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

DPM-Stereo	1.97 1	0.64 16	2.95 8	0.17 1	0.10 1	4.83 25	0.13 2	8.60 9	4.06 4	6.42 16	4.92 4	0.44 1	0.72 1	3.57 3	1.80 5	0.00 1	0.01 25	0.00 1	0.00 1	0.05 15	0.04 15

PMTNet	1.99 2	0.32 1	2.21 3	0.39 2	0.23 6	5.08 27	0.49 11	5.84 1	8.22 27	3.07 1	3.29 1	0.73 2	0.75 2	8.18 28	0.94 3	0.00 1	0.00 1	0.00 1	0.00 1	0.03 10	0.00 1

R-Stereo	2.44 3	0.32 1	1.93 1	0.94 4	0.16 4	3.67 8	0.61 16	6.37 3	3.08 1	9.14 38	17.44 66	1.80 3	0.77 3	1.76 1	0.70 1	0.00 1	0.01 25	0.00 1	0.00 1	0.01 1	0.03 9

R-Stereo Train	2.44 3	0.32 1	1.93 1	0.94 4	0.16 4	3.67 8	0.61 16	6.37 3	3.08 1	9.14 38	17.44 66	1.80 3	0.77 3	1.76 1	0.70 1	0.00 1	0.01 25	0.00 1	0.00 1	0.01 1	0.03 9

DN-CSS_ROB	2.69 5	1.40 55	5.34 33	2.31 51	0.75 22	3.14 6	0.06 1	6.11 2	3.87 3	5.34 11	12.18 40	2.34 5	1.22 5	7.84 18	1.48 4	0.03 33	0.00 1	0.00 1	0.00 1	0.35 62	0.03 9

HITNet	2.79 6	0.77 17	4.02 19	2.03 40	0.11 3	5.58 31	0.59 14	9.24 12	5.15 8	6.42 16	7.26 11	3.66 6	2.92 16	4.07 4	3.87 29	0.00 1	0.00 1	0.00 1	0.00 1	0.06 19	0.02 3
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
ccs	3.04 7	0.39 7	3.08 10	1.78 27	0.52 16	2.04 1	0.50 12	13.09 53	13.71 60	3.54 4	5.36 6	5.50 12	2.45 11	4.81 6	2.88 12	0.09 48	0.08 60	0.12 76	0.10 70	0.20 43	0.50 73

AdaStereo	3.09 8	0.58 12	3.04 9	2.84 64	0.48 15	4.08 15	1.29 32	12.16 45	7.77 23	6.03 12	9.62 24	5.79 14	1.53 7	4.56 5	1.93 7	0.00 1	0.00 1	0.00 1	0.00 1	0.02 4	0.02 3
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.
BEATNet_4x	3.24 9	1.27 49	5.89 41	1.56 18	0.10 1	5.26 28	1.07 27	10.08 19	5.50 9	6.89 21	7.73 13	4.53 9	4.13 27	5.05 7	5.27 35	0.04 38	0.05 48	0.00 1	0.00 1	0.23 53	0.23 49

DMCA	3.29 10	1.05 33	4.18 22	1.60 21	2.87 71	2.11 2	0.60 15	7.95 7	4.65 7	8.62 33	8.59 19	9.24 31	4.68 34	6.25 8	3.03 14	0.04 38	0.09 64	0.06 70	0.03 50	0.18 39	0.07 18

NOSS_ROB	3.30 11	0.46 8	2.62 4	2.08 41	1.01 34	5.60 32	0.74 23	10.37 26	11.48 49	5.15 9	8.43 18	5.67 13	1.73 8	7.97 20	2.34 9	0.02 23	0.06 54	0.00 1	0.00 1	0.07 20	0.14 40

CFNet_RVC	3.31 12	0.94 28	2.69 5	1.50 16	2.38 61	2.81 4	0.68 20	8.35 8	7.43 19	4.45 6	9.94 25	10.20 37	4.60 32	6.49 9	3.41 22	0.00 1	0.00 1	0.03 61	0.00 1	0.22 49	0.03 9

MLCV	3.44 13	0.88 21	5.60 36	1.39 12	0.25 7	4.36 18	0.33 6	7.25 5	7.28 16	9.17 40	12.24 42	5.09 10	2.47 12	9.15 40	3.23 19	0.00 1	0.00 1	0.00 1	0.00 1	0.10 23	0.02 3

DeepPruner_ROB	3.52 14	1.14 43	4.06 20	1.12 7	1.65 47	3.65 7	0.83 25	13.96 61	4.47 5	7.80 25	10.84 30	7.05 21	2.16 10	8.14 26	3.08 17	0.07 46	0.03 40	0.00 1	0.01 38	0.32 58	0.06 17

