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 19	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 9	3.39 1	5.33 10	1.00 2	1.27 1	0.28 1	0.93 5	4.04 9	0.74 4	5.00 129	0.00 1	0.00 1	0.00 1	0.03 13	0.01 2

DPM-Stereo	1.97 3	0.64 26	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 36	0.00 1	0.00 1	0.05 19	0.04 24

Gwc-CoAtRS	2.02 4	0.33 6	2.61 5	1.04 10	0.30 10	3.56 16	0.40 12	5.89 4	5.94 16	5.08 13	5.01 7	5.55 15	1.72 9	1.60 2	0.91 5	0.01 27	0.09 81	0.00 1	0.25 98	0.01 2	0.02 6

FENet	2.19 5	0.34 7	3.04 14	2.05 49	0.26 9	2.82 10	0.13 3	7.02 8	5.55 12	4.97 12	1.94 3	4.91 11	3.39 22	4.71 12	2.50 13	0.02 34	0.03 53	0.00 1	0.00 1	0.00 1	0.21 60

R-Stereo Train	2.44 6	0.32 1	1.93 2	0.94 7	0.16 5	3.67 18	0.61 23	6.37 6	3.08 1	9.14 49	17.44 82	1.80 4	0.77 3	1.76 3	0.70 2	0.00 1	0.01 36	0.00 1	0.00 1	0.01 2	0.03 15

RAFT-Stereo	2.44 6	0.32 1	1.93 2	0.94 7	0.16 5	3.67 18	0.61 23	6.37 6	3.08 1	9.14 49	17.44 82	1.80 4	0.77 3	1.76 3	0.70 2	0.00 1	0.01 36	0.00 1	0.00 1	0.01 2	0.03 15
Lahav Lipson, Zachary Teed, and Jia Deng: RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching. 3DV
ACVNet	2.58 8	0.53 17	2.69 7	0.84 5	0.59 20	2.61 6	0.55 18	8.35 12	5.70 13	4.45 7	9.26 29	5.77 17	3.50 24	2.24 5	4.41 38	0.00 1	0.00 1	0.00 1	0.00 1	0.17 51	0.01 2

DN-CSS_ROB	2.69 9	1.40 72	5.34 47	2.31 64	0.75 27	3.14 15	0.06 2	6.11 5	3.87 3	5.34 16	12.18 52	2.34 6	1.22 6	7.84 32	1.48 6	0.03 45	0.00 1	0.00 1	0.00 1	0.35 80	0.03 15

HITNet	2.79 10	0.77 30	4.02 30	2.03 48	0.11 3	5.58 43	0.59 22	9.24 23	5.15 9	6.42 26	7.26 18	3.66 7	2.92 20	4.07 10	3.87 35	0.00 1	0.00 1	0.00 1	0.00 1	0.06 24	0.02 6
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 26	4.45 36	1.61 27	0.89 34	3.86 22	0.57 21	9.18 21	5.10 8	6.24 22	6.49 12	7.17 31	2.13 12	3.31 7	4.73 42	0.00 1	0.01 36	0.00 1	0.00 1	0.04 16	0.02 6

ccs	3.04 12	0.39 9	3.08 16	1.78 34	0.52 19	2.04 2	0.50 16	13.09 71	13.71 75	3.54 5	5.36 10	5.50 14	2.45 14	4.81 13	2.88 16	0.09 66	0.08 77	0.12 96	0.10 86	0.20 56	0.50 89

AdaStereo	3.09 13	0.58 21	3.04 14	2.84 82	0.48 18	4.08 25	1.29 44	12.16 62	7.77 38	6.03 20	9.62 31	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 6
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 65	6.39 65	2.10 52	1.51 53	3.02 14	0.56 20	7.84 11	5.06 7	9.23 52	5.19 8	8.46 39	2.72 18	6.31 18	3.22 23	0.06 62	0.11 84	0.09 93	0.02 56	0.16 49	0.08 31

BEATNet_4x	3.24 15	1.27 66	5.89 56	1.56 24	0.10 1	5.26 40	1.07 39	10.08 30	5.50 11	6.89 31	7.73 20	4.53 10	4.13 34	5.05 14	5.27 46	0.04 53	0.05 62	0.00 1	0.00 1	0.23 70	0.23 63

GANet-RSSM	3.27 16	0.60 22	3.38 20	2.94 89	2.00 68	2.61 6	0.48 14	10.93 50	6.11 17	5.47 17	10.20 35	6.57 23	5.44 55	6.25 17	2.23 11	0.00 1	0.00 1	0.08 90	0.00 1	0.17 51	0.03 15

NOSS_ROB	3.30 17	0.46 11	2.62 6	2.08 50	1.01 42	5.60 44	0.74 34	10.37 38	11.48 65	5.15 14	8.43 25	5.67 16	1.73 10	7.97 34	2.34 12	0.02 34	0.06 68	0.00 1	0.00 1	0.07 26	0.14 51

CFNet-ft	3.31 18	0.94 44	2.69 7	1.50 21	2.38 75	2.81 8	0.68 28	8.35 12	7.43 32	4.45 7	9.94 32	10.20 49	4.60 40	6.50 21	3.41 27	0.00 1	0.00 1	0.03 74	0.00 1	0.22 65	0.03 15

CFNet_RVC	3.31 18	0.94 44	2.69 7	1.50 21	2.38 75	2.81 8	0.68 28	8.35 12	7.43 32	4.45 7	9.94 32	10.20 49	4.60 40	6.49 20	3.41 27	0.00 1	0.00 1	0.03 74	0.00 1	0.22 65	0.03 15

PSMNet-RSSM	3.33 20	0.77 30	3.22 19	2.12 53	1.90 67	2.33 4	0.71 31	11.17 51	5.83 15	5.90 18	11.43 47	7.04 27	4.83 49	5.96 16	3.17 21	0.00 1	0.00 1	0.02 66	0.00 1	0.08 28	0.02 6

cf-r	3.42 21	0.81 33	3.97 29	2.41 68	2.78 84	2.85 11	0.64 27	8.44 15	6.32 18	6.25 23	11.57 48	8.97 43	3.54 26	5.93 15	3.83 34	0.00 1	0.00 1	0.00 1	0.00 1	0.09 32	0.07 28

