	1.11 36	1.89 39	0.40 41	0.93 60	2.16 66	0.51 55	1.78 73	1.95 74	2.00 77	2.88 57	3.52 59	2.02 57	0.08 3	0.11 18	0.09 2	1.97 54	2.81 49	1.94 46
SuperFlow [89]	49.0	0.25 61	0.48 44	0.15 54	0.63 52	1.21 41	0.50 60	1.30 41	1.97 43	0.88 67	0.80 49	1.88 42	0.46 50	1.69 61	1.92 69	1.79 62	1.61 39	3.20 45	1.09 39	0.13 21	0.15 64	0.14 12	2.09 59	2.93 55	1.93 45
Deep-Matching [85]	49.2	0.26 63	0.49 54	0.16 62	0.86 69	1.37 58	0.69 70	1.30 41	1.99 45	0.81 63	1.04 68	2.43 79	0.68 67	1.53 35	1.81 40	1.37 34	1.47 29	3.46 56	0.89 15	0.11 10	0.09 2	0.17 26	2.23 65	3.06 67	2.20 63
Classic++ [32]	49.7	0.22 40	0.48 44	0.15 54	0.60 47	1.34 55	0.38 45	1.35 45	2.10 47	0.44 43	0.84 55	2.08 62	0.44 47	1.59 42	1.88 57	1.39 36	1.47 29	3.17 43	1.04 38	0.20 63	0.14 59	0.27 58	2.11 61	3.01 63	2.17 60
p-harmonic [29]	50.2	0.23 46	0.48 44	0.15 54	0.54 34	1.20 38	0.40 49	1.62 63	2.29 61	0.61 56	0.78 43	1.75 31	0.53 59	1.75 71	1.92 69	1.99 75	1.45 26	3.28 48	0.99 27	0.16 38	0.15 64	0.16 21	2.17 63	3.06 67	2.12 57
CLG-TV [48]	50.6	0.23 46	0.49 54	0.14 47	0.59 44	1.30 48	0.37 42	1.67 67	2.39 77	0.48 46	0.74 33	1.70 25	0.41 37	1.64 55	1.90 62	1.52 47	1.55 35	3.54 60	0.93 20	0.23 71	0.19 80	0.36 71	1.89 47	2.88 54	1.95 47
FastOF [78]	53.4	0.26 63	0.54 66	0.16 62	0.92 71	1.54 70	0.68 69	1.58 57	2.11 49	0.96 70	0.78 43	1.87 40	0.51 55	1.69 61	1.91 64	1.84 68	2.08 54	3.89 68	1.32 47	0.16 38	0.11 18	0.19 34	1.87 46	2.47 41	1.66 27
TriangleFlow [30]	53.8	0.25 61	0.55 69	0.13 37	0.69 60	1.53 69	0.40 49	1.47 52	2.19 54	0.38 38	0.74 33	1.87 40	0.43 42	1.81 77	2.00 80	1.98 73	2.41 56	2.89 38	1.74 56	0.19 58	0.18 78	0.24 51	1.52 39	2.29 38	1.86 43
Local-TV-L1 [65]	53.9	0.28 68	0.53 64	0.17 65	1.04 74	1.49 66	0.91 80	1.80 74	2.24 59	1.00 72	0.92 59	2.16 66	0.54 62	1.94 85	1.87 54	1.41 37	1.18 11	2.67 29	0.81 10	0.12 15	0.10 8	0.14 12	2.34 71	3.52 85	2.36 68
Filter Flow [19]	54.0	0.28 68	0.54 66	0.19 69	0.69 60	1.31 52	0.51 61	1.45 48	1.98 44	1.02 73	1.13 72	1.82 38	1.04 75	1.71 64	1.83 45	2.04 79	1.28 15	2.37 15	1.01 34	0.16 38	0.16 70	0.17 26	2.29 68	2.98 59	2.12 57
StereoFlow [44]	54.2	0.52 86	0.77 87	0.38 86	1.21 84	1.73 83	0.91 80	1.49 53	1.92 40	0.99 71	1.41 83	2.88 87	1.03 74	1.59 42	1.84 47	1.52 47	1.36 19	3.16 42	0.78 8	0.07 1	0.09 2	0.08 1	2.06 57	3.00 61	2.17 60