STTStereo	3.60 15	0.93 27	6.34 49	2.71 62	2.23 58	3.68 10	0.63 19	9.42 13	6.73 12	9.87 47	6.97 9	8.84 30	3.65 20	6.85 11	3.04 15	0.00 1	0.02 35	0.01 43	0.00 1	0.02 4	0.02 3

ccs_rob	3.63 16	1.12 42	4.42 24	2.52 55	0.91 30	5.50 30	0.21 4	10.11 22	9.11 33	6.55 19	11.28 34	8.32 28	2.55 13	7.66 15	2.01 8	0.00 1	0.00 1	0.00 1	0.00 1	0.20 43	0.08 21

iResNet	3.68 17	0.91 24	7.94 65	2.97 70	0.34 9	4.44 22	0.48 10	7.70 6	9.74 37	7.72 24	12.74 45	4.03 7	2.87 15	8.05 22	3.37 21	0.02 23	0.01 25	0.00 1	0.00 1	0.10 23	0.09 23

DMCA-RVC	3.68 17	1.58 64	6.33 47	1.79 28	2.33 60	4.04 14	0.68 20	9.07 10	4.57 6	8.48 32	9.34 23	10.91 41	3.45 19	6.67 10	3.78 27	0.02 23	0.11 67	0.01 43	0.04 59	0.18 39	0.12 34

CFNet	3.72 19	1.10 39	5.03 29	2.49 54	1.59 44	4.90 26	0.22 5	11.38 35	9.88 39	4.80 7	11.25 33	6.44 17	3.68 21	8.33 29	3.00 13	0.00 1	0.00 1	0.00 1	0.00 1	0.22 49	0.07 18

FADNet-RVC-Resample	3.79 20	1.62 67	12.06 78	1.43 14	0.66 18	5.94 34	2.41 40	10.18 24	8.58 31	6.28 14	4.22 3	5.33 11	4.80 38	7.71 16	3.19 18	0.17 60	0.21 81	0.17 82	0.12 72	0.41 70	0.29 61

NLCA_NET_v2_RVC	3.84 21	1.06 34	5.23 31	2.72 63	3.27 74	4.36 18	0.61 16	10.71 31	7.56 20	8.75 34	7.89 14	9.86 36	3.90 24	7.15 13	3.44 23	0.14 55	0.02 35	0.02 55	0.03 50	0.04 13	0.03 9
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 21	1.07 35	5.23 31	2.65 59	2.96 72	4.22 16	0.69 22	10.43 27	7.72 21	8.78 35	8.29 17	9.61 34	4.02 26	7.16 14	3.65 26	0.13 54	0.03 40	0.02 55	0.03 50	0.05 15	0.03 9

FADNet_RVC	3.91 23	1.67 70	12.95 85	0.96 6	0.75 22	5.71 33	0.54 13	10.83 33	6.60 11	3.46 2	8.09 15	4.10 8	3.40 18	9.43 43	6.33 39	0.36 76	0.44 93	0.17 82	0.46 96	0.91 86	0.95 90

FADNet-RVC	3.98 24	1.84 76	12.48 81	1.69 25	0.44 13	4.33 17	1.31 33	11.84 39	7.15 14	3.53 3	3.50 2	10.63 40	4.43 31	9.12 39	6.25 38	0.03 33	0.10 65	0.00 1	0.03 50	0.60 76	0.25 55

HSM	4.00 25	0.79 18	3.16 12	1.59 20	2.17 56	6.77 40	1.11 28	12.28 46	6.35 10	6.75 20	8.11 16	13.90 56	5.37 43	8.85 37	2.71 11	0.00 1	0.00 1	0.00 1	0.00 1	0.02 4	0.02 3

TDLM	4.11 26	1.11 41	3.54 14	1.62 22	1.04 35	3.91 12	7.41 84	10.60 30	10.67 43	6.38 15	12.59 44	5.95 15	4.77 36	8.79 36	3.04 15	0.58 88	0.00 1	0.01 43	0.00 1	0.19 42	0.12 34

CBMV_ROB	4.14 27	0.52 9	3.14 11	1.30 10	0.77 25	6.92 41	1.97 39	10.11 22	9.58 35	8.92 37	14.20 53	7.12 22	5.90 46	8.65 33	3.50 25	0.01 18	0.05 48	0.00 1	0.00 1	0.04 13	0.09 23

CVANet_RVC	4.16 28	1.16 44	3.60 15	1.94 38	1.46 42	3.92 13	4.68 66	10.89 34	8.34 29	7.58 23	10.84 30	10.27 38	6.62 50	8.56 32	2.69 10	0.39 78	0.00 1	0.00 1	0.01 38	0.21 48	0.09 23

HSM-Net_RVC	4.20 29	0.32 1	2.76 6	0.63 3	0.69 20	6.95 42	1.69 37	11.96 40	8.36 30	8.83 36	12.17 39	15.18 64	4.21 29	6.91 12	3.30 20	0.02 23	0.02 35	0.00 1	0.00 1	0.01 1	0.01 2
Gengshan Yang, Joshua Manela, Michael Happold, and Deva Ramanan: Hierarchical Deep Stereo Matching on High-resolution Images. CVPR 2019
iResNet_ROB	4.23 30	1.02 31	4.90 28	2.18 44	0.93 32	2.92 5	0.37 8	15.10 72	16.91 74	7.89 27	10.51 28	7.03 19	3.07 17	8.16 27	3.46 24	0.01 18	0.00 1	0.00 1	0.00 1	0.10 23	0.02 3