MLCV	3.44 22	0.88 37	5.60 51	1.39 17	0.25 8	4.36 29	0.33 8	7.25 9	7.28 29	9.17 51	12.24 54	5.09 12	2.47 15	9.15 56	3.23 24	0.00 1	0.00 1	0.00 1	0.00 1	0.10 33	0.02 6

DeepPruner_ROB	3.52 23	1.14 59	4.06 31	1.12 11	1.65 57	3.65 17	0.83 36	13.96 80	4.47 6	7.80 37	10.84 40	7.05 29	2.16 13	8.14 41	3.08 20	0.07 64	0.03 53	0.00 1	0.01 52	0.32 76	0.06 27

STTStereo	3.60 24	0.93 43	6.34 63	2.71 79	2.23 73	3.68 20	0.63 26	9.42 24	6.73 22	9.87 60	6.97 16	8.84 42	3.65 27	6.85 22	3.04 18	0.00 1	0.02 47	0.01 54	0.00 1	0.02 7	0.02 6

ccs_rob	3.63 25	1.12 58	4.42 34	2.52 71	0.91 37	5.50 42	0.21 6	10.11 33	9.11 48	6.55 29	11.28 44	8.32 38	2.55 16	7.66 29	2.01 10	0.00 1	0.00 1	0.00 1	0.00 1	0.20 56	0.08 31

hitnet-ft	3.66 26	0.65 28	2.79 11	0.89 6	0.72 26	4.25 27	0.55 18	9.11 20	7.52 34	7.14 33	10.19 34	12.49 65	4.70 44	7.44 27	4.41 38	0.03 45	0.00 1	0.06 86	0.00 1	0.20 56	0.04 24

iResNet	3.68 27	0.91 40	7.94 81	2.97 90	0.34 12	4.44 33	0.48 14	7.70 10	9.74 52	7.72 36	12.74 58	4.03 8	2.87 19	8.05 37	3.37 26	0.02 34	0.01 36	0.00 1	0.00 1	0.10 33	0.09 35

acv_ft	3.69 28	0.53 17	4.58 38	2.31 64	4.71 116	7.44 63	0.86 37	8.54 16	5.70 13	9.29 53	9.26 29	5.77 17	4.15 35	2.24 5	8.13 70	0.00 1	0.00 1	0.00 1	0.00 1	0.29 72	0.01 2

ac_64	3.70 29	0.47 12	3.50 23	2.87 83	3.50 96	5.91 47	0.72 32	10.17 35	4.34 5	8.16 41	5.80 11	10.82 54	5.64 57	7.08 24	4.73 42	0.03 45	0.00 1	0.00 1	0.00 1	0.08 28	0.14 51

CFNet	3.72 30	1.10 56	5.03 42	2.49 70	1.59 54	4.90 38	0.22 7	11.38 52	9.88 54	4.80 10	11.25 43	6.44 22	3.68 28	8.33 43	3.00 17	0.00 1	0.00 1	0.00 1	0.00 1	0.22 65	0.07 28

GwcNet-RSSM	3.77 31	1.05 50	5.06 43	2.21 58	1.87 65	2.36 5	1.52 47	8.98 19	7.96 39	5.91 19	14.59 67	7.94 36	3.50 24	6.43 19	5.70 49	0.00 1	0.00 1	0.04 81	0.00 1	0.20 56	0.08 31

FADNet-RVC-Resample	3.79 32	1.62 84	12.06 96	1.43 19	0.66 22	5.94 48	2.41 55	10.18 36	8.58 46	6.28 24	4.22 5	5.33 13	4.80 48	7.71 30	3.19 22	0.17 80	0.21 101	0.17 103	0.12 88	0.41 88	0.29 76

CC-Net-ROB	3.84 33	1.07 52	5.23 45	2.65 76	2.96 87	4.22 26	0.69 30	10.43 40	7.72 36	8.78 46	8.29 24	9.61 46	4.02 33	7.16 26	3.65 32	0.13 73	0.03 53	0.02 66	0.03 65	0.05 19	0.03 15

NLCA_NET_v2_RVC	3.84 33	1.06 51	5.23 45	2.72 80	3.27 89	4.36 29	0.61 23	10.71 45	7.56 35	8.75 45	7.89 21	9.86 48	3.90 31	7.15 25	3.44 29	0.14 74	0.02 47	0.02 66	0.03 65	0.04 16	0.03 15
Zhibo Rao, Mingyi He, Yuchao Dai, Zhidong Zhu, Bo Li, and Renjie He.: NLCA-Net: A non-local context attention network for stereo matching.
FADNet_RVC	3.91 35	1.67 87	12.95 102	0.96 9	0.75 27	5.71 46	0.54 17	10.83 48	6.60 21	3.46 3	8.09 22	4.10 9	3.40 23	9.43 60	6.33 52	0.36 97	0.44 115	0.17 103	0.46 115	0.91 105	0.95 108

FADNet-RVC	3.98 36	1.84 93	12.48 99	1.69 32	0.44 16	4.33 28	1.31 45	11.84 56	7.15 27	3.53 4	3.50 4	10.63 53	4.43 39	9.12 55	6.25 51	0.03 45	0.10 82	0.00 1	0.03 65	0.60 95	0.25 69

HSM	4.00 37	0.79 32	3.16 18	1.59 26	2.17 71	6.77 57	1.11 40	12.28 63	6.35 20	6.75 30	8.11 23	13.90 71	5.37 54	8.85 51	2.71 15	0.00 1	0.00 1	0.00 1	0.00 1	0.02 7	0.02 6

TDLM	4.11 38	1.11 57	3.54 24	1.62 28	1.04 43	3.91 23	7.41 104	10.60 43	10.67 59	6.38 25	12.59 57	5.95 20	4.77 46	8.79 50	3.04 18	0.58 109	0.00 1	0.01 54	0.00 1	0.19 55	0.12 46

