Low-res two-view results

This table lists the benchmark results for the low-res two-view scenario. This benchmark evaluates the Middlebury stereo metrics (for all metrics, smaller is better):

bad 0.5, 1.0, 2.0, 4.0 [%]: Fraction of pixels with errors larger than the given number of disparities.
Average error [px]: The per-pixel average disparity error.
Root mean square error [px]: The per-pixel root mean square disparity error.
50%, 90%, 95%, 99% error quantile [px]: The highest disparity error within the given percentage of best pixels (for 50%, this is the median error).
Time [s]: The runtime of the method.

The mask determines whether the metric is evaluated for all pixels with ground truth, or only for pixels which are visible in both images (non-occluded).
The coverage selector allows to limit the table to results for all pixels (dense), or a given minimum fraction of pixels.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click one or more dataset result cells or column headers to show visualizations. Most visualizations are only available for training datasets. The visualizations may not work with mobile browsers.

Method	all	lakes. 1l	lakes. 1s	sand box 1l	sand box 1s	stora. room 1l	stora. room 1s	stora. room 2l	stora. room 2s	stora. room 2 1l	stora. room 2 1s	stora. room 2 2l	stora. room 2 2s	stora. room 3l	stora. room 3s	tunnel 1l	tunnel 1s	tunnel 2l	tunnel 2s	tunnel 3l	tunnel 3s

CREStereo	0.98 1	0.42 10	1.86 1	0.07 1	0.22 7	1.65 1	0.02 1	4.07 2	6.33 21	0.72 1	1.54 2	0.43 2	0.64 1	1.22 1	0.44 1	0.00 1	0.00 1	0.00 1	0.00 1	0.01 2	0.00 1

PMTNet	1.41 2	0.37 8	2.06 4	0.26 3	0.15 4	2.94 13	0.34 10	3.39 1	5.33 11	1.00 2	1.27 1	0.28 1	0.93 5	4.04 9	0.74 4	5.00 135	0.00 1	0.00 1	0.00 1	0.03 14	0.01 2

DPM-Stereo	1.97 3	0.64 28	2.95 13	0.17 2	0.10 1	4.83 36	0.13 3	8.60 17	4.06 4	6.42 26	4.92 6	0.44 3	0.72 2	3.57 8	1.80 7	0.00 1	0.01 39	0.00 1	0.00 1	0.05 22	0.04 27

Gwc-CoAtRS	2.02 4	0.33 6	2.61 5	1.04 10	0.30 10	3.56 16	0.40 13	5.89 4	5.94 17	5.08 13	5.01 7	5.55 15	1.72 9	1.60 2	0.91 5	0.01 30	0.09 86	0.00 1	0.25 104	0.01 2	0.02 7

FENet	2.19 5	0.34 7	3.04 15	2.05 53	0.26 9	2.82 10	0.13 3	7.02 8	5.55 13	4.97 12	1.94 3	4.91 11	3.39 23	4.71 12	2.50 13	0.02 38	0.03 58	0.00 1	0.00 1	0.00 1	0.21 66

RAFT-Stereo	2.44 6	0.32 1	1.93 2	0.94 7	0.16 5	3.67 18	0.61 24	6.37 6	3.08 1	9.14 54	17.44 88	1.80 4	0.77 3	1.76 3	0.70 2	0.00 1	0.01 39	0.00 1	0.00 1	0.01 2	0.03 17
Lahav Lipson, Zachary Teed, and Jia Deng: RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching. 3DV
R-Stereo Train	2.44 6	0.32 1	1.93 2	0.94 7	0.16 5	3.67 18	0.61 24	6.37 6	3.08 1	9.14 54	17.44 88	1.80 4	0.77 3	1.76 3	0.70 2	0.00 1	0.01 39	0.00 1	0.00 1	0.01 2	0.03 17

ACVNet	2.58 8	0.53 18	2.69 7	0.84 5	0.59 20	2.61 6	0.55 19	8.35 12	5.70 14	4.45 7	9.26 34	5.77 17	3.50 25	2.24 5	4.41 39	0.00 1	0.00 1	0.00 1	0.00 1	0.17 56	0.01 2

DN-CSS_ROB	2.69 9	1.40 78	5.34 50	2.31 69	0.75 27	3.14 15	0.06 2	6.11 5	3.87 3	5.34 16	12.18 57	2.34 6	1.22 6	7.84 37	1.48 6	0.03 49	0.00 1	0.00 1	0.00 1	0.35 85	0.03 17

HITNet	2.79 10	0.77 33	4.02 31	2.03 52	0.11 3	5.58 44	0.59 23	9.24 24	5.15 9	6.42 26	7.26 19	3.66 7	2.92 20	4.07 10	3.87 36	0.00 1	0.00 1	0.00 1	0.00 1	0.06 27	0.02 7
Vladimir Tankovich, Christian Häne, Yinda Zhang, Adarsh Kowdle, Sean Fanello, Sofien Bouaziz: HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matching. CVPR 2021
DMCA	2.82 11	0.64 28	4.45 38	1.61 29	0.89 34	3.86 22	0.57 22	9.18 22	5.10 8	6.24 22	6.49 13	7.17 31	2.13 12	3.31 7	4.73 43	0.00 1	0.01 39	0.00 1	0.00 1	0.04 18	0.02 7

ccs	3.04 12	0.39 9	3.08 17	1.78 37	0.52 19	2.04 2	0.50 17	13.09 76	13.71 81	3.54 5	5.36 10	5.50 14	2.45 14	4.81 13	2.88 17	0.09 70	0.08 82	0.12 101	0.10 91	0.20 61	0.50 95

AdaStereo	3.09 13	0.58 22	3.04 15	2.84 87	0.48 18	4.08 25	1.29 46	12.16 67	7.77 41	6.03 20	9.62 36	5.79 19	1.53 8	4.56 11	1.93 9	0.00 1	0.00 1	0.00 1	0.00 1	0.02 7	0.02 7
Xiao Song, Guorun Yang, Xinge Zhu, Hui Zhou, Zhe Wang, Jianping Shi: AdaStereo: A Simple and Efficient Approach for Adaptive Stereo Matching. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2021.
DMCA-RVC	3.17 14	1.26 71	6.39 69	2.10 56	1.51 53	3.02 14	0.56 21	7.84 11	5.06 7	9.23 57	5.19 8	8.46 41	2.72 18	6.31 19	3.22 24	0.06 66	0.11 89	0.09 98	0.02 61	0.16 54	0.08 36

BEATNet_4x	3.24 15	1.27 72	5.89 60	1.56 26	0.10 1	5.26 40	1.07 41	10.08 34	5.50 12	6.89 31	7.73 23	4.53 10	4.13 36	5.05 14	5.27 47	0.04 57	0.05 67	0.00 1	0.00 1	0.23 75	0.23 69