FADNet	4.23 30	1.65 69	11.75 77	1.64 24	0.80 27	4.80 24	0.77 24	13.76 60	11.65 51	3.97 5	5.24 5	9.62 35	5.14 40	8.40 30	3.78 27	0.21 64	0.04 44	0.07 71	0.05 62	1.14 91	0.10 30

iResNetv2_ROB	4.28 32	1.43 56	7.17 60	2.91 65	1.26 39	4.36 18	1.62 35	13.64 59	10.25 42	9.83 46	11.41 35	7.68 24	4.00 25	7.75 17	1.85 6	0.00 1	0.00 1	0.00 1	0.00 1	0.37 64	0.09 23

StereoDRNet-Refined	4.46 33	0.62 15	3.80 18	1.92 35	0.40 11	9.35 52	0.15 3	10.02 17	8.83 32	12.69 64	11.62 37	9.34 32	3.87 23	8.06 23	8.02 52	0.00 1	0.00 1	0.01 43	0.05 62	0.20 43	0.26 58
Rohan Chabra, Julian Straub, Chris Sweeney, Richard Newcombe, Henry Fuchs: StereoDRNet. CVPR
DLCB_ROB	4.51 34	0.91 24	3.78 17	2.19 45	1.07 36	6.28 35	3.09 44	9.78 16	7.72 21	10.65 51	12.97 46	13.91 57	3.71 22	8.72 34	5.30 36	0.00 1	0.00 1	0.00 1	0.00 1	0.03 10	0.10 30

NVstereo2D	4.51 34	0.82 19	6.86 58	3.28 75	3.38 78	8.16 47	3.13 45	10.51 28	15.15 65	4.90 8	6.89 8	7.87 25	4.78 37	9.88 46	3.91 30	0.01 18	0.00 1	0.00 1	0.06 64	0.02 4	0.58 78

RASNet	4.52 36	0.61 14	4.42 24	3.42 79	4.68 96	4.58 23	0.99 26	9.54 15	8.01 24	5.28 10	11.42 36	10.34 39	8.88 63	9.28 41	8.68 61	0.15 57	0.00 1	0.00 1	0.00 1	0.03 10	0.04 15

SGM-Forest	4.96 37	0.32 1	2.84 7	1.21 8	0.64 17	10.23 62	6.64 79	11.55 36	10.98 44	10.94 54	13.59 49	11.65 47	4.30 30	8.94 38	4.63 33	0.11 51	0.04 44	0.00 1	0.00 1	0.05 15	0.46 70
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 38	1.47 58	7.42 62	2.40 52	2.14 55	8.73 49	3.64 54	12.42 47	13.11 56	7.03 22	7.57 12	7.88 26	6.52 49	10.16 48	7.82 50	0.02 23	0.03 40	0.00 1	0.00 1	0.11 27	1.07 93
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 39	1.74 71	6.38 50	1.96 39	1.29 41	2.26 3	1.69 37	10.07 18	18.53 77	7.88 26	18.15 68	8.49 29	2.70 14	10.59 52	7.04 44	0.96 98	0.15 76	0.02 55	0.00 1	0.13 31	0.12 34

PSMNet_ROB	5.02 40	1.63 68	6.03 43	1.90 34	1.83 52	9.57 56	6.35 76	15.58 77	7.23 15	6.15 13	10.48 27	12.22 49	4.16 28	8.02 21	8.71 62	0.02 23	0.01 25	0.01 43	0.10 70	0.20 43	0.12 34

CBMV	5.35 41	0.91 24	3.67 16	1.62 22	0.44 13	10.09 60	7.19 83	12.49 48	12.33 55	12.22 60	14.69 55	10.93 42	6.48 48	8.51 31	4.96 34	0.02 23	0.15 76	0.00 1	0.00 1	0.17 38	0.17 44
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 42	1.75 72	6.80 57	3.12 72	4.45 91	10.61 64	4.35 61	18.80 87	9.73 36	12.22 60	6.87 7	11.44 45	4.65 33	8.09 25	8.26 57	0.02 23	0.11 67	0.00 1	0.03 50	0.20 43	0.28 60

ETE_ROB	5.80 43	1.77 73	6.33 47	1.44 15	0.78 26	6.43 39	6.90 80	12.53 49	8.08 25	12.93 68	14.89 56	21.13 88	5.87 45	9.83 45	6.57 42	0.04 38	0.01 25	0.00 1	0.02 42	0.08 22	0.33 62

DRN-Test	5.87 44	0.98 29	5.89 41	2.69 61	3.65 83	12.37 71	3.35 48	20.07 98	10.20 41	11.93 59	12.31 43	11.06 44	5.31 42	7.89 19	9.05 64	0.04 38	0.05 48	0.04 66	0.04 59	0.18 39	0.25 55

NCCL2	5.88 45	1.59 65	5.44 34	1.87 31	0.92 31	9.55 55	11.55 98	12.11 42	9.94 40	9.67 45	8.85 21	22.28 90	7.41 54	8.78 35	7.17 45	0.01 18	0.00 1	0.03 61	0.00 1	0.13 31	0.23 49