CBMV_ROB	4.14 39	0.52 14	3.14 17	1.30 14	0.77 30	6.92 58	1.97 53	10.11 33	9.58 50	8.92 48	14.20 66	7.12 30	5.90 60	8.65 47	3.50 31	0.01 27	0.05 62	0.00 1	0.00 1	0.04 16	0.09 35

CVANet_RVC	4.16 40	1.16 60	3.60 25	1.94 44	1.46 51	3.92 24	4.68 83	10.89 49	8.34 44	7.58 35	10.84 40	10.27 51	6.62 64	8.56 46	2.69 14	0.39 99	0.00 1	0.00 1	0.01 52	0.21 63	0.09 35

HSM-Net_RVC	4.20 41	0.32 1	2.76 10	0.63 4	0.69 24	6.95 59	1.69 50	11.96 57	8.36 45	8.83 47	12.17 51	15.18 79	4.21 37	6.91 23	3.30 25	0.02 34	0.02 47	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 42	0.50 13	5.45 49	1.34 15	1.68 59	7.04 60	4.51 80	10.73 46	7.00 24	10.78 68	6.80 13	8.48 40	4.63 42	9.91 64	5.12 45	0.02 34	0.06 68	0.02 66	0.03 65	0.08 28	0.03 15

FADNet	4.23 43	1.65 86	11.75 95	1.64 30	0.80 32	4.80 35	0.77 35	13.76 79	11.65 67	3.97 6	5.24 9	9.62 47	5.14 51	8.40 44	3.78 33	0.21 84	0.04 58	0.07 89	0.05 76	1.14 110	0.10 42

iResNet_ROB	4.23 43	1.02 48	4.90 41	2.18 55	0.93 40	2.92 12	0.37 11	15.10 91	16.91 90	7.89 39	10.51 38	7.03 26	3.07 21	8.16 42	3.46 30	0.01 27	0.00 1	0.00 1	0.00 1	0.10 33	0.02 6

HGLStereo	4.25 45	0.52 14	4.65 39	3.09 92	5.18 118	6.51 55	0.73 33	10.37 38	6.74 23	7.32 34	12.44 56	7.00 25	7.21 68	7.46 28	5.51 48	0.00 1	0.02 47	0.00 1	0.00 1	0.06 24	0.10 42

iResNetv2_ROB	4.28 46	1.43 73	7.17 76	2.91 84	1.26 47	4.36 29	1.62 48	13.64 78	10.25 58	9.83 59	11.41 45	7.68 33	4.00 32	7.75 31	1.85 8	0.00 1	0.00 1	0.00 1	0.00 1	0.37 82	0.09 35

StereoDRNet-Refined	4.46 47	0.62 25	3.80 28	1.92 41	0.40 14	9.35 71	0.15 5	10.02 28	8.83 47	12.69 80	11.62 49	9.34 44	3.87 30	8.06 38	8.02 66	0.00 1	0.00 1	0.01 54	0.05 76	0.20 56	0.26 72
Rohan Chabra, Julian Straub, Chris Sweeney, Richard Newcombe, Henry Fuchs: StereoDRNet. CVPR
NVstereo2D	4.51 48	0.82 34	6.86 74	3.28 97	3.38 93	8.16 66	3.13 60	10.51 41	15.15 80	4.90 11	6.89 15	7.87 34	4.78 47	9.88 63	3.91 36	0.01 27	0.00 1	0.00 1	0.06 78	0.02 7	0.58 95

DLCB_ROB	4.51 48	0.91 40	3.78 27	2.19 56	1.07 44	6.28 49	3.09 59	9.78 27	7.72 36	10.65 66	12.97 59	13.91 72	3.71 29	8.72 48	5.30 47	0.00 1	0.00 1	0.00 1	0.00 1	0.03 13	0.10 42

RASNet	4.52 50	0.61 24	4.42 34	3.42 100	4.68 115	4.58 34	0.99 38	9.54 26	8.01 40	5.28 15	11.42 46	10.34 52	8.88 78	9.28 58	8.68 75	0.15 76	0.00 1	0.00 1	0.00 1	0.03 13	0.04 24

SGM-Forest	4.96 51	0.32 1	2.84 12	1.21 12	0.64 21	10.23 81	6.64 99	11.55 53	10.98 60	10.94 70	13.59 62	11.65 60	4.30 38	8.94 53	4.63 41	0.11 69	0.04 58	0.00 1	0.00 1	0.05 19	0.46 86
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 52	1.47 75	7.42 78	2.40 67	2.14 70	8.73 68	3.64 69	12.42 64	13.11 71	7.03 32	7.57 19	7.88 35	6.52 63	10.16 66	7.82 64	0.02 34	0.03 53	0.00 1	0.00 1	0.11 37	1.07 111
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 53	1.74 88	6.38 64	1.96 46	1.29 49	2.26 3	1.69 50	10.07 29	18.53 93	7.88 38	18.15 84	8.49 41	2.70 17	10.59 70	7.04 57	0.96 119	0.15 93	0.02 66	0.00 1	0.13 42	0.12 46

PSMNet_ROB	5.02 54	1.63 85	6.03 58	1.90 40	1.83 64	9.57 75	6.35 96	15.58 96	7.23 28	6.15 21	10.48 37	12.22 63	4.16 36	8.02 35	8.71 76	0.02 34	0.01 36	0.01 54	0.10 86	0.20 56	0.12 46

CBMV	5.35 55	0.91 40	3.67 26	1.62 28	0.44 16	10.09 79	7.19 103	12.49 65	12.33 70	12.22 76	14.69 68	10.93 56	6.48 62	8.51 45	4.96 44	0.02 34	0.15 93	0.00 1	0.00 1	0.17 51	0.17 56
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 56	1.75 89	6.80 72	3.12 93	4.45 110	10.61 84	4.35 76	18.80 108	9.73 51	12.22 76	6.87 14	11.44 59	4.65 43	8.09 40	8.26 71	0.02 34	0.11 84	0.00 1	0.03 65	0.20 56	0.28 75