GANet-RSSM	3.27 16	0.60 23	3.38 21	2.94 94	2.00 69	2.61 6	0.48 15	10.93 55	6.11 19	5.47 17	10.20 40	6.57 23	5.44 57	6.25 18	2.23 11	0.00 1	0.00 1	0.08 95	0.00 1	0.17 56	0.03 17

NOSS_ROB	3.30 17	0.46 11	2.62 6	2.08 54	1.01 42	5.60 45	0.74 36	10.37 42	11.48 70	5.15 14	8.43 29	5.67 16	1.73 10	7.97 39	2.34 12	0.02 38	0.06 73	0.00 1	0.00 1	0.07 29	0.14 57

CFNet-ft	3.31 18	0.94 49	2.69 7	1.50 23	2.38 76	2.81 8	0.68 30	8.35 12	7.43 35	4.45 7	9.94 37	10.20 53	4.60 42	6.50 22	3.41 28	0.00 1	0.00 1	0.03 79	0.00 1	0.22 70	0.03 17

CFNet_RVC	3.31 18	0.94 49	2.69 7	1.50 23	2.38 76	2.81 8	0.68 30	8.35 12	7.43 35	4.45 7	9.94 37	10.20 53	4.60 42	6.49 21	3.41 28	0.00 1	0.00 1	0.03 79	0.00 1	0.22 70	0.03 17

PSMNet-RSSM	3.33 20	0.77 33	3.22 20	2.12 57	1.90 68	2.33 4	0.71 33	11.17 56	5.83 16	5.90 18	11.43 52	7.04 27	4.83 51	5.96 16	3.17 22	0.00 1	0.00 1	0.02 71	0.00 1	0.08 31	0.02 7

cf-r	3.42 21	0.81 37	3.97 30	2.41 73	2.78 86	2.85 11	0.64 29	8.44 15	6.32 20	6.25 23	11.57 53	8.97 46	3.54 27	5.93 15	3.83 35	0.00 1	0.00 1	0.00 1	0.00 1	0.09 35	0.07 33

MLCV	3.44 22	0.88 42	5.60 55	1.39 18	0.25 8	4.36 29	0.33 9	7.25 9	7.28 32	9.17 56	12.24 59	5.09 12	2.47 15	9.15 61	3.23 25	0.00 1	0.00 1	0.00 1	0.00 1	0.10 36	0.02 7

DeepPruner_ROB	3.52 23	1.14 65	4.06 32	1.12 12	1.65 57	3.65 17	0.83 38	13.96 85	4.47 6	7.80 39	10.84 45	7.05 29	2.16 13	8.14 46	3.08 21	0.07 68	0.03 58	0.00 1	0.01 57	0.32 81	0.06 31

STTStereo	3.60 24	0.93 48	6.34 67	2.71 84	2.23 74	3.68 20	0.63 27	9.42 25	6.73 25	9.87 66	6.97 17	8.84 45	3.65 28	6.85 23	3.04 19	0.00 1	0.02 51	0.01 59	0.00 1	0.02 7	0.02 7

ccs_rob	3.63 25	1.12 64	4.42 36	2.52 76	0.91 37	5.50 43	0.21 6	10.11 37	9.11 53	6.55 29	11.28 49	8.32 40	2.55 16	7.66 33	2.01 10	0.00 1	0.00 1	0.00 1	0.00 1	0.20 61	0.08 36

hitnet-ft	3.66 26	0.65 30	2.79 11	0.89 6	0.72 26	4.25 27	0.55 19	9.11 21	7.52 37	7.14 33	10.19 39	12.49 71	4.70 46	7.44 29	4.41 39	0.03 49	0.00 1	0.06 91	0.00 1	0.20 61	0.04 27

iResNet	3.68 27	0.91 45	7.94 86	2.97 95	0.34 12	4.44 33	0.48 15	7.70 10	9.74 57	7.72 38	12.74 63	4.03 8	2.87 19	8.05 42	3.37 27	0.02 38	0.01 39	0.00 1	0.00 1	0.10 36	0.09 40

acv_ft	3.69 28	0.53 18	4.58 41	2.31 69	4.71 121	7.44 65	0.86 39	8.54 16	5.70 14	9.29 58	9.26 34	5.77 17	4.15 37	2.24 5	8.13 76	0.00 1	0.00 1	0.00 1	0.00 1	0.29 77	0.01 2

ac_64	3.70 29	0.47 12	3.50 24	2.87 88	3.50 100	5.91 48	0.72 34	10.17 39	4.34 5	8.16 45	5.80 11	10.82 59	5.64 59	7.08 26	4.73 43	0.03 49	0.00 1	0.00 1	0.00 1	0.08 31	0.14 57

CFNet	3.72 30	1.10 61	5.03 45	2.49 75	1.59 54	4.90 38	0.22 7	11.38 57	9.88 59	4.80 10	11.25 48	6.44 22	3.68 29	8.33 48	3.00 18	0.00 1	0.00 1	0.00 1	0.00 1	0.22 70	0.07 33

GwcNet-RSSM	3.77 31	1.05 55	5.06 46	2.21 62	1.87 66	2.36 5	1.52 49	8.98 20	7.96 43	5.91 19	14.59 73	7.94 38	3.50 25	6.43 20	5.70 51	0.00 1	0.00 1	0.04 86	0.00 1	0.20 61	0.08 36

FADNet-RVC-Resample	3.79 32	1.62 90	12.06 101	1.43 21	0.66 22	5.94 49	2.41 57	10.18 40	8.58 51	6.28 24	4.22 5	5.33 13	4.80 50	7.71 34	3.19 23	0.17 84	0.21 106	0.17 108	0.12 93	0.41 93	0.29 82

UPFNet	3.82 33	0.47 12	4.34 35	2.21 62	3.38 96	7.26 62	2.69 59	9.89 30	5.96 18	7.98 42	7.53 21	7.89 37	3.15 22	7.72 35	5.88 53	0.01 30	0.02 51	0.00 1	0.00 1	0.04 18	0.06 31

NLCA_NET_v2_RVC	3.84 34	1.06 56	5.23 48	2.72 85	3.27 92	4.36 29	0.61 24	10.71 49	7.56 38	8.75 49	7.89 24	9.86 51	3.90 33	7.15 27	3.44 30	0.14 78	0.02 51	0.02 71	0.03 70	0.04 18	0.03 17
Zhibo Rao, Mingyi He, Yuchao Dai, Zhidong Zhu, Bo Li, and Renjie He.: NLCA-Net: A non-local context attention network for stereo matching.
CC-Net-ROB	3.84 34	1.07 57	5.23 48	2.65 81	2.96 89	4.22 26	0.69 32	10.43 44	7.72 39	8.78 50	8.29 27	9.61 49	4.02 35	7.16 28	3.65 33	0.13 77	0.03 58	0.02 71	0.03 70	0.05 22	0.03 17

psm_up	3.85 36	0.82 38	3.01 14	2.00 51	2.58 84	5.28 41	3.34 66	10.85 53	6.33 21	7.27 35	7.32 20	10.15 52	9.02 85	6.19 17	2.51 14	0.22 89	0.01 39	0.00 1	0.00 1	0.12 43	0.03 17