NaN_ROB	6.00 46	1.24 47	6.29 46	1.34 11	1.68 49	9.60 57	10.31 94	15.09 70	15.79 68	12.62 63	8.95 22	11.67 48	5.83 44	11.78 60	6.41 41	0.05 43	0.13 73	0.08 72	0.20 78	0.22 49	0.79 86

DANet	6.02 47	1.23 46	8.45 67	3.86 88	3.94 85	7.64 46	1.34 34	9.51 14	7.00 13	13.39 70	15.53 59	15.99 67	7.02 53	12.14 61	12.37 80	0.19 62	0.12 72	0.02 55	0.03 50	0.13 31	0.56 77

XPNet_ROB	6.03 48	1.22 45	5.61 37	2.56 58	0.90 29	6.32 36	7.07 81	12.92 52	8.30 28	14.76 75	15.13 58	19.84 83	6.66 52	10.36 49	8.58 60	0.02 23	0.04 44	0.00 1	0.03 50	0.11 27	0.24 52

Anonymous Stereo	6.16 49	3.15 93	23.75 102	2.97 70	2.48 65	4.39 21	13.30 100	9.21 11	9.86 38	9.56 44	8.76 20	6.79 18	1.99 9	13.50 72	13.04 83	0.01 18	0.05 48	0.00 1	0.06 64	0.22 49	0.19 46

GANet	6.22 50	1.07 35	4.07 21	2.27 48	0.89 28	9.19 51	9.52 89	12.02 41	8.13 26	10.72 52	29.09 92	13.86 55	7.52 56	11.00 56	4.39 31	0.36 76	0.00 1	0.02 55	0.02 42	0.12 29	0.08 21

DISCO	6.28 51	0.57 11	5.78 39	3.43 80	1.17 37	11.22 66	3.39 49	12.14 44	16.16 70	6.52 18	11.22 32	16.96 70	6.32 47	19.51 93	10.74 74	0.00 1	0.00 1	0.00 1	0.00 1	0.35 62	0.11 32

RYNet	6.34 52	0.89 23	5.88 40	1.41 13	4.48 93	15.97 82	4.18 58	13.41 55	16.49 71	10.81 53	7.00 10	14.33 59	8.72 61	9.43 43	13.71 84	0.00 1	0.01 25	0.00 1	0.00 1	0.02 4	0.07 18

GANetREF_RVC	6.56 53	2.89 88	7.58 64	3.41 78	0.40 11	12.96 74	9.58 90	15.09 70	17.25 76	10.33 49	10.62 29	12.27 50	8.16 58	12.21 62	4.53 32	0.41 80	0.00 1	0.00 1	0.02 42	3.12 105	0.39 65
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 54	1.80 75	6.25 45	1.26 9	0.94 33	10.08 59	9.02 86	16.00 78	11.51 50	12.74 65	13.02 47	24.77 92	5.25 41	10.56 51	8.02 52	0.04 38	0.05 48	0.00 1	0.02 42	0.10 23	0.25 55

DeepPrunerF	6.75 55	2.69 86	23.31 101	3.68 83	7.16 105	3.78 11	4.29 59	13.42 56	20.13 85	8.13 28	10.46 26	7.18 23	8.06 57	11.10 57	9.44 66	0.24 66	0.15 76	0.29 90	0.42 92	0.66 79	0.45 68

edge stereo	6.76 56	1.01 30	6.76 56	2.20 46	2.45 64	6.41 38	2.45 41	14.84 68	11.98 54	15.29 76	18.31 69	22.02 89	12.56 77	10.82 53	7.49 46	0.03 33	0.06 54	0.11 75	0.03 50	0.30 55	0.14 40

Abc-Net	6.77 57	1.49 59	6.48 51	2.92 67	4.40 87	7.43 43	3.61 52	19.52 94	13.29 57	8.39 30	16.91 62	15.96 65	12.13 75	12.85 67	7.70 48	1.47 102	0.11 67	0.01 43	0.42 92	0.14 35	0.24 52

NCC-stereo	6.77 57	1.49 59	6.48 51	2.92 67	4.40 87	7.43 43	3.61 52	19.52 94	13.29 57	8.39 30	16.91 62	15.96 65	12.13 75	12.85 67	7.70 48	1.47 102	0.11 67	0.01 43	0.42 92	0.14 35	0.24 52

RP	6.84 59	1.29 53	5.53 35	3.92 89	5.18 98	6.32 36	3.53 50	11.73 38	15.31 66	9.54 43	22.38 76	18.25 77	14.47 84	10.11 47	7.49 46	0.91 97	0.01 25	0.12 76	0.15 75	0.33 59	0.19 46

RGC	6.88 60	2.23 82	6.13 44	4.05 90	4.73 97	8.94 50	2.78 43	15.19 74	11.74 52	11.13 55	19.34 71	17.86 74	10.42 70	13.02 69	8.03 54	0.73 91	0.01 25	0.24 89	0.41 91	0.31 57	0.38 64

Nwc_Net	6.97 61	1.25 48	6.63 54	3.82 87	3.37 77	10.83 65	1.67 36	19.56 96	11.35 47	8.36 29	23.62 78	17.19 72	11.44 74	11.21 58	8.08 56	0.80 93	0.00 1	0.00 1	0.02 42	0.13 31	0.09 23