F-TV-L1 [15]	54.5	0.26 63	0.54 66	0.15 54	0.86 69	1.50 67	0.61 67	1.73 72	2.31 68	0.65 59	1.00 66	2.46 81	0.52 57	1.57 38	1.84 47	1.42 38	1.66 41	3.42 53	1.15 42	0.14 27	0.18 78	0.13 8	1.95 52	2.97 57	1.76 37
Second-order prior [8]	54.8	0.22 40	0.47 31	0.14 47	0.65 55	1.33 53	0.46 57	1.64 65	2.30 66	0.52 50	0.79 46	1.89 43	0.48 52	1.66 59	1.89 61	1.70 60	1.78 46	3.44 55	1.47 54	0.23 71	0.14 59	0.32 67	2.04 56	2.83 50	2.44 72
Fusion [6]	55.1	0.23 46	0.48 44	0.16 62	0.50 22	1.23 43	0.30 26	0.81 13	1.32 13	0.38 38	0.72 32	1.92 44	0.47 51	1.83 81	2.04 84	2.00 77	5.51 79	3.26 46	3.93 80	0.20 63	0.19 80	0.26 56	2.56 79	3.51 84	2.80 80
TV-L1-improved [17]	55.2	0.22 40	0.47 31	0.14 47	0.53 30	1.20 38	0.37 42	1.71 70	2.48 82	0.60 55	0.98 65	2.45 80	0.54 62	1.61 50	1.87 54	1.50 43	4.77 71	3.84 66	3.21 68	0.18 55	0.17 72	0.22 40	1.96 53	2.94 56	2.08 55
Shiralkar [42]	55.2	0.23 46	0.45 22	0.13 37	0.72 63	1.43 63	0.46 57	1.70 68	2.33 70	0.61 56	0.91 58	2.03 56	0.57 64	1.61 50	1.83 45	1.57 53	1.89 49	3.02 41	1.26 45	0.24 73	0.13 48	0.33 68	2.28 66	3.05 65	2.20 63
GraphCuts [14]	55.6	0.24 57	0.47 31	0.17 65	1.17 82	1.72 81	0.90 79	1.12 37	1.70 30	0.83 64	0.69 26	1.60 16	0.39 28	1.46 29	1.69 26	1.31 31	6.11 85	3.97 70	4.27 84	0.24 73	0.13 48	0.34 70	2.36 73	3.16 74	2.54 76
Rannacher [23]	57.0	0.23 46	0.50 57	0.15 54	0.59 44	1.33 53	0.41 53	1.76 73	2.51 86	0.64 58	0.97 62	2.38 78	0.53 59	1.59 42	1.86 53	1.43 40	4.79 72	3.91 69	3.22 69	0.17 50	0.13 48	0.24 51	1.83 45	2.86 53	2.06 54
Bartels [41]	57.9	0.23 46	0.50 57	0.13 37	0.49 20	1.15 23	0.29 23	1.01 32	1.78 33	0.38 38	1.07 71	2.60 84	0.63 66	1.71 64	1.97 76	1.82 64	4.54 68	3.85 67	3.40 72	0.28 79	0.14 59	0.51 83	2.36 73	3.22 77	2.66 78
Dynamic MRF [7]	60.1	0.24 57	0.52 61	0.14 47	0.62 51	1.43 63	0.40 49	1.33 44	2.16 53	0.45 44	0.94 61	2.23 69	0.58 65	1.81 77	2.01 82	1.91 71	4.83 73	4.05 74	3.55 76	0.14 27	0.09 2	0.23 45	2.75 83	3.57 86	2.97 82
IAOF2 [51]	60.3	0.26 63	0.53 64	0.20 71	0.80 66	1.59 74	0.56 63	1.58 57	2.33 70	0.86 66	1.18 76	1.81 37	1.13 79	1.65 56	1.90 62	1.62 57	1.83 47	2.75 30	1.34 49	0.24 73	0.15 64	0.47 80	1.92 50	2.66 46	1.98 48
Ad-TV-NDC [36]	60.5	0.38 80	0.62 78	0.32 82	1.53 86	1.77 84	1.42 86	2.25 87	2.56 88	1.17 82	0.97 62	1.75 31	0.85 72	1.58 40	1.88 57	1.28 26	1.39 21	3.26 46	0.86 13	0.14 27	0.13 48	0.15 15	2.80 84	3.12 72	3.41 85