FADNet_RVC	3.91 37	1.67 93	12.95 108	0.96 9	0.75 27	5.71 47	0.54 18	10.83 52	6.60 24	3.46 3	8.09 25	4.10 9	3.40 24	9.43 65	6.33 56	0.36 102	0.44 120	0.17 108	0.46 121	0.91 110	0.95 114

UNet	3.97 38	0.61 25	6.50 72	1.68 34	3.22 91	9.82 79	0.31 8	9.50 26	5.32 10	7.20 34	6.35 12	10.59 57	5.91 63	6.93 25	5.49 49	0.00 1	0.00 1	0.00 1	0.00 1	0.02 7	0.01 2

FADNet-RVC	3.98 39	1.84 99	12.48 104	1.69 35	0.44 16	4.33 28	1.31 47	11.84 61	7.15 30	3.53 4	3.50 4	10.63 58	4.43 41	9.12 60	6.25 55	0.03 49	0.10 87	0.00 1	0.03 70	0.60 100	0.25 75

HSM	4.00 40	0.79 36	3.16 19	1.59 28	2.17 72	6.77 58	1.11 42	12.28 68	6.35 23	6.75 30	8.11 26	13.90 77	5.37 56	8.85 56	2.71 16	0.00 1	0.00 1	0.00 1	0.00 1	0.02 7	0.02 7

TDLM	4.11 41	1.11 63	3.54 25	1.62 30	1.04 43	3.91 23	7.41 110	10.60 47	10.67 64	6.38 25	12.59 62	5.95 20	4.77 48	8.79 55	3.04 19	0.58 114	0.00 1	0.01 59	0.00 1	0.19 60	0.12 52

CBMV_ROB	4.14 42	0.52 15	3.14 18	1.30 15	0.77 30	6.92 59	1.97 55	10.11 37	9.58 55	8.92 53	14.20 71	7.12 30	5.90 62	8.65 52	3.50 32	0.01 30	0.05 67	0.00 1	0.00 1	0.04 18	0.09 40

CVANet_RVC	4.16 43	1.16 66	3.60 26	1.94 47	1.46 51	3.92 24	4.68 89	10.89 54	8.34 48	7.58 37	10.84 45	10.27 55	6.62 68	8.56 51	2.69 15	0.39 104	0.00 1	0.00 1	0.01 57	0.21 68	0.09 40

MMNet	4.16 43	0.77 33	5.47 53	1.40 19	1.67 59	10.78 88	0.63 27	8.64 19	8.47 50	8.80 51	8.33 28	7.51 33	6.61 67	7.53 31	6.54 59	0.00 1	0.00 1	0.00 1	0.00 1	0.03 14	0.05 30

HSM-Net_RVC	4.20 45	0.32 1	2.76 10	0.63 4	0.69 24	6.95 60	1.69 52	11.96 62	8.36 49	8.83 52	12.17 56	15.18 85	4.21 39	6.91 24	3.30 26	0.02 38	0.02 51	0.00 1	0.00 1	0.01 2	0.01 2
Gengshan Yang, Joshua Manela, Michael Happold, and Deva Ramanan: Hierarchical Deep Stereo Matching on High-resolution Images. CVPR 2019
DSFCA	4.21 46	0.50 14	5.45 52	1.34 16	1.68 60	7.04 61	4.51 86	10.73 50	7.00 27	10.78 74	6.80 14	8.48 43	4.63 44	9.91 69	5.12 46	0.02 38	0.06 73	0.02 71	0.03 70	0.08 31	0.03 17

iResNet_ROB	4.23 47	1.02 53	4.90 44	2.18 59	0.93 40	2.92 12	0.37 12	15.10 97	16.91 96	7.89 41	10.51 43	7.03 26	3.07 21	8.16 47	3.46 31	0.01 30	0.00 1	0.00 1	0.00 1	0.10 36	0.02 7

FADNet	4.23 47	1.65 92	11.75 100	1.64 32	0.80 32	4.80 35	0.77 37	13.76 84	11.65 72	3.97 6	5.24 9	9.62 50	5.14 53	8.40 49	3.78 34	0.21 88	0.04 63	0.07 94	0.05 81	1.14 115	0.10 47

HGLStereo	4.25 49	0.52 15	4.65 42	3.09 97	5.18 123	6.51 56	0.73 35	10.37 42	6.74 26	7.32 36	12.44 61	7.00 25	7.21 72	7.46 30	5.51 50	0.00 1	0.02 51	0.00 1	0.00 1	0.06 27	0.10 47

delet	4.27 50	0.72 32	4.50 39	1.07 11	3.75 106	10.79 89	4.04 76	9.95 31	7.89 42	8.09 43	8.89 32	8.46 41	3.81 31	7.56 32	5.80 52	0.00 1	0.00 1	0.00 1	0.00 1	0.11 40	0.02 7

iResNetv2_ROB	4.28 51	1.43 79	7.17 81	2.91 89	1.26 47	4.36 29	1.62 50	13.64 83	10.25 63	9.83 65	11.41 50	7.68 34	4.00 34	7.75 36	1.85 8	0.00 1	0.00 1	0.00 1	0.00 1	0.37 87	0.09 40

StereoDRNet-Refined	4.46 52	0.62 27	3.80 29	1.92 44	0.40 14	9.35 73	0.15 5	10.02 32	8.83 52	12.69 86	11.62 54	9.34 47	3.87 32	8.06 43	8.02 71	0.00 1	0.00 1	0.01 59	0.05 81	0.20 61	0.26 78
Rohan Chabra, Julian Straub, Chris Sweeney, Richard Newcombe, Henry Fuchs: StereoDRNet. CVPR
NVstereo2D	4.51 53	0.82 38	6.86 79	3.28 102	3.38 96	8.16 68	3.13 63	10.51 45	15.15 86	4.90 11	6.89 16	7.87 35	4.78 49	9.88 68	3.91 37	0.01 30	0.00 1	0.00 1	0.06 83	0.02 7	0.58 101

DLCB_ROB	4.51 53	0.91 45	3.78 28	2.19 60	1.07 44	6.28 50	3.09 62	9.78 29	7.72 39	10.65 72	12.97 64	13.91 78	3.71 30	8.72 53	5.30 48	0.00 1	0.00 1	0.00 1	0.00 1	0.03 14	0.10 47

RASNet	4.52 55	0.61 25	4.42 36	3.42 106	4.68 120	4.58 34	0.99 40	9.54 28	8.01 44	5.28 15	11.42 51	10.34 56	8.88 83	9.28 63	8.68 81	0.15 80	0.00 1	0.00 1	0.00 1	0.03 14	0.04 27