STTRV1_RVC	7.02 62	1.10 39	12.88 83	3.32 76	6.92 104	11.90 70	4.00 56	15.07 69	11.94 53	9.51 41	14.57 54	11.63 46	8.73 62	12.65 66	8.06 55	3.32 108	2.75 108	0.41 98	0.12 72	1.38 96	0.11 32

ADCRef	7.27 63	1.38 54	16.37 91	2.52 55	3.30 76	11.63 68	3.16 46	10.80 32	9.35 34	13.03 69	25.27 86	8.17 27	8.92 64	8.06 23	21.81 99	0.15 57	0.08 60	0.16 81	0.34 88	0.38 65	0.58 78

CSAN	7.62 64	1.60 66	6.56 53	1.83 29	0.66 18	12.40 72	10.52 96	14.45 65	21.32 87	14.19 72	15.98 61	17.84 73	13.02 81	12.32 63	8.38 58	0.09 48	0.07 58	0.03 61	0.04 59	0.33 59	0.67 84

stereogan	7.69 65	0.88 21	7.08 59	3.49 81	3.93 84	18.98 89	3.23 47	16.52 80	19.58 82	9.93 48	18.92 70	20.50 86	9.04 65	14.07 76	6.14 37	0.26 68	0.04 44	0.21 87	0.03 50	0.63 78	0.33 62

pmcnn	7.72 66	1.27 49	9.42 70	2.91 65	3.14 73	9.44 53	6.23 73	12.56 50	16.51 72	14.53 73	24.08 80	27.44 98	8.49 59	9.32 42	8.44 59	0.06 45	0.08 60	0.00 1	0.00 1	0.30 55	0.15 42

AF-Net	7.78 67	1.44 57	6.68 55	3.37 77	4.50 94	8.61 48	2.69 42	17.07 83	20.17 86	9.52 42	24.02 79	20.31 85	14.59 85	11.58 59	9.84 71	0.61 89	0.00 1	0.12 76	0.00 1	0.38 65	0.12 34

PASM	7.90 68	4.22 98	21.97 99	3.25 74	3.29 75	5.39 29	6.57 78	10.57 29	19.09 79	12.77 66	13.92 51	18.11 76	9.51 67	13.79 75	10.77 76	0.19 62	0.45 94	0.29 90	1.08 103	1.49 98	1.19 95

PWCDC_ROB	7.92 69	3.17 95	7.48 63	5.73 101	4.40 87	10.45 63	0.35 7	14.52 66	28.19 95	10.36 50	31.27 95	7.04 20	9.14 66	13.22 71	8.78 63	2.74 107	0.02 35	0.00 1	0.00 1	1.31 95	0.17 44

ADCP+	8.09 70	1.79 74	14.50 89	1.54 17	4.28 86	16.57 84	5.20 68	12.80 51	11.20 46	12.83 67	17.07 64	11.02 43	10.80 72	17.59 89	23.18 102	0.03 33	0.05 48	0.01 43	0.18 76	0.39 69	0.81 87

SuperB	8.10 71	3.15 93	24.67 103	2.65 59	1.23 38	9.88 58	4.29 59	10.18 24	30.07 98	11.53 57	12.18 40	6.12 16	6.65 51	10.50 50	14.47 86	0.14 55	0.11 67	0.35 94	0.25 82	13.06 113	0.48 71

PWC_ROB	8.24 72	3.13 91	12.74 82	2.43 53	4.43 90	7.51 45	1.22 29	16.63 81	19.24 80	16.08 78	28.29 89	13.99 58	10.16 69	13.63 74	14.06 85	0.42 83	0.00 1	0.05 68	0.00 1	0.59 75	0.27 59

MDST_ROB	8.37 73	0.32 1	9.03 68	4.18 93	2.42 63	26.86 102	6.14 71	19.36 91	13.52 59	27.09 101	22.75 77	9.47 33	4.74 35	15.06 81	6.34 40	0.02 23	0.02 35	0.00 1	0.00 1	0.02 4	0.13 39

STTStereo_v2	8.41 74	1.54 62	10.97 73	5.73 101	3.60 81	26.19 99	4.41 62	10.10 20	7.42 17	19.71 86	24.99 84	14.38 60	15.83 86	10.99 54	9.53 67	0.50 86	0.46 95	0.19 85	0.25 82	0.80 83	0.66 82

G-Net	8.41 74	1.54 62	10.97 73	5.73 101	3.60 81	26.19 99	4.41 62	10.10 20	7.42 17	19.71 86	24.99 84	14.38 60	15.83 86	10.99 54	9.53 67	0.50 86	0.46 95	0.19 85	0.25 82	0.80 83	0.66 82

XQC	8.43 76	3.58 96	16.40 92	2.92 67	2.17 56	13.22 76	3.60 51	14.64 67	25.86 92	11.87 58	12.04 38	15.06 63	10.67 71	15.24 82	19.41 91	0.39 78	0.08 60	0.05 68	0.07 66	0.84 85	0.45 68