ETE_ROB	5.80 57	1.77 90	6.33 62	1.44 20	0.78 31	6.43 53	6.90 100	12.53 66	8.08 41	12.93 84	14.89 69	21.13 107	5.87 59	9.83 62	6.57 55	0.04 53	0.01 36	0.00 1	0.02 56	0.08 28	0.33 77

DRN-Test	5.87 58	0.98 46	5.89 56	2.69 78	3.65 101	12.37 91	3.35 63	20.07 119	10.20 57	11.93 75	12.31 55	11.06 58	5.31 53	7.89 33	9.05 79	0.04 53	0.05 62	0.04 81	0.04 74	0.18 54	0.25 69

NCCL2	5.88 59	1.59 82	5.44 48	1.87 37	0.92 38	9.55 74	11.55 119	12.11 59	9.94 55	9.67 58	8.85 27	22.28 109	7.41 69	8.78 49	7.17 58	0.01 27	0.00 1	0.03 74	0.00 1	0.13 42	0.23 63

NaN_ROB	6.00 60	1.24 63	6.29 61	1.34 15	1.68 59	9.60 76	10.31 115	15.09 89	15.79 83	12.62 79	8.95 28	11.67 61	5.83 58	11.78 79	6.41 54	0.05 60	0.13 90	0.08 90	0.20 94	0.22 65	0.79 103

DANet	6.02 61	1.23 62	8.45 83	3.86 109	3.94 104	7.64 65	1.34 46	9.51 25	7.00 24	13.39 86	15.53 73	15.99 83	7.02 67	12.14 80	12.37 99	0.19 82	0.12 89	0.02 66	0.03 65	0.13 42	0.56 94

XPNet_ROB	6.03 62	1.22 61	5.61 52	2.56 74	0.90 36	6.32 50	7.07 101	12.92 69	8.30 43	14.76 91	15.13 71	19.84 101	6.66 66	10.36 67	8.58 74	0.02 34	0.04 58	0.00 1	0.03 65	0.11 37	0.24 66

Anonymous Stereo	6.16 63	3.15 111	23.75 120	2.97 90	2.48 80	4.39 32	13.30 121	9.21 22	9.86 53	9.56 57	8.76 26	6.79 24	1.99 11	13.50 91	13.04 102	0.01 27	0.05 62	0.00 1	0.06 78	0.22 65	0.19 58

GANet	6.22 64	1.07 52	4.07 32	2.27 60	0.89 34	9.19 70	9.52 110	12.02 58	8.13 42	10.72 67	29.09 109	13.86 70	7.52 71	11.00 74	4.39 37	0.36 97	0.00 1	0.02 66	0.02 56	0.12 39	0.08 31

DISCO	6.28 65	0.57 20	5.78 54	3.43 101	1.17 45	11.22 86	3.39 64	12.14 61	16.16 85	6.52 28	11.22 42	16.96 86	6.32 61	19.51 114	10.74 92	0.00 1	0.00 1	0.00 1	0.00 1	0.35 80	0.11 45

RYNet	6.34 66	0.89 39	5.88 55	1.41 18	4.48 112	15.97 102	4.18 72	13.41 74	16.49 86	10.81 69	7.00 17	14.33 74	8.72 77	9.43 60	13.71 103	0.00 1	0.01 36	0.00 1	0.00 1	0.02 7	0.07 28

GwcNet	6.42 67	1.97 96	10.92 90	2.59 75	5.58 121	11.55 88	2.21 54	14.10 82	16.52 89	10.04 62	17.19 81	10.86 55	5.61 56	9.23 57	8.84 78	0.01 27	0.06 68	0.03 74	0.08 82	0.56 91	0.40 81

GANetREF_RVC	6.56 68	2.89 106	7.58 80	3.41 99	0.40 14	12.96 94	9.58 111	15.09 89	17.25 92	10.33 63	10.62 39	12.27 64	8.16 73	12.21 81	4.53 40	0.41 101	0.00 1	0.00 1	0.02 56	3.12 125	0.39 80
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 69	1.80 92	6.25 60	1.26 13	0.94 41	10.08 78	9.02 107	16.00 97	11.51 66	12.74 81	13.02 60	24.77 111	5.25 52	10.56 69	8.02 66	0.04 53	0.05 62	0.00 1	0.02 56	0.10 33	0.25 69

S-Stereo	6.63 70	0.84 35	9.67 87	3.15 94	3.48 95	6.49 54	6.22 91	12.99 70	22.84 106	9.48 54	15.51 72	12.00 62	8.43 74	8.04 36	10.70 91	0.12 72	0.17 97	0.00 1	0.38 108	0.13 42	1.92 120

DeepPrunerF	6.75 71	2.69 104	23.31 119	3.68 104	7.16 126	3.78 21	4.29 74	13.42 75	20.13 103	8.13 40	10.46 36	7.18 32	8.06 72	11.10 75	9.44 81	0.24 86	0.15 93	0.29 112	0.42 111	0.66 98	0.45 84

edge stereo	6.76 72	1.01 47	6.76 71	2.20 57	2.45 79	6.41 52	2.45 56	14.84 88	11.98 69	15.29 92	18.31 85	22.02 108	12.56 93	10.82 71	7.49 60	0.03 45	0.06 68	0.11 95	0.03 65	0.30 73	0.14 51

Abc-Net	6.77 73	1.49 76	6.48 66	2.92 86	4.40 106	7.43 61	3.61 67	19.52 115	13.29 72	8.39 43	16.91 76	15.96 81	12.13 91	12.85 85	7.70 62	1.47 123	0.11 84	0.01 54	0.42 111	0.14 47	0.24 66
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 73	1.49 76	6.48 66	2.92 86	4.40 106	7.43 61	3.61 67	19.52 115	13.29 72	8.39 43	16.91 76	15.96 81	12.13 91	12.85 85	7.70 62	1.47 123	0.11 84	0.01 54	0.42 111	0.14 47	0.24 66