SGM-Forest	4.96 56	0.32 1	2.84 12	1.21 13	0.64 21	10.23 84	6.64 105	11.55 58	10.98 65	10.94 76	13.59 67	11.65 66	4.30 40	8.94 58	4.63 42	0.11 73	0.04 63	0.00 1	0.00 1	0.05 22	0.46 92
Johannes L. Schönberger, Sudipta Sinha, Marc Pollefeys: Learning to Fuse Proposals from Multiple Scanline Optimizations in Semi-Global Matching. ECCV 2018
PA-Net	4.98 57	1.47 81	7.42 83	2.40 72	2.14 71	8.73 70	3.64 73	12.42 69	13.11 77	7.03 32	7.57 22	7.88 36	6.52 66	10.16 71	7.82 69	0.02 38	0.03 58	0.00 1	0.00 1	0.11 40	1.07 117
Zhibo Rao, Mingyi He, Yuchao Dai, Zhelun Shen: Patch Attention Network with Generative Adversarial Model for Semi-Supervised Binocular Disparity Prediction.
AANet_RVC	5.01 58	1.74 94	6.38 68	1.96 49	1.29 49	2.26 3	1.69 52	10.07 33	18.53 99	7.88 40	18.15 90	8.49 44	2.70 17	10.59 75	7.04 62	0.96 124	0.15 98	0.02 71	0.00 1	0.13 47	0.12 52

PSMNet_ROB	5.02 59	1.63 91	6.03 62	1.90 43	1.83 65	9.57 77	6.35 102	15.58 102	7.23 31	6.15 21	10.48 42	12.22 69	4.16 38	8.02 40	8.71 82	0.02 38	0.01 39	0.01 59	0.10 91	0.20 61	0.12 52

CBMV	5.35 60	0.91 45	3.67 27	1.62 30	0.44 16	10.09 82	7.19 109	12.49 70	12.33 76	12.22 82	14.69 74	10.93 61	6.48 65	8.51 50	4.96 45	0.02 38	0.15 98	0.00 1	0.00 1	0.17 56	0.17 62
Konstantinos Batsos, Changjiang Cai, Philippos Mordohai: CBMV: A Coalesced Bidirectional Matching Volume for Disparity Estimation. Computer Vision and Pattern Recognition (CVPR) 2018
StereoDRNet	5.59 61	1.75 95	6.80 77	3.12 98	4.45 115	10.61 87	4.35 82	18.80 114	9.73 56	12.22 82	6.87 15	11.44 64	4.65 45	8.09 45	8.26 77	0.02 38	0.11 89	0.00 1	0.03 70	0.20 61	0.28 81

ETE_ROB	5.80 62	1.77 96	6.33 66	1.44 22	0.78 31	6.43 54	6.90 106	12.53 71	8.08 45	12.93 90	14.89 75	21.13 113	5.87 61	9.83 67	6.57 60	0.04 57	0.01 39	0.00 1	0.02 61	0.08 31	0.33 83

DRN-Test	5.87 63	0.98 51	5.89 60	2.69 83	3.65 105	12.37 97	3.35 67	20.07 125	10.20 62	11.93 81	12.31 60	11.06 63	5.31 55	7.89 38	9.05 85	0.04 57	0.05 67	0.04 86	0.04 79	0.18 59	0.25 75

NCCL2	5.88 64	1.59 88	5.44 51	1.87 40	0.92 38	9.55 76	11.55 125	12.11 64	9.94 60	9.67 64	8.85 31	22.28 115	7.41 73	8.78 54	7.17 63	0.01 30	0.00 1	0.03 79	0.00 1	0.13 47	0.23 69

NaN_ROB	6.00 65	1.24 69	6.29 65	1.34 16	1.68 60	9.60 78	10.31 121	15.09 95	15.79 89	12.62 85	8.95 33	11.67 67	5.83 60	11.78 84	6.41 58	0.05 64	0.13 95	0.08 95	0.20 100	0.22 70	0.79 109

DANet	6.02 66	1.23 68	8.45 88	3.86 115	3.94 109	7.64 67	1.34 48	9.51 27	7.00 27	13.39 92	15.53 79	15.99 89	7.02 71	12.14 85	12.37 105	0.19 86	0.12 94	0.02 71	0.03 70	0.13 47	0.56 100

XPNet_ROB	6.03 67	1.22 67	5.61 56	2.56 79	0.90 36	6.32 51	7.07 107	12.92 74	8.30 47	14.76 97	15.13 77	19.84 107	6.66 70	10.36 72	8.58 80	0.02 38	0.04 63	0.00 1	0.03 70	0.11 40	0.24 72

Anonymous Stereo	6.16 68	3.15 117	23.75 126	2.97 95	2.48 81	4.39 32	13.30 127	9.21 23	9.86 58	9.56 63	8.76 30	6.79 24	1.99 11	13.50 97	13.04 108	0.01 30	0.05 67	0.00 1	0.06 83	0.22 70	0.19 64

GANet	6.22 69	1.07 57	4.07 33	2.27 65	0.89 34	9.19 72	9.52 116	12.02 63	8.13 46	10.72 73	29.09 115	13.86 76	7.52 75	11.00 79	4.39 38	0.36 102	0.00 1	0.02 71	0.02 61	0.12 43	0.08 36

DISCO	6.28 70	0.57 21	5.78 58	3.43 107	1.17 45	11.22 91	3.39 68	12.14 66	16.16 91	6.52 28	11.22 47	16.96 92	6.32 64	19.51 120	10.74 98	0.00 1	0.00 1	0.00 1	0.00 1	0.35 85	0.11 50

RYNet	6.34 71	0.89 44	5.88 59	1.41 20	4.48 117	15.97 108	4.18 78	13.41 79	16.49 92	10.81 75	7.00 18	14.33 80	8.72 81	9.43 65	13.71 109	0.00 1	0.01 39	0.00 1	0.00 1	0.02 7	0.07 33

GwcNet	6.42 72	1.97 102	10.92 95	2.59 80	5.58 126	11.55 93	2.21 56	14.10 87	16.52 95	10.04 68	17.19 87	10.86 60	5.61 58	9.23 62	8.84 84	0.01 30	0.06 73	0.03 79	0.08 87	0.56 96	0.40 87

GANetREF_RVC	6.56 73	2.89 112	7.58 85	3.41 105	0.40 14	12.96 100	9.58 117	15.09 95	17.25 98	10.33 69	10.62 44	12.27 70	8.16 77	12.21 86	4.53 41	0.41 106	0.00 1	0.00 1	0.02 61	3.12 131	0.39 86
Zhang, Feihu and Prisacariu, Victor and Yang, Ruigang and Torr, Philip HS: GA-Net: Guided Aggregation Net for End- to-end Stereo Matching. CVPR 2019
LALA_ROB	6.58 74	1.80 98	6.25 64	1.26 14	0.94 41	10.08 81	9.02 113	16.00 103	11.51 71	12.74 87	13.02 65	24.77 117	5.25 54	10.56 74	8.02 71	0.04 57	0.05 67	0.00 1	0.02 61	0.10 36	0.25 75