FBW_ROB	8.50 77	1.03 32	7.98 66	1.93 37	1.28 40	13.10 75	6.23 73	22.50 102	18.98 78	18.82 83	14.91 57	19.06 80	10.04 68	18.41 90	9.83 70	0.62 90	0.22 82	1.82 109	0.82 101	0.99 89	1.36 97

RTSC	9.15 78	3.00 90	13.57 87	3.72 85	1.76 51	11.82 69	0.46 9	16.95 82	36.83 105	15.80 77	15.53 59	12.91 52	7.46 55	20.01 96	21.76 98	0.31 73	0.13 73	0.01 43	0.08 67	0.57 73	0.41 67

WCMA_ROB	9.21 79	0.87 20	7.37 61	2.54 57	2.13 54	13.59 77	5.80 70	11.64 37	14.01 61	24.43 99	32.99 99	27.09 97	18.02 90	12.51 65	9.85 72	0.81 94	0.07 58	0.01 43	0.01 38	0.16 37	0.23 49

MSMD_ROB	9.28 80	1.09 38	4.65 27	1.58 19	0.39 10	16.52 83	4.41 62	13.60 57	14.87 64	22.34 91	39.89 106	25.67 94	20.71 99	12.42 64	6.98 43	0.34 75	0.03 40	0.00 1	0.00 1	0.05 15	0.09 23

ADCPNet	9.54 81	2.39 84	31.46 106	2.09 42	1.60 45	16.71 86	6.39 77	12.11 42	11.45 48	13.53 71	21.45 74	19.41 81	10.94 73	14.38 78	21.54 97	0.27 71	1.16 102	0.39 97	1.49 107	0.58 74	1.45 98

SHD	9.61 82	2.60 85	12.46 80	3.69 84	3.54 80	9.47 54	1.25 30	20.16 99	37.84 108	18.19 82	21.24 73	16.96 70	12.83 80	14.47 80	16.05 88	0.32 74	0.13 73	0.01 43	0.08 67	0.38 65	0.48 71

PDISCO_ROB	9.62 83	1.99 79	11.51 75	9.88 109	9.61 110	21.48 93	3.83 55	19.33 90	28.49 96	11.27 56	14.17 52	19.92 84	5.02 39	16.35 86	9.18 65	5.28 110	0.41 90	0.14 80	0.09 69	2.05 102	2.36 106

MFN_U_SF_DS_RVC	9.78 84	4.27 99	14.47 88	2.29 49	2.85 70	23.40 97	13.62 101	13.60 57	19.54 81	19.42 85	24.27 81	16.74 69	8.59 60	17.05 88	7.98 51	1.25 101	1.68 106	0.17 82	2.63 109	0.72 81	1.04 91

SGM_RVC	10.08 85	0.60 13	3.42 13	2.30 50	0.32 8	19.41 90	6.33 75	18.95 88	14.64 62	25.14 100	24.32 82	33.34 105	18.79 94	19.86 94	12.55 82	0.25 67	0.26 85	0.22 88	0.24 81	0.34 61	0.40 66
Heiko Hirschmueller: Stereo processing by semiglobal matching and mutual information. TPAMI 2008, Volume 30(2), pp. 328-341
DPSNet	10.14 86	1.88 78	16.82 93	1.85 30	1.73 50	24.84 98	17.20 110	19.92 97	27.41 94	12.23 62	13.62 50	16.52 68	18.35 91	14.42 79	12.50 81	0.78 92	0.54 99	0.08 72	0.25 82	1.18 92	0.59 81

ADCL	10.16 87	2.11 80	19.36 96	1.92 35	1.88 53	22.23 94	8.91 85	14.04 62	23.56 89	14.62 74	26.19 87	12.75 51	13.59 83	16.06 85	22.95 101	0.26 68	0.18 79	0.75 101	0.65 97	0.69 80	0.58 78

ADCMid	10.24 88	3.13 91	20.70 97	2.21 47	2.39 62	11.23 67	6.19 72	14.17 63	11.19 45	23.20 97	22.25 75	17.89 75	19.54 96	18.51 91	26.21 105	0.45 84	0.42 92	1.10 105	1.29 104	1.56 100	1.18 94

SANet	10.64 89	1.86 77	10.91 72	1.76 26	0.71 21	14.62 80	9.23 88	19.18 89	37.14 106	19.22 84	27.96 88	25.86 95	19.11 95	13.02 69	10.63 73	0.08 47	0.06 54	0.03 61	0.02 42	0.62 77	0.81 87

FC-DCNN	10.72 90	0.52 9	4.27 23	1.88 32	1.63 46	17.18 87	5.29 69	18.20 85	19.69 83	28.50 102	34.51 102	34.03 106	21.48 102	15.89 84	11.15 78	0.03 33	0.01 25	0.02 55	0.01 38	0.07 20	0.09 23

AnyNet_C32	10.98 91	5.58 101	22.79 100	4.16 91	5.83 100	15.64 81	14.30 102	13.18 54	17.15 75	16.44 80	20.52 72	14.68 62	13.44 82	22.46 98	30.08 110	0.17 60	0.26 85	0.36 95	0.36 89	1.23 93	0.91 89