2D-CLG [1]	63.0	0.47 84	0.75 86	0.32 82	0.74 64	1.30 48	0.62 68	1.89 77	2.29 61	1.15 81	1.26 79	1.97 49	1.16 80	1.80 76	1.92 69	2.04 79	4.75 70	3.83 65	3.27 70	0.10 8	0.08 1	0.14 12	2.34 71	3.00 61	2.44 72
IAOF [50]	64.4	0.27 67	0.51 60	0.20 71	1.10 79	1.70 79	0.82 74	2.57 89	2.92 90	1.22 85	1.15 73	1.93 45	1.09 77	1.65 56	1.88 57	1.74 61	1.77 45	3.35 51	1.02 35	0.18 55	0.12 31	0.28 60	2.44 76	2.78 48	2.86 81
GroupFlow [9]	64.8	0.33 75	0.60 74	0.22 78	1.08 76	1.71 80	0.85 75	1.61 62	2.13 51	0.94 68	0.65 17	1.54 8	0.43 42	2.01 86	2.22 87	1.45 42	5.60 80	4.02 72	3.86 79	0.26 77	0.16 70	0.46 79	2.08 58	2.72 47	2.41 71
Nguyen [33]	65.0	0.33 75	0.59 73	0.21 74	1.00 73	1.60 76	0.81 73	2.10 82	2.46 80	1.13 79	1.32 80	2.07 61	1.22 81	1.73 68	1.92 69	1.89 70	2.00 50	3.97 70	1.33 48	0.13 21	0.12 31	0.17 26	2.31 69	3.02 64	2.34 67
Learning Flow [11]	65.4	0.23 46	0.49 54	0.13 37	0.64 54	1.44 65	0.41 53	1.46 50	2.20 56	0.50 48	1.15 73	2.26 71	0.86 73	2.05 87	2.32 88	2.04 79	5.24 76	5.18 88	3.43 74	0.16 38	0.17 72	0.28 60	2.47 77	3.29 81	2.39 70
Modified CLG [34]	67.5	0.31 73	0.57 72	0.21 74	0.67 56	1.34 55	0.53 62	1.89 77	2.34 74	1.11 78	1.06 69	2.28 72	0.75 70	1.82 80	1.99 78	2.06 82	3.91 63	4.32 78	2.86 65	0.16 38	0.13 48	0.27 58	2.14 62	3.09 70	2.21 65
Horn & Schunck [3]	67.9	0.36 78	0.62 78	0.23 79	0.98 72	1.58 71	0.77 72	1.88 76	2.26 60	1.13 79	1.36 82	2.15 65	1.22 81	1.69 61	1.84 47	1.83 66	3.92 64	4.34 79	2.78 64	0.16 38	0.15 64	0.23 45	2.40 75	3.05 65	2.38 69
SPSA-learn [13]	68.2	0.33 75	0.61 76	0.21 74	1.09 78	1.83 85	0.85 75	1.82 75	2.33 70	1.05 74	1.23 77	2.31 73	1.06 76	1.79 75	1.96 75	1.98 73	5.61 81	4.52 82	3.84 78	0.12 15	0.10 8	0.15 15	2.48 78	3.21 76	2.45 74
TI-DOFE [24]	69.2	0.46 83	0.69 82	0.35 84	1.16 81	1.59 74	1.03 83	2.17 85	2.39 77	1.27 86	1.43 84	2.04 59	1.34 84	1.71 64	1.87 54	1.83 66	3.36 60	4.03 73	2.58 61	0.13 21	0.12 31	0.20 38	2.67 81	3.12 72	2.76 79
Black & Anandan [4]	69.5	0.31 73	0.55 69	0.20 71	1.08 76	1.68 78	0.85 75	2.00 80	2.41 79	1.07 76	1.03 67	1.99 50	0.83 71	1.71 64	1.91 64	1.82 64	4.64 69	5.05 85	3.01 67	0.20 63	0.17 72	0.30 65	2.28 66	3.09 70	2.04 53
LDOF [28]	69.8	0.29 70	0.61 76	0.17 65	0.81 67	1.58 71	0.59 66	1.17 39	1.78 33	0.67 60	2.17 87	5.16 90	1.57 85	1.78 73	2.01 82	1.86 69	4.52 67	4.42 81	3.33 71	0.22 68	0.22 86	0.47 80	2.21 64	3.27 80	1.92 44