FAT-Stereo	6.78 75	0.68 29	6.80 72	2.30 62	1.77 63	5.63 45	4.20 73	18.79 107	18.62 94	10.53 65	17.15 79	18.52 95	13.74 101	8.86 52	7.38 59	0.03 45	0.15 93	0.01 54	0.07 80	0.12 39	0.26 72

RP	6.84 76	1.29 70	5.53 50	3.92 110	5.18 118	6.32 50	3.53 65	11.73 55	15.31 81	9.54 56	22.38 92	18.25 93	14.47 102	10.11 65	7.49 60	0.91 118	0.01 36	0.12 96	0.15 90	0.33 77	0.19 58

RGC	6.88 77	2.23 100	6.13 59	4.05 111	4.73 117	8.94 69	2.78 58	15.19 93	11.74 68	11.13 71	19.34 87	17.86 90	10.42 85	13.02 88	8.03 68	0.73 112	0.01 36	0.24 111	0.41 110	0.31 75	0.38 79

Nwc_Net	6.97 78	1.25 64	6.63 69	3.82 108	3.37 92	10.83 85	1.67 49	19.56 117	11.35 63	8.36 42	23.62 95	17.19 88	11.44 90	11.21 76	8.08 69	0.80 114	0.00 1	0.00 1	0.02 56	0.13 42	0.09 35

ADCRef	7.27 79	1.38 71	16.37 108	2.52 71	3.30 91	11.63 89	3.16 61	10.80 47	9.35 49	13.03 85	25.27 103	8.17 37	8.92 79	8.06 38	21.81 118	0.15 76	0.08 77	0.16 102	0.34 106	0.38 83	0.58 95

psmorigin	7.34 80	1.58 81	18.31 112	2.35 66	0.87 33	6.72 56	1.70 52	10.63 44	7.14 26	19.77 104	22.71 93	20.13 103	11.34 89	12.96 87	9.49 82	0.04 53	0.17 97	0.06 86	0.17 91	0.21 63	0.50 89

CSAN	7.62 81	1.60 83	6.56 68	1.83 35	0.66 22	12.40 92	10.52 117	14.45 85	21.32 105	14.19 88	15.98 75	17.84 89	13.02 98	12.32 82	8.38 72	0.09 66	0.07 75	0.03 74	0.04 74	0.33 77	0.67 101

stereogan	7.69 82	0.88 37	7.08 75	3.49 102	3.93 103	18.98 110	3.23 62	16.52 99	19.58 100	9.93 61	18.92 86	20.50 105	9.04 80	14.07 95	6.14 50	0.26 89	0.04 58	0.21 108	0.03 65	0.63 97	0.33 77

pmcnn	7.72 83	1.27 66	9.42 86	2.91 84	3.14 88	9.44 72	6.23 92	12.56 67	16.51 87	14.53 89	24.08 97	27.44 116	8.49 75	9.32 59	8.44 73	0.06 62	0.08 77	0.00 1	0.00 1	0.30 73	0.15 54

AF-Net	7.78 84	1.44 74	6.68 70	3.37 98	4.50 113	8.61 67	2.69 57	17.07 102	20.17 104	9.52 55	24.02 96	20.31 104	14.59 103	11.58 78	9.84 87	0.61 110	0.00 1	0.12 96	0.00 1	0.38 83	0.12 46

PASM	7.90 85	4.22 117	21.97 117	3.25 96	3.29 90	5.39 41	6.57 98	10.57 42	19.09 96	12.77 82	13.92 64	18.11 92	9.51 82	13.79 94	10.77 94	0.19 82	0.45 116	0.29 112	1.08 124	1.49 117	1.19 113

PWCDC_ROB	7.92 86	3.17 113	7.48 79	5.73 122	4.40 106	10.45 82	0.35 10	14.52 86	28.19 114	10.36 64	31.27 113	7.04 27	9.14 81	13.22 90	8.78 77	2.74 128	0.02 47	0.00 1	0.00 1	1.31 115	0.17 56

ADCP+	8.09 87	1.79 91	14.50 106	1.54 23	4.28 105	16.57 104	5.20 85	12.80 68	11.20 62	12.83 83	17.07 78	11.02 57	10.80 87	17.59 110	23.18 121	0.03 45	0.05 62	0.01 54	0.18 92	0.39 87	0.81 104

SuperB	8.10 88	3.15 111	24.67 121	2.65 76	1.23 46	9.88 77	4.29 74	10.18 36	30.07 117	11.53 73	12.18 52	6.12 21	6.65 65	10.50 68	14.47 105	0.14 74	0.11 84	0.35 116	0.25 98	13.06 133	0.48 87

PWC_ROB	8.24 89	3.13 109	12.74 100	2.43 69	4.43 109	7.51 64	1.22 41	16.63 100	19.24 98	16.08 94	28.29 106	13.99 73	10.16 84	13.63 93	14.06 104	0.42 104	0.00 1	0.05 84	0.00 1	0.59 94	0.27 74

MDST_ROB	8.37 90	0.32 1	9.03 84	4.18 114	2.42 78	26.86 123	6.14 89	19.36 112	13.52 74	27.09 118	22.75 94	9.47 45	4.74 45	15.06 101	6.34 53	0.02 34	0.02 47	0.00 1	0.00 1	0.02 7	0.13 50

STTStereo_v2	8.41 91	1.54 79	10.97 91	5.73 122	3.60 98	26.19 120	4.41 77	10.10 31	7.42 30	19.71 102	24.99 101	14.38 75	15.83 104	10.99 72	9.53 83	0.50 107	0.46 117	0.19 106	0.25 98	0.80 102	0.66 99

G-Net	8.41 91	1.54 79	10.97 91	5.73 122	3.60 98	26.19 120	4.41 77	10.10 31	7.42 30	19.71 102	24.99 101	14.38 75	15.83 104	10.99 72	9.53 83	0.50 107	0.46 117	0.19 106	0.25 98	0.80 102	0.66 99