MeshStereo	11.52 92	1.52 61	4.55 26	1.89 33	1.46 42	19.87 92	5.11 67	20.66 100	15.91 69	32.67 107	34.51 102	39.34 111	21.15 100	18.74 92	12.10 79	0.11 51	0.06 54	0.01 43	0.00 1	0.45 72	0.22 48
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 93	3.66 97	25.81 104	3.61 82	2.26 59	22.77 95	4.55 65	27.10 107	20.06 84	23.90 98	28.99 91	30.53 102	16.98 88	19.92 95	20.26 93	1.24 100	1.07 101	0.98 104	1.33 105	1.80 101	2.04 102

ADCS	13.02 94	4.93 100	28.38 105	3.17 73	2.67 68	13.61 78	10.83 97	18.70 86	33.46 101	22.59 92	24.78 83	19.59 82	18.51 93	23.40 101	32.16 112	0.10 50	0.19 80	0.37 96	0.18 76	1.26 94	1.46 99

MFMNet_re	13.29 95	8.60 107	18.29 94	9.75 108	7.25 107	19.65 91	14.84 106	20.71 101	30.72 99	23.03 95	28.77 90	18.85 79	26.09 107	13.55 73	9.82 69	2.44 105	1.35 105	0.34 93	0.23 80	4.78 108	6.69 110

LSM	14.01 96	5.95 102	33.49 107	6.78 106	43.61 115	10.22 61	9.98 93	15.16 73	22.93 88	23.07 96	32.34 98	18.52 78	12.67 78	15.45 83	11.10 77	0.16 59	0.51 98	0.09 74	0.32 86	1.08 90	16.85 115

SAMSARA	14.63 97	2.74 87	12.38 79	12.65 112	6.74 103	36.50 108	72.93 116	19.36 91	23.77 90	16.20 79	13.04 48	29.21 99	12.78 79	16.98 87	15.21 87	0.11 51	0.26 85	0.03 61	0.14 74	0.76 82	0.77 85

SPS-STEREO	15.04 98	6.23 103	13.21 86	11.34 111	11.65 113	23.30 96	7.15 82	24.16 104	15.65 67	31.78 106	29.19 93	31.62 103	21.32 101	24.62 102	19.50 92	7.59 112	4.19 113	3.22 110	1.48 106	6.99 112	6.54 109
K. Yamaguchi, D. McAllester, R. Urtasun: Efficient Joint Segmentation, Occlusion Labeling, Stereo and Flow Estimation. ECCV 2014
PVD	15.44 99	2.93 89	14.67 90	4.21 94	3.39 79	17.43 88	4.16 57	27.84 110	48.84 113	31.02 105	43.54 110	29.76 101	30.81 110	25.97 104	21.40 96	0.23 65	0.41 90	0.04 66	0.33 87	0.41 70	1.33 96

SGM+DAISY	15.62 100	7.26 106	19.28 95	8.94 107	10.11 112	26.25 101	10.49 95	19.36 91	14.65 63	30.64 104	33.59 100	33.00 104	22.32 103	24.96 103	16.42 89	7.90 113	6.25 114	4.51 111	3.37 110	5.86 110	7.20 111

NVStereoNet_ROB	16.04 101	6.75 104	12.90 84	6.37 105	7.42 108	12.89 73	9.74 91	22.78 103	25.12 91	30.32 103	46.19 112	34.37 107	25.38 105	21.48 97	21.38 95	5.94 111	3.10 111	6.07 112	10.09 114	4.01 106	8.54 113
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	16.12 102	10.81 111	59.36 112	4.42 95	2.49 66	30.06 104	15.15 108	17.51 84	16.51 72	17.88 81	37.69 105	24.04 91	17.54 89	29.60 107	33.29 113	0.28 72	0.38 88	0.43 99	0.42 92	2.57 104	1.98 101

MSC_U_SF_DS_RVC	16.41 103	6.93 105	21.83 98	5.94 104	2.81 69	38.71 109	14.59 103	24.55 105	34.87 103	33.66 108	34.35 101	29.24 100	24.20 104	22.59 99	17.95 90	2.52 106	2.81 109	1.17 107	1.51 108	5.89 111	2.16 103

ELAS_RVC	16.54 104	2.26 83	10.09 71	5.50 100	4.46 92	28.28 103	16.72 109	25.55 106	33.54 102	40.19 110	40.30 108	36.68 109	30.03 108	29.40 106	20.61 94	0.98 99	1.21 103	0.86 103	0.70 99	1.39 97	2.16 103
A. Geiger, M. Roser, R. Urtasun: Efficient large-scale stereo matching. ACCV 2010
ELAS	16.72 105	2.14 81	9.23 69	4.92 97	4.53 95	32.66 107	15.11 107	27.40 108	28.68 97	40.27 111	44.90 111	38.33 110	30.50 109	26.44 105	21.94 100	0.88 95	1.23 104	0.67 100	0.89 102	1.49 98	2.18 105
A. Geiger, M. Roser, R. Urtasun: Efficient large-scale stereo matching. ACCV 2010
LE_ROB	16.73 106	1.28 52	11.61 76	3.72 85	1.65 47	16.67 85	9.17 87	14.39 64	55.91 115	63.81 115	40.86 109	35.94 108	37.73 113	14.24 77	26.87 106	0.05 43	0.10 65	0.13 79	0.22 79	0.12 29	0.15 42