HBpMotionGpu [43]	70.3	0.36 78	0.67 80	0.21 74	1.07 75	1.85 86	0.88 78	2.00 80	2.49 83	1.08 77	1.16 75	2.81 86	0.68 67	1.89 84	2.10 85	2.08 83	2.01 51	3.19 44	1.27 46	0.16 38	0.15 64	0.19 34	2.32 70	3.18 75	2.48 75
BlockOverlap [61]	74.3	0.29 70	0.56 71	0.19 69	0.82 68	1.41 61	0.69 70	1.70 68	2.22 57	0.94 68	1.06 69	2.54 83	0.70 69	1.81 77	1.99 78	2.18 85	5.46 78	3.35 51	3.96 81	0.67 89	0.32 89	1.47 90	2.67 81	3.22 77	3.31 84
Adaptive flow [45]	77.2	0.44 82	0.69 82	0.26 80	1.43 85	1.72 81	1.31 85	1.91 79	2.22 57	1.33 87	1.35 81	2.10 63	1.28 83	1.74 70	2.00 80	1.51 44	4.85 74	3.50 57	3.49 75	0.70 90	0.36 90	0.97 88	2.62 80	3.33 82	2.57 77
PGAM+LK [55]	78.9	0.66 89	0.72 84	1.02 90	1.64 87	2.08 88	1.67 87	1.46 50	1.79 35	1.05 74	2.59 90	3.23 88	2.39 90	1.75 71	1.76 34	2.09 84	6.62 88	4.24 77	5.02 88	0.40 85	0.21 83	0.57 84	2.95 85	3.22 77	3.48 86
SLK [47]	79.7	0.47 84	0.73 85	0.44 88	1.13 80	1.51 68	1.02 82	2.12 83	2.34 74	1.19 83	1.72 85	2.35 75	1.60 86	1.86 83	1.92 69	2.20 87	5.75 82	4.91 83	4.02 82	0.32 83	0.12 31	0.44 78	3.61 87	4.02 87	3.71 87
SILK [87]	80.0	0.39 81	0.68 81	0.30 81	1.19 83	1.60 76	1.10 84	2.19 86	2.47 81	1.19 83	1.25 78	2.36 76	1.10 78	1.84 82	1.98 77	2.18 85	5.84 83	5.17 87	4.03 83	0.45 86	0.12 31	0.96 87	3.03 86	3.47 83	3.24 83
FOLKI [16]	86.8	0.55 87	0.95 89	0.41 87	2.45 89	2.14 89	2.44 89	2.12 83	2.50 85	1.33 87	1.75 86	2.61 85	1.67 87	2.10 88	2.15 86	2.52 88	5.86 84	5.06 86	4.32 85	0.52 87	0.21 83	0.95 86	5.03 90	4.59 88	8.32 90
Periodicity [86]	87.4	0.59 88	1.02 90	0.35 84	2.90 90	3.18 90	3.12 90	2.61 90	2.53 87	2.05 90	2.19 88	3.28 89	2.08 88	7.58 90	8.15 90	6.70 90	7.02 89	6.03 90	5.54 90	0.27 78	0.15 64	0.92 85	4.68 89	6.02 90	4.37 89
Pyramid LK [2]	88.3	0.68 90	0.87 88	0.77 89	1.94 88	1.95 87	1.92 88	2.43 88	2.59 89	1.60 89	2.36 89	2.46 81	2.27 89	4.19 89	4.59 89	3.80 89	7.35 90	5.52 89	5.19 89	0.57 88	0.26 88	1.19 89	4.63 88	5.72 89	4.02 88

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. 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	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] Direct ZNCC	260	2	color	M. Drulea, C. Pantilie, and S. Nedevschi. A direct approach for correlation-based matching in variational optical flow. Submitted to TIP 2012.