XQC	8.43 93	3.58 115	16.40 109	2.92 86	2.17 71	13.22 96	3.60 66	14.64 87	25.86 111	11.87 74	12.04 50	15.06 78	10.67 86	15.24 102	19.41 110	0.39 99	0.08 77	0.05 84	0.07 80	0.84 104	0.45 84

FBW_ROB	8.50 94	1.03 49	7.98 82	1.93 43	1.28 48	13.10 95	6.23 92	22.50 123	18.98 95	18.82 99	14.91 70	19.06 98	10.04 83	18.41 111	9.83 86	0.62 111	0.22 102	1.82 130	0.82 121	0.99 108	1.36 115

aanetorigin	8.72 95	3.29 114	27.55 123	1.95 45	3.84 102	4.93 39	5.39 87	5.49 3	10.05 56	27.85 119	31.47 114	15.80 80	12.78 95	9.04 54	11.98 97	0.25 87	0.22 102	0.22 109	0.25 98	1.28 114	0.84 106

RTSC	9.15 96	3.00 108	13.57 104	3.72 106	1.76 62	11.82 90	0.46 13	16.95 101	36.83 126	15.80 93	15.53 73	12.91 67	7.46 70	20.01 117	21.76 117	0.31 94	0.13 90	0.01 54	0.08 82	0.57 92	0.41 83

WCMA_ROB	9.21 97	0.87 36	7.37 77	2.54 73	2.13 69	13.59 97	5.80 88	11.64 54	14.01 76	24.43 115	32.99 119	27.09 115	18.02 108	12.51 84	9.85 88	0.81 115	0.07 75	0.01 54	0.01 52	0.16 49	0.23 63

MSMD_ROB	9.28 98	1.09 55	4.65 39	1.58 25	0.39 13	16.52 103	4.41 77	13.60 76	14.87 79	22.34 107	39.89 127	25.67 113	20.71 117	12.42 83	6.98 56	0.34 96	0.03 53	0.00 1	0.00 1	0.05 19	0.09 35

ADCPNet	9.54 99	2.39 102	31.46 125	2.09 51	1.60 55	16.71 106	6.39 97	12.11 59	11.45 64	13.53 87	21.45 90	19.41 99	10.94 88	14.38 97	21.54 116	0.27 92	1.16 124	0.39 119	1.49 128	0.58 93	1.45 116

SHD	9.61 100	2.60 103	12.46 98	3.69 105	3.54 97	9.47 73	1.25 42	20.16 120	37.84 129	18.19 98	21.24 89	16.96 86	12.83 97	14.47 99	16.05 107	0.32 95	0.13 90	0.01 54	0.08 82	0.38 83	0.48 87

PDISCO_ROB	9.62 101	1.99 97	11.51 93	9.88 130	9.61 131	21.48 114	3.83 70	19.33 111	28.49 115	11.27 72	14.17 65	19.92 102	5.02 50	16.35 107	9.18 80	5.28 131	0.41 112	0.14 100	0.09 85	2.05 121	2.36 126

MFN_U_SF_DS_RVC	9.78 102	4.27 118	14.47 105	2.29 61	2.85 86	23.40 118	13.62 122	13.60 76	19.54 99	19.42 101	24.27 98	16.74 85	8.59 76	17.05 109	7.98 65	1.25 122	1.68 128	0.17 103	2.63 130	0.72 100	1.04 109

SGM_RVC	10.08 103	0.60 22	3.42 21	2.30 62	0.32 11	19.41 111	6.33 95	18.95 109	14.64 77	25.14 117	24.32 99	33.34 124	18.79 112	19.86 115	12.55 101	0.25 87	0.26 107	0.22 109	0.24 97	0.34 79	0.40 81
Heiko Hirschmueller: Stereo processing by semiglobal matching and mutual information. TPAMI 2008, Volume 30(2), pp. 328-341
DPSNet	10.14 104	1.88 95	16.82 110	1.85 36	1.73 61	24.84 119	17.20 131	19.92 118	27.41 113	12.23 78	13.62 63	16.52 84	18.35 109	14.42 98	12.50 100	0.78 113	0.54 121	0.08 90	0.25 98	1.18 111	0.59 98

ADCL	10.16 105	2.11 98	19.36 114	1.92 41	1.88 66	22.23 115	8.91 106	14.04 81	23.56 108	14.62 90	26.19 104	12.75 66	13.59 100	16.06 106	22.95 120	0.26 89	0.18 99	0.75 122	0.65 117	0.69 99	0.58 95

FCDSN-DC	10.24 106	0.56 19	3.49 22	1.96 46	1.29 49	16.90 107	4.59 82	17.16 103	19.10 97	24.64 116	32.46 118	33.82 125	22.14 122	15.93 105	10.45 89	0.04 53	0.00 1	0.00 1	0.00 1	0.05 19	0.21 60
Dominik Hirner, Friedrich Fraundorfer: FCDSN-DC: An accurate but lightweight end-to-end trainable neural network for stereo estimation with depth completion.
ADCMid	10.24 106	3.13 109	20.70 115	2.21 58	2.39 77	11.23 87	6.19 90	14.17 83	11.19 61	23.20 113	22.25 91	17.89 91	19.54 114	18.51 112	26.21 126	0.45 105	0.42 114	1.10 126	1.29 125	1.56 119	1.18 112

SANet	10.64 108	1.86 94	10.91 89	1.76 33	0.71 25	14.62 100	9.23 109	19.18 110	37.14 127	19.22 100	27.96 105	25.86 114	19.11 113	13.02 88	10.63 90	0.08 65	0.06 68	0.03 74	0.02 56	0.62 96	0.81 104

FC-DCNN	10.72 109	0.52 14	4.27 33	1.88 38	1.63 56	17.18 108	5.29 86	18.20 105	19.69 101	28.50 120	34.51 122	34.03 126	21.48 120	15.89 104	11.15 96	0.03 45	0.01 36	0.02 66	0.01 52	0.07 26	0.09 35