S-Stereo	6.63 75	0.84 40	9.67 92	3.15 99	3.48 99	6.49 55	6.22 97	12.99 75	22.84 112	9.48 59	15.51 78	12.00 68	8.43 78	8.04 41	10.70 97	0.12 76	0.17 102	0.00 1	0.38 114	0.13 47	1.92 126

DeepPrunerF	6.75 76	2.69 110	23.31 125	3.68 110	7.16 132	3.78 21	4.29 80	13.42 80	20.13 109	8.13 44	10.46 41	7.18 32	8.06 76	11.10 80	9.44 87	0.24 91	0.15 98	0.29 117	0.42 117	0.66 103	0.45 90

edge stereo	6.76 77	1.01 52	6.76 76	2.20 61	2.45 80	6.41 53	2.45 58	14.84 93	11.98 75	15.29 98	18.31 91	22.02 114	12.56 99	10.82 76	7.49 65	0.03 49	0.06 73	0.11 100	0.03 70	0.30 78	0.14 57

Abc-Net	6.77 78	1.49 82	6.48 70	2.92 91	4.40 111	7.43 63	3.61 71	19.52 121	13.29 78	8.39 47	16.91 82	15.96 87	12.13 97	12.85 91	7.70 67	1.47 128	0.11 89	0.01 59	0.42 117	0.14 52	0.24 72
Xing Li, Yangyu Fan, Guoyun Lv, and Haoyue Ma: Area-based Correlation and Non-local Attention Network for Stereo Matching. The Visual Computer
NCC-stereo	6.77 78	1.49 82	6.48 70	2.92 91	4.40 111	7.43 63	3.61 71	19.52 121	13.29 78	8.39 47	16.91 82	15.96 87	12.13 97	12.85 91	7.70 67	1.47 128	0.11 89	0.01 59	0.42 117	0.14 52	0.24 72

FAT-Stereo	6.78 80	0.68 31	6.80 77	2.30 67	1.77 64	5.63 46	4.20 79	18.79 113	18.62 100	10.53 71	17.15 85	18.52 101	13.74 107	8.86 57	7.38 64	0.03 49	0.15 98	0.01 59	0.07 85	0.12 43	0.26 78

RP	6.84 81	1.29 76	5.53 54	3.92 116	5.18 123	6.32 51	3.53 69	11.73 60	15.31 87	9.54 62	22.38 98	18.25 99	14.47 108	10.11 70	7.49 65	0.91 123	0.01 39	0.12 101	0.15 96	0.33 82	0.19 64

RGC	6.88 82	2.23 106	6.13 63	4.05 117	4.73 122	8.94 71	2.78 61	15.19 99	11.74 73	11.13 77	19.34 93	17.86 96	10.42 91	13.02 94	8.03 73	0.73 117	0.01 39	0.24 116	0.41 116	0.31 80	0.38 85

Nwc_Net	6.97 83	1.25 70	6.63 74	3.82 114	3.37 95	10.83 90	1.67 51	19.56 123	11.35 68	8.36 46	23.62 101	17.19 94	11.44 96	11.21 81	8.08 75	0.80 119	0.00 1	0.00 1	0.02 61	0.13 47	0.09 40

STTRV1_RVC	7.02 84	1.10 61	12.88 106	3.32 103	6.92 131	11.90 96	4.00 75	15.07 94	11.94 74	9.51 60	14.57 72	11.63 65	8.73 82	12.65 90	8.06 74	3.32 134	2.75 135	0.41 125	0.12 93	1.38 121	0.11 50

ADCRef	7.27 85	1.38 77	16.37 114	2.52 76	3.30 94	11.63 94	3.16 64	10.80 51	9.35 54	13.03 91	25.27 109	8.17 39	8.92 84	8.06 43	21.81 124	0.15 80	0.08 82	0.16 107	0.34 112	0.38 88	0.58 101

psmorigin	7.34 86	1.58 87	18.31 118	2.35 71	0.87 33	6.72 57	1.70 54	10.63 48	7.14 29	19.77 110	22.71 99	20.13 109	11.34 95	12.96 93	9.49 88	0.04 57	0.17 102	0.06 91	0.17 97	0.21 68	0.50 95

CSAN	7.62 87	1.60 89	6.56 73	1.83 38	0.66 22	12.40 98	10.52 123	14.45 90	21.32 111	14.19 94	15.98 81	17.84 95	13.02 104	12.32 87	8.38 78	0.09 70	0.07 80	0.03 79	0.04 79	0.33 82	0.67 107

stereogan	7.69 88	0.88 42	7.08 80	3.49 108	3.93 108	18.98 116	3.23 65	16.52 105	19.58 106	9.93 67	18.92 92	20.50 111	9.04 86	14.07 101	6.14 54	0.26 94	0.04 63	0.21 113	0.03 70	0.63 102	0.33 83

pmcnn	7.72 89	1.27 72	9.42 91	2.91 89	3.14 90	9.44 74	6.23 98	12.56 72	16.51 93	14.53 95	24.08 103	27.44 123	8.49 79	9.32 64	8.44 79	0.06 66	0.08 82	0.00 1	0.00 1	0.30 78	0.15 60

AF-Net	7.78 90	1.44 80	6.68 75	3.37 104	4.50 118	8.61 69	2.69 59	17.07 108	20.17 110	9.52 61	24.02 102	20.31 110	14.59 109	11.58 83	9.84 93	0.61 115	0.00 1	0.12 101	0.00 1	0.38 88	0.12 52

PASM	7.90 91	4.22 123	21.97 123	3.25 101	3.29 93	5.39 42	6.57 104	10.57 46	19.09 102	12.77 88	13.92 69	18.11 98	9.51 88	13.79 100	10.77 100	0.19 86	0.45 121	0.29 117	1.08 130	1.49 123	1.19 119

PWCDC_ROB	7.92 92	3.17 119	7.48 84	5.73 128	4.40 111	10.45 85	0.35 11	14.52 91	28.19 120	10.36 70	31.27 119	7.04 27	9.14 87	13.22 96	8.78 83	2.74 133	0.02 51	0.00 1	0.00 1	1.31 120	0.17 62

ADCP+	8.09 93	1.79 97	14.50 112	1.54 25	4.28 110	16.57 110	5.20 91	12.80 73	11.20 67	12.83 89	17.07 84	11.02 62	10.80 93	17.59 116	23.18 127	0.03 49	0.05 67	0.01 59	0.18 98	0.39 92	0.81 110