[67] ADF	1535	2	color	Anonymous. Optical flow estimation by adaptive data fusion. NIPS 2012 submission 601.
[68] ALD-Flow	61	2	color	M. Stoll, A. Bruhn, and S. Volz. Adaptive integration of feature matches into variational optic flow methods. ACCV 2012.
[69] SIOF	234	2	color	L. Xu, Z. Dai, and J. Jia. Scale invariant optical flow. ECCV 2012.
[70] 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.
[71] TCOF	1421	all	gray	Anonymous. Optical flow estimation with consistent spatio-temporal coherence models. VISAPP 2013 submission 20.
[72] LME	476	2	color	Anonymous. Optical flow estimation using Laplacian mesh energy. CVPR 2013 submission 11.
[73] 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.
[74] SCR	257	2	color	Anonymous. Segmentation constrained regularization for optical flow estimation. CVPR 2013 submission 297.
[75] 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.
[76] PMF	35	2	color	Anonymous. PatchMatch filter: efficient edge-aware filtering meets randomized search for fast correspondence field estimation. CVPR 2013 submission 573.
[77] 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.
[78] FastOF	0.18	2	color	Anonymous. Quasi-realtime variational optical flow computation. CVPR 2013 submission 792.
[79] Correlation Flow	290	2	color	M. Drulea and S. Nedevschi. Motion estimation using the correlation transform. Submitted to TIP 2013.
[80] TC/T-Flow	341	5	color	Anonymous. Joint trilateral filtering for multiframe optical flow. ICIP 2013 submission 2685.
[81] ComplexFlow	673	2	color	Anonymous. Constructing dense correspondence for complex motion. ICCV 2013 submission 353.
[82] OFLADF	1530	2	color	Anonymous. Optical flow via locally adaptive fusion of complementary data costs. ICCV 2013 submission 423.
[83] EP-PM	2.7	2	color	Anonymous. Fast edge-preserving PatchMatch for large displacement optical flow. ICCV 2013 submission 575.
[84] Epistemic	6.5	2	color	Anonymous. Epistemic optical flow. ICCV 2013 submission 804.
[85] Deep-Matching	13	2	color	Anonymous. Large displacement optical flow with deep matching. ICCV 2013 submission 1095.
[86] Periodicity	8000	4	color	Anonymous. A periodicity-based computation of optical flow. BMVC 2013 submission 133.
[87] 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.
[88] CRTflow	13	3	color	Anonymous. The complete rank transform: a tool for accurate and morphologically invariant matching of structures. BMVC 2013 submission 488.
[89] SuperFlow	178	2	color	Anonymous. Superpixel based optical flow estimation. ICCV 2013 submission 507.
[90] Levin3	247	2	color	L. Chen, J. Wang, and Y. Wu. Decomposing and regularizing sparse/non-sparse components for motion field estimation. Submitted to PAMI 2013.

* 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.