AnyNet_C32	10.98 110	5.58 120	22.79 118	4.16 112	5.83 122	15.64 101	14.30 123	13.18 72	17.15 91	16.44 96	20.52 88	14.68 77	13.44 99	22.46 119	30.08 131	0.17 80	0.26 107	0.36 117	0.36 107	1.23 112	0.91 107

MeshStereo	11.52 111	1.52 78	4.55 37	1.89 39	1.46 51	19.87 113	5.11 84	20.66 121	15.91 84	32.67 125	34.51 122	39.34 131	21.15 118	18.74 113	12.10 98	0.11 69	0.06 68	0.01 54	0.00 1	0.45 90	0.22 62
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	12.94 112	3.66 116	25.81 122	3.61 103	2.26 74	22.77 116	4.55 81	27.10 128	20.06 102	23.90 114	28.99 108	30.53 121	16.98 106	19.92 116	20.26 112	1.24 121	1.07 123	0.98 125	1.33 126	1.80 120	2.04 122

ADCS	13.02 113	4.93 119	28.38 124	3.17 95	2.67 83	13.61 98	10.83 118	18.70 106	33.46 121	22.59 108	24.78 100	19.59 100	18.51 111	23.40 122	32.16 133	0.10 68	0.19 100	0.37 118	0.18 92	1.26 113	1.46 117

MFMNet_re	13.29 114	8.60 127	18.29 111	9.75 129	7.25 128	19.65 112	14.84 127	20.71 122	30.72 118	23.03 111	28.77 107	18.85 97	26.09 127	13.55 92	9.82 85	2.44 126	1.35 127	0.34 115	0.23 96	4.78 129	6.69 130

EDNetEfficient	13.82 115	6.19 122	54.79 131	2.83 81	3.60 98	4.86 37	8.57 105	8.61 18	32.90 120	40.77 131	30.59 112	18.33 94	21.87 121	11.38 77	25.36 124	0.15 76	0.23 104	0.06 86	1.03 123	2.54 123	1.79 118

LSM	14.01 116	5.95 121	33.49 126	6.78 127	43.61 135	10.22 80	9.98 114	15.16 92	22.93 107	23.07 112	32.34 117	18.52 95	12.67 94	15.45 103	11.10 95	0.16 79	0.51 120	0.09 93	0.32 104	1.08 109	16.85 135

SAMSARA	14.63 117	2.74 105	12.38 97	12.65 132	6.74 125	36.50 129	72.93 137	19.36 112	23.77 109	16.20 95	13.04 61	29.21 118	12.78 95	16.98 108	15.21 106	0.11 69	0.26 107	0.03 74	0.14 89	0.76 101	0.77 102

SPS-STEREO	15.04 118	6.23 123	13.21 103	11.34 131	11.65 133	23.30 117	7.15 102	24.16 125	15.65 82	31.78 124	29.19 110	31.62 122	21.32 119	24.62 123	19.50 111	7.59 133	4.19 134	3.22 131	1.48 127	6.99 132	6.54 129
K. Yamaguchi, D. McAllester, R. Urtasun: Efficient Joint Segmentation, Occlusion Labeling, Stereo and Flow Estimation. ECCV 2014
PVD	15.44 119	2.93 107	14.67 107	4.21 115	3.39 94	17.43 109	4.16 71	27.84 131	48.84 134	31.02 123	43.54 131	29.76 120	30.81 131	25.97 125	21.40 115	0.23 85	0.41 112	0.04 81	0.33 105	0.41 88	1.33 114

SGM+DAISY	15.62 120	7.26 126	19.28 113	8.94 128	10.11 132	26.25 122	10.49 116	19.36 112	14.65 78	30.64 122	33.59 120	33.00 123	22.32 123	24.96 124	16.42 108	7.90 134	6.25 135	4.51 132	3.37 131	5.86 130	7.20 131

NVStereoNet_ROB	16.04 121	6.75 124	12.90 101	6.37 126	7.42 129	12.89 93	9.74 112	22.78 124	25.12 110	30.32 121	46.19 133	34.37 127	25.38 125	21.48 118	21.38 114	5.94 132	3.10 132	6.07 133	10.09 135	4.01 127	8.54 133
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	16.12 122	10.81 131	59.36 132	4.42 116	2.49 81	30.06 125	15.15 129	17.51 104	16.51 87	17.88 97	37.69 126	24.04 110	17.54 107	29.60 128	33.29 134	0.28 93	0.38 110	0.43 120	0.42 111	2.57 124	1.98 121

MSC_U_SF_DS_RVC	16.41 123	6.93 125	21.83 116	5.94 125	2.81 85	38.71 130	14.59 124	24.55 126	34.87 124	33.66 126	34.35 121	29.24 119	24.20 124	22.59 120	17.95 109	2.52 127	2.81 130	1.17 128	1.51 129	5.89 131	2.16 123

ELAS_RVC	16.54 124	2.26 101	10.09 88	5.50 121	4.46 111	28.28 124	16.72 130	25.55 127	33.54 122	40.19 129	40.30 129	36.68 129	30.03 129	29.40 127	20.61 113	0.98 120	1.21 125	0.86 124	0.70 119	1.39 116	2.16 123
A. Geiger, M. Roser, R. Urtasun: Efficient large-scale stereo matching. ACCV 2010
ELAS	16.72 125	2.14 99	9.23 85	4.92 118	4.53 114	32.66 128	15.11 128	27.40 129	28.68 116	40.27 130	44.90 132	38.33 130	30.50 130	26.44 126	21.94 119	0.88 116	1.23 126	0.67 121	0.89 122	1.49 117	2.18 125
A. Geiger, M. Roser, R. Urtasun: Efficient large-scale stereo matching. ACCV 2010
LE_ROB	16.73 126	1.28 69	11.61 94	3.72 106	1.65 57	16.67 105	9.17 108	14.39 84	55.91 135	63.81 135	40.86 130	35.94 128	37.73 134	14.24 96	26.87 127	0.05 60	0.10 82	0.13 99	0.22 95	0.12 39	0.15 54