SuperB	8.10 94	3.15 117	24.67 127	2.65 81	1.23 46	9.88 80	4.29 80	10.18 40	30.07 123	11.53 79	12.18 57	6.12 21	6.65 69	10.50 73	14.47 111	0.14 78	0.11 89	0.35 121	0.25 104	13.06 140	0.48 93

PWC_ROB	8.24 95	3.13 115	12.74 105	2.43 74	4.43 114	7.51 66	1.22 43	16.63 106	19.24 104	16.08 100	28.29 112	13.99 79	10.16 90	13.63 99	14.06 110	0.42 109	0.00 1	0.05 89	0.00 1	0.59 99	0.27 80

MDST_ROB	8.37 96	0.32 1	9.03 89	4.18 120	2.42 79	26.86 129	6.14 95	19.36 118	13.52 80	27.09 125	22.75 100	9.47 48	4.74 47	15.06 107	6.34 57	0.02 38	0.02 51	0.00 1	0.00 1	0.02 7	0.13 56

G-Net	8.41 97	1.54 85	10.97 96	5.73 128	3.60 102	26.19 126	4.41 83	10.10 35	7.42 33	19.71 108	24.99 107	14.38 81	15.83 110	10.99 77	9.53 89	0.50 112	0.46 122	0.19 111	0.25 104	0.80 107	0.66 105

STTStereo_v2	8.41 97	1.54 85	10.97 96	5.73 128	3.60 102	26.19 126	4.41 83	10.10 35	7.42 33	19.71 108	24.99 107	14.38 81	15.83 110	10.99 77	9.53 89	0.50 112	0.46 122	0.19 111	0.25 104	0.80 107	0.66 105

XQC	8.43 99	3.58 121	16.40 115	2.92 91	2.17 72	13.22 102	3.60 70	14.64 92	25.86 117	11.87 80	12.04 55	15.06 84	10.67 92	15.24 108	19.41 116	0.39 104	0.08 82	0.05 89	0.07 85	0.84 109	0.45 90

FBW_ROB	8.50 100	1.03 54	7.98 87	1.93 46	1.28 48	13.10 101	6.23 98	22.50 129	18.98 101	18.82 105	14.91 76	19.06 104	10.04 89	18.41 117	9.83 92	0.62 116	0.22 107	1.82 136	0.82 127	0.99 113	1.36 121

aanetorigin	8.72 101	3.29 120	27.55 129	1.95 48	3.84 107	4.93 39	5.39 93	5.49 3	10.05 61	27.85 126	31.47 120	15.80 86	12.78 101	9.04 59	11.98 103	0.25 92	0.22 107	0.22 114	0.25 104	1.28 119	0.84 112

RTSC	9.15 102	3.00 114	13.57 110	3.72 112	1.76 63	11.82 95	0.46 14	16.95 107	36.83 132	15.80 99	15.53 79	12.91 73	7.46 74	20.01 123	21.76 123	0.31 99	0.13 95	0.01 59	0.08 87	0.57 97	0.41 89

WCMA_ROB	9.21 103	0.87 41	7.37 82	2.54 78	2.13 70	13.59 103	5.80 94	11.64 59	14.01 82	24.43 122	32.99 125	27.09 122	18.02 114	12.51 89	9.85 94	0.81 120	0.07 80	0.01 59	0.01 57	0.16 54	0.23 69

MSMD_ROB	9.28 104	1.09 60	4.65 42	1.58 27	0.39 13	16.52 109	4.41 83	13.60 81	14.87 85	22.34 114	39.89 133	25.67 119	20.71 123	12.42 88	6.98 61	0.34 101	0.03 58	0.00 1	0.00 1	0.05 22	0.09 40

ADCPNet	9.54 105	2.39 108	31.46 131	2.09 55	1.60 55	16.71 112	6.39 103	12.11 64	11.45 69	13.53 93	21.45 96	19.41 105	10.94 94	14.38 103	21.54 122	0.27 97	1.16 129	0.39 124	1.49 134	0.58 98	1.45 122

SHD	9.61 106	2.60 109	12.46 103	3.69 111	3.54 101	9.47 75	1.25 44	20.16 126	37.84 135	18.19 104	21.24 95	16.96 92	12.83 103	14.47 105	16.05 113	0.32 100	0.13 95	0.01 59	0.08 87	0.38 88	0.48 93

PDISCO_ROB	9.62 107	1.99 103	11.51 98	9.88 136	9.61 137	21.48 120	3.83 74	19.33 117	28.49 121	11.27 78	14.17 70	19.92 108	5.02 52	16.35 113	9.18 86	5.28 137	0.41 117	0.14 105	0.09 90	2.05 127	2.36 132

MFN_U_SF_DS_RVC	9.78 108	4.27 124	14.47 111	2.29 66	2.85 88	23.40 124	13.62 128	13.60 81	19.54 105	19.42 107	24.27 104	16.74 91	8.59 80	17.05 115	7.98 70	1.25 127	1.68 133	0.17 108	2.63 136	0.72 105	1.04 115

SGM_RVC	10.08 109	0.60 23	3.42 22	2.30 67	0.32 11	19.41 117	6.33 101	18.95 115	14.64 83	25.14 124	24.32 105	33.34 131	18.79 118	19.86 121	12.55 107	0.25 92	0.26 112	0.22 114	0.24 103	0.34 84	0.40 87
Heiko Hirschmueller: Stereo processing by semiglobal matching and mutual information. TPAMI 2008, Volume 30(2), pp. 328-341
DPSNet	10.14 110	1.88 101	16.82 116	1.85 39	1.73 62	24.84 125	17.20 137	19.92 124	27.41 119	12.23 84	13.62 68	16.52 90	18.35 115	14.42 104	12.50 106	0.78 118	0.54 126	0.08 95	0.25 104	1.18 116	0.59 104

ADCL	10.16 111	2.11 104	19.36 120	1.92 44	1.88 67	22.23 121	8.91 112	14.04 86	23.56 114	14.62 96	26.19 110	12.75 72	13.59 106	16.06 112	22.95 126	0.26 94	0.18 104	0.75 128	0.65 123	0.69 104	0.58 101

FCDSN-DC	10.24 112	0.56 20	3.49 23	1.96 49	1.29 49	16.90 113	4.59 88	17.16 109	19.10 103	24.64 123	32.46 124	33.82 132	22.14 128	15.93 111	10.45 95	0.04 57	0.00 1	0.00 1	0.00 1	0.05 22	0.21 66
Dominik Hirner, Friedrich Fraundorfer: FCDSN-DC: An accurate but lightweight end-to-end trainable neural network for stereo estimation with depth completion.
ADCMid	10.24 112	3.13 115	20.70 121	2.21 62	2.39 78	11.23 92	6.19 96	14.17 88	11.19 66	23.20 120	22.25 97	17.89 97	19.54 120	18.51 118	26.21 132	0.45 110	0.42 119	1.10 132	1.29 131	1.56 125	1.18 118