SGM-ForestM	16.99 127	1.08 54	5.74 53	2.12 53	0.75 27	31.63 127	12.21 120	27.80 130	32.25 119	37.88 127	39.99 128	52.96 134	35.20 133	33.60 130	24.47 122	0.26 89	0.39 111	0.31 114	0.39 109	0.26 71	0.53 93

DispFullNet	17.47 128	26.01 133	33.98 127	22.58 134	20.86 134	13.84 99	1.28 43	16.50 98	26.27 112	19.97 105	17.17 80	20.52 106	18.49 110	22.86 121	10.76 93	5.13 130	2.83 131	30.72 135	7.72 133	20.86 134	11.01 134

EDNetEfficientorigin	17.87 129	14.00 132	99.53 139	1.64 30	0.92 38	10.55 83	6.26 94	13.21 73	34.84 123	38.20 128	36.91 125	27.47 117	26.32 128	14.71 100	25.69 125	0.04 53	0.06 68	0.14 100	0.52 116	3.16 126	3.27 127

RTSA	18.87 130	9.32 129	86.48 134	4.95 119	6.10 123	42.08 132	14.70 125	15.49 94	41.06 131	22.65 109	32.32 115	13.77 68	19.54 114	37.98 131	28.96 128	0.41 101	0.23 104	0.00 1	0.02 56	0.91 105	0.50 89

RTS	18.87 130	9.32 129	86.48 134	4.95 119	6.10 123	42.08 132	14.70 125	15.49 94	41.06 131	22.65 109	32.32 115	13.77 68	19.54 114	37.98 131	28.96 128	0.41 101	0.23 104	0.00 1	0.02 56	0.91 105	0.50 89

MANE	19.47 132	1.27 66	5.07 44	4.69 117	5.55 120	30.49 126	9.94 113	34.01 133	37.27 128	44.13 132	51.57 136	52.51 133	40.41 135	33.58 129	24.81 123	0.89 117	0.86 122	1.11 127	9.72 134	0.38 83	1.06 110

BEATNet-Init1	23.31 133	9.03 128	41.67 128	4.17 113	2.53 82	45.68 134	19.47 132	33.43 132	38.45 130	47.59 134	49.10 134	59.31 135	41.80 136	38.35 133	29.21 130	0.47 106	0.50 119	0.81 123	0.66 118	2.10 122	1.86 119

MADNet+	27.07 134	33.84 134	90.97 136	20.14 133	7.47 130	48.43 135	47.10 134	35.43 134	36.46 125	20.11 106	30.05 111	25.29 112	35.08 132	45.50 135	50.28 135	2.13 125	2.00 129	1.19 129	0.76 120	4.71 128	4.43 128

PWCK	30.53 135	44.32 135	47.25 130	29.76 135	7.23 127	40.78 131	27.10 133	44.73 135	44.32 133	47.31 133	36.37 124	47.16 132	26.05 126	41.26 134	31.87 132	21.83 135	4.03 133	29.50 134	4.67 132	27.17 135	7.80 132

DPSimNet_ROB	53.45 136	64.73 136	44.39 129	53.97 136	45.39 136	53.66 136	54.83 135	55.15 136	57.87 136	64.16 136	50.83 135	63.40 136	53.34 137	46.45 136	65.81 136	63.13 136	26.54 136	57.94 136	51.11 136	45.52 136	50.69 136

MADNet++	82.84 137	82.38 138	73.57 133	87.72 137	82.97 137	93.14 137	69.15 136	86.42 137	82.50 137	93.46 137	86.70 137	86.28 137	80.92 138	88.34 137	88.84 137	86.83 137	84.17 137	72.64 137	68.92 137	80.47 137	81.42 137

MEDIAN_ROB	98.41 138	99.70 139	99.30 138	97.09 138	97.02 138	96.89 138	95.77 139	97.66 138	97.28 138	98.79 140	98.94 138	99.18 138	98.14 139	96.89 138	96.88 138	99.96 140	99.16 138	100.00 138	99.99 138	99.69 138	99.88 138

AVERAGE_ROB	99.62 139	99.95 140	98.81 137	100.00 143	100.00 139	98.08 139	95.47 138	100.00 141	100.00 139	100.00 141	100.00 139	100.00 141	100.00 140	100.00 141	99.99 139	100.00 142	100.00 139	100.00 138	100.00 139	100.00 141	100.00 142

DGTPSM_ROB	99.90 140	100.00 141	99.99 140	99.99 141	100.00 139	100.00 140	100.00 140	99.97 139	100.00 139	98.35 138	100.00 139	99.84 139	100.00 140	99.98 139	99.99 139	99.99 141	100.00 139	100.00 138	100.00 139	100.00 141	100.00 142

DPSMNet_ROB	99.91 141	100.00 141	99.99 140	99.99 141	100.00 139	100.00 140	100.00 140	99.98 140	100.00 139	98.35 138	100.00 139	99.84 139	100.00 140	99.98 139	99.99 139	100.00 142	100.00 139	100.00 138	100.00 139	100.00 141	100.00 142

DPSM_ROB	99.95 142	100.00 141	100.00 142	99.76 139	100.00 139	100.00 140	100.00 140	100.00 141	100.00 139	100.00 141	100.00 139	100.00 141	100.00 140	100.00 141	100.00 142	99.21 138	100.00 139	100.00 138	100.00 139	99.99 139	99.95 139

DPSM	99.95 142	100.00 141	100.00 142	99.76 139	100.00 139	100.00 140	100.00 140	100.00 141	100.00 139	100.00 141	100.00 139	100.00 141	100.00 140	100.00 141	100.00 142	99.21 138	100.00 139	100.00 138	100.00 139	99.99 139	99.95 139

LSM0	100.00 144	100.00 141	100.00 142	100.00 143	100.00 139	100.00 140	100.00 140	100.00 141	100.00 139	100.00 141	100.00 139	100.00 141	100.00 140	100.00 141	100.00 142	100.00 142	100.00 139	100.00 138	100.00 139	100.00 141	99.99 141

ASD4		81.57 137

MSMDNet													1.26 7

Low-res two-view benchmark