SANet	10.64 114	1.86 100	10.91 94	1.76 36	0.71 25	14.62 106	9.23 115	19.18 116	37.14 133	19.22 106	27.96 111	25.86 120	19.11 119	13.02 94	10.63 96	0.08 69	0.06 73	0.03 79	0.02 61	0.62 101	0.81 110

FC-DCNN	10.72 115	0.52 15	4.27 34	1.88 41	1.63 56	17.18 114	5.29 92	18.20 111	19.69 107	28.50 127	34.51 128	34.03 133	21.48 126	15.89 110	11.15 102	0.03 49	0.01 39	0.02 71	0.01 57	0.07 29	0.09 40

AnyNet_C32	10.98 116	5.58 126	22.79 124	4.16 118	5.83 127	15.64 107	14.30 129	13.18 77	17.15 97	16.44 102	20.52 94	14.68 83	13.44 105	22.46 125	30.08 137	0.17 84	0.26 112	0.36 122	0.36 113	1.23 117	0.91 113

MeshStereo	11.52 117	1.52 84	4.55 40	1.89 42	1.46 51	19.87 119	5.11 90	20.66 127	15.91 90	32.67 132	34.51 128	39.34 138	21.15 124	18.74 119	12.10 104	0.11 73	0.06 73	0.01 59	0.00 1	0.45 95	0.22 68
C. Zhang, Z. Li, Y. Cheng, R. Cai, H. Chao, Y. Rui: MeshStereo: A Global Stereo Model with Mesh Alignment Regularization for View Interpolation. ICCV 2015
MFN_U_SF_RVC	12.94 118	3.66 122	25.81 128	3.61 109	2.26 75	22.77 122	4.55 87	27.10 134	20.06 108	23.90 121	28.99 114	30.53 128	16.98 112	19.92 122	20.26 118	1.24 126	1.07 128	0.98 131	1.33 132	1.80 126	2.04 128

ADCS	13.02 119	4.93 125	28.38 130	3.17 100	2.67 85	13.61 104	10.83 124	18.70 112	33.46 127	22.59 115	24.78 106	19.59 106	18.51 117	23.40 128	32.16 139	0.10 72	0.19 105	0.37 123	0.18 98	1.26 118	1.46 123

MFMNet_re	13.29 120	8.60 133	18.29 117	9.75 135	7.25 134	19.65 118	14.84 133	20.71 128	30.72 124	23.03 118	28.77 113	18.85 103	26.09 133	13.55 98	9.82 91	2.44 131	1.35 132	0.34 120	0.23 102	4.78 135	6.69 137

EDNetEfficient	13.82 121	6.19 128	54.79 137	2.83 86	3.60 102	4.86 37	8.57 111	8.61 18	32.90 126	40.77 138	30.59 118	18.33 100	21.87 127	11.38 82	25.36 130	0.15 80	0.23 109	0.06 91	1.03 129	2.54 129	1.79 124

LSM	14.01 122	5.95 127	33.49 132	6.78 133	43.61 142	10.22 83	9.98 120	15.16 98	22.93 113	23.07 119	32.34 123	18.52 101	12.67 100	15.45 109	11.10 101	0.16 83	0.51 125	0.09 98	0.32 110	1.08 114	16.85 142

SAMSARA	14.63 123	2.74 111	12.38 102	12.65 139	6.74 130	36.50 135	72.93 143	19.36 118	23.77 115	16.20 101	13.04 66	29.21 125	12.78 101	16.98 114	15.21 112	0.11 73	0.26 112	0.03 79	0.14 95	0.76 106	0.77 108

SPS-STEREO	15.04 124	6.23 129	13.21 109	11.34 138	11.65 140	23.30 123	7.15 108	24.16 131	15.65 88	31.78 131	29.19 116	31.62 129	21.32 125	24.62 129	19.50 117	7.59 139	4.19 140	3.22 137	1.48 133	6.99 139	6.54 136
K. Yamaguchi, D. McAllester, R. Urtasun: Efficient Joint Segmentation, Occlusion Labeling, Stereo and Flow Estimation. ECCV 2014
PVD	15.44 125	2.93 113	14.67 113	4.21 121	3.39 98	17.43 115	4.16 77	27.84 137	48.84 140	31.02 130	43.54 137	29.76 127	30.81 137	25.97 131	21.40 121	0.23 90	0.41 117	0.04 86	0.33 111	0.41 93	1.33 120

SGM+DAISY	15.62 126	7.26 132	19.28 119	8.94 134	10.11 139	26.25 128	10.49 122	19.36 118	14.65 84	30.64 129	33.59 126	33.00 130	22.32 129	24.96 130	16.42 114	7.90 140	6.25 141	4.51 138	3.37 137	5.86 137	7.20 138

NVStereoNet_ROB	16.04 127	6.75 130	12.90 107	6.37 132	7.42 135	12.89 99	9.74 118	22.78 130	25.12 116	30.32 128	46.19 139	34.37 134	25.38 131	21.48 124	21.38 120	5.94 138	3.10 138	6.07 139	10.09 141	4.01 133	8.54 140
Nikolai Smolyanskiy, Alexey Kamenev, Stan Birchfield: On the Importance of Stereo for Accurate Depth Estimation: An Efficient Semi-Supervised Deep Neural Network Approach. Arxiv
AnyNet_C01	16.12 128	10.81 137	59.36 138	4.42 122	2.49 82	30.06 131	15.15 135	17.51 110	16.51 93	17.88 103	37.69 132	24.04 116	17.54 113	29.60 134	33.29 140	0.28 98	0.38 115	0.43 126	0.42 117	2.57 130	1.98 127

MSC_U_SF_DS_RVC	16.41 129	6.93 131	21.83 122	5.94 131	2.81 87	38.71 136	14.59 130	24.55 132	34.87 130	33.66 133	34.35 127	29.24 126	24.20 130	22.59 126	17.95 115	2.52 132	2.81 136	1.17 134	1.51 135	5.89 138	2.16 129

ELAS_RVC	16.54 130	2.26 107	10.09 93	5.50 127	4.46 116	28.28 130	16.72 136	25.55 133	33.54 128	40.19 136	40.30 135	36.68 136	30.03 135	29.40 133	20.61 119	0.98 125	1.21 130	0.86 130	0.70 125	1.39 122	2.16 129
A. Geiger, M. Roser, R. Urtasun: Efficient large-scale stereo matching. ACCV 2010
ELAS	16.72 131	2.14 105	9.23 90	4.92 124	4.53 119	32.66 134	15.11 134	27.40 135	28.68 122	40.27 137	44.90 138	38.33 137	30.50 136	26.44 132	21.94 125	0.88 121	1.23 131	0.67 127	0.89 128	1.49 123	2.18 131
A. Geiger, M. Roser, R. Urtasun: Efficient large-scale stereo matching. ACCV 2010
LE_ROB	16.73 132	1.28 75	11.61 99	3.72 112	1.65 57	16.67 111	9.17 114	14.39 89	55.91 142	63.81 142	40.86 136	35.94 135	37.73 140	14.24 102	26.87 133	0.05 64	0.10 87	0.13 104	0.22 101	0.12 43	0.15 60

SGM-ForestM	16.99 133	1.08 59	5.74 57	2.12 57	0.75 27	31.63 133	12.21 126	27.80 136	32.25 125	37.88 134	39.99 134	52.96 141	35.20 139	33.60 136	24.47 128	0.26 94	0.39 116	0.31 119	0.39 115	0.26 76	0.53 99

DispFullNet	17.47 134	26.01 140	33.98 133	22.58 141	20.86 141	13.84 105	1.28 45	16.50 104	26.27 118	19.97 111	17.17 86	20.52 112	18.49 116	22.86 127	10.76 99	5.13 136	2.83 137	30.72 141	7.72 139	20.86 141	11.01 141

EDNetEfficientorigin	17.87 135	14.00 138	99.53 146	1.64 32	0.92 38	10.55 86	6.26 100	13.21 78	34.84 129	38.20 135	36.91 131	27.47 124	26.32 134	14.71 106	25.69 131	0.04 57	0.06 73	0.14 105	0.52 122	3.16 132	3.27 133

RTS	18.87 136	9.32 135	86.48 141	4.95 125	6.10 128	42.08 138	14.70 131	15.49 100	41.06 137	22.65 116	32.32 121	13.77 74	19.54 120	37.98 137	28.96 134	0.41 106	0.23 109	0.00 1	0.02 61	0.91 110	0.50 95

RTSA	18.87 136	9.32 135	86.48 141	4.95 125	6.10 128	42.08 138	14.70 131	15.49 100	41.06 137	22.65 116	32.32 121	13.77 74	19.54 120	37.98 137	28.96 134	0.41 106	0.23 109	0.00 1	0.02 61	0.91 110	0.50 95

MANE	19.47 138	1.27 72	5.07 47	4.69 123	5.55 125	30.49 132	9.94 119	34.01 139	37.27 134	44.13 139	51.57 142	52.51 140	40.41 141	33.58 135	24.81 129	0.89 122	0.86 127	1.11 133	9.72 140	0.38 88	1.06 116

BEATNet-Init1	23.31 139	9.03 134	41.67 134	4.17 119	2.53 83	45.68 140	19.47 138	33.43 138	38.45 136	47.59 141	49.10 140	59.31 142	41.80 142	38.35 139	29.21 136	0.47 111	0.50 124	0.81 129	0.66 124	2.10 128	1.86 125

MADNet+	27.07 140	33.84 141	90.97 143	20.14 140	7.47 136	48.43 141	47.10 140	35.43 140	36.46 131	20.11 112	30.05 117	25.29 118	35.08 138	45.50 142	50.28 141	2.13 130	2.00 134	1.19 135	0.76 126	4.71 134	4.43 134

PWCK	30.53 141	44.32 142	47.25 136	29.76 142	7.23 133	40.78 137	27.10 139	44.73 142	44.32 139	47.31 140	36.37 130	47.16 139	26.05 132	41.26 141	31.87 138	21.83 141	4.03 139	29.50 140	4.67 138	27.17 142	7.80 139

DPSimNet_ROB	53.45 142	64.73 143	44.39 135	53.97 143	45.39 143	53.66 142	54.83 141	55.15 143	57.87 143	64.16 143	50.83 141	63.40 143	53.34 143	46.45 143	65.81 142	63.13 144	26.54 143	57.94 144	51.11 143	45.52 143	50.69 143

ASD4	75.85 143	81.57 144	69.25 139	68.23 144	80.87 144	96.24 144	99.15 146	77.50 144	93.47 145	77.59 144	85.63 143	78.32 144	76.43 144	77.89 144	82.61 143	58.30 143	62.67 144	55.02 143	62.43 144	68.35 144	65.49 144

MADNet++	82.84 144	82.38 145	73.57 140	87.72 145	82.97 145	93.14 143	69.15 142	86.42 145	82.50 144	93.46 145	86.70 144	86.28 145	80.92 145	88.34 145	88.84 144	86.83 145	84.17 145	72.64 145	68.92 145	80.47 145	81.42 145

MEDIAN_ROB	98.41 145	99.70 146	99.30 145	97.09 146	97.02 146	96.89 145	95.77 145	97.66 146	97.28 146	98.79 148	98.94 145	99.18 146	98.14 146	96.89 146	96.88 145	99.96 148	99.16 146	100.00 146	99.99 146	99.69 146	99.88 146

AVERAGE_ROB	99.62 146	99.95 147	98.81 144	100.00 151	100.00 147	98.08 146	95.47 144	100.00 149	100.00 147	100.00 149	100.00 146	100.00 149	100.00 147	100.00 149	99.99 146	100.00 150	100.00 147	100.00 146	100.00 147	100.00 149	100.00 150

DGTPSM_ROB	99.90 147	100.00 148	99.99 147	99.99 149	100.00 147	100.00 147	100.00 147	99.97 147	100.00 147	98.35 146	100.00 146	99.84 147	100.00 147	99.98 147	99.99 146	99.99 149	100.00 147	100.00 146	100.00 147	100.00 149	100.00 150

DPSMNet_ROB	99.91 148	100.00 148	99.99 147	99.99 149	100.00 147	100.00 147	100.00 147	99.98 148	100.00 147	98.35 146	100.00 146	99.84 147	100.00 147	99.98 147	99.99 146	100.00 150	100.00 147	100.00 146	100.00 147	100.00 149	100.00 150

DPSM_ROB	99.95 149	100.00 148	100.00 149	99.76 147	100.00 147	100.00 147	100.00 147	100.00 149	100.00 147	100.00 149	100.00 146	100.00 149	100.00 147	100.00 149	100.00 149	99.21 146	100.00 147	100.00 146	100.00 147	99.99 147	99.95 147

DPSM	99.95 149	100.00 148	100.00 149	99.76 147	100.00 147	100.00 147	100.00 147	100.00 149	100.00 147	100.00 149	100.00 146	100.00 149	100.00 147	100.00 149	100.00 149	99.21 146	100.00 147	100.00 146	100.00 147	99.99 147	99.95 147

LSM0	100.00 151	100.00 148	100.00 149	100.00 151	100.00 147	100.00 147	100.00 147	100.00 149	100.00 147	100.00 149	100.00 146	100.00 149	100.00 147	100.00 149	100.00 149	100.00 150	100.00 147	100.00 146	100.00 147	100.00 149	99.99 149

FADE		17.27 139		10.46 137	9.90 138			35.80 141	53.05 141	20.32 113		26.54 121		39.35 140		30.62 142	14.22 142	38.39 142	37.63 142	5.22 136	5.56 135

MSMDNet													1.26 7

Low-res two-view benchmark