SGM-ForestM	16.99 107	1.08 37	5.74 38	2.12 43	0.75 22	31.63 106	12.21 99	27.80 109	32.25 100	37.88 109	39.99 107	52.96 114	35.20 112	33.60 109	24.47 103	0.26 68	0.39 89	0.31 92	0.39 90	0.26 54	0.53 76

DispFullNet	17.47 108	26.01 113	33.98 108	22.58 114	20.86 114	13.84 79	1.28 31	16.50 79	26.27 93	19.97 88	17.17 65	20.52 87	18.49 92	22.86 100	10.76 75	5.13 109	2.83 110	30.72 114	7.72 112	20.86 114	11.01 114

RTSA	18.87 109	9.32 109	86.48 114	4.95 98	6.10 101	42.08 111	14.70 104	15.49 75	41.06 110	22.65 93	32.32 96	13.77 53	19.54 96	37.98 110	28.96 107	0.41 80	0.23 83	0.00 1	0.02 42	0.91 86	0.50 73

RTS	18.87 109	9.32 109	86.48 114	4.95 98	6.10 101	42.08 111	14.70 104	15.49 75	41.06 110	22.65 93	32.32 96	13.77 53	19.54 96	37.98 110	28.96 107	0.41 80	0.23 83	0.00 1	0.02 42	0.91 86	0.50 73

MANE	19.47 111	1.27 49	5.07 30	4.69 96	5.55 99	30.49 105	9.94 92	34.01 112	37.27 107	44.13 112	51.57 115	52.51 113	40.41 114	33.58 108	24.81 104	0.89 96	0.86 100	1.11 106	9.72 113	0.38 65	1.06 92

BEATNet-Init1	23.31 112	9.03 108	41.67 109	4.17 92	2.53 67	45.68 113	19.47 111	33.43 111	38.45 109	47.59 114	49.10 113	59.31 115	41.80 115	38.35 112	29.21 109	0.47 85	0.50 97	0.81 102	0.66 98	2.10 103	1.86 100

MADNet+	27.07 113	33.84 114	90.97 116	20.14 113	7.47 109	48.43 114	47.10 113	35.43 113	36.46 104	20.11 89	30.05 94	25.29 93	35.08 111	45.50 115	50.28 114	2.13 104	2.00 107	1.19 108	0.76 100	4.71 107	4.43 107

PWCK	30.53 114	44.32 115	47.25 111	29.76 115	7.23 106	40.78 110	27.10 112	44.73 115	44.32 112	47.31 113	36.37 104	47.16 112	26.05 106	41.26 114	31.87 111	21.83 114	4.03 112	29.50 113	4.67 111	27.17 115	7.80 112

DPSimNet_ROB	53.45 115	64.73 116	44.39 110	53.97 116	45.39 116	53.66 115	54.83 114	55.15 116	57.87 116	64.16 116	50.83 114	63.40 116	53.34 116	46.45 116	65.81 115	63.13 116	26.54 116	57.94 116	51.11 116	45.52 116	50.69 116

MADNet++	82.84 116	82.38 117	73.57 113	87.72 117	82.97 117	93.14 116	69.15 115	86.42 117	82.50 117	93.46 117	86.70 116	86.28 117	80.92 117	88.34 117	88.84 116	86.83 117	84.17 117	72.64 117	68.92 117	80.47 117	81.42 117

MEDIAN_ROB	98.41 117	99.70 118	99.30 118	97.09 118	97.02 118	96.89 117	95.77 118	97.66 118	97.28 118	98.79 120	98.94 117	99.18 118	98.14 118	96.89 118	96.88 117	99.96 120	99.16 118	100.00 118	99.99 118	99.69 118	99.88 118

AVERAGE_ROB	99.62 118	99.95 119	98.81 117	100.00 123	100.00 119	98.08 118	95.47 117	100.00 121	100.00 119	100.00 121	100.00 118	100.00 121	100.00 119	100.00 121	99.99 118	100.00 122	100.00 119	100.00 118	100.00 119	100.00 121	100.00 122

DGTPSM_ROB	99.90 119	100.00 120	99.99 119	99.99 121	100.00 119	100.00 119	100.00 119	99.97 119	100.00 119	98.35 118	100.00 118	99.84 119	100.00 119	99.98 119	99.99 118	99.99 121	100.00 119	100.00 118	100.00 119	100.00 121	100.00 122

DPSMNet_ROB	99.91 120	100.00 120	99.99 119	99.99 121	100.00 119	100.00 119	100.00 119	99.98 120	100.00 119	98.35 118	100.00 118	99.84 119	100.00 119	99.98 119	99.99 118	100.00 122	100.00 119	100.00 118	100.00 119	100.00 121	100.00 122

DPSM	99.95 121	100.00 120	100.00 121	99.76 119	100.00 119	100.00 119	100.00 119	100.00 121	100.00 119	100.00 121	100.00 118	100.00 121	100.00 119	100.00 121	100.00 121	99.21 118	100.00 119	100.00 118	100.00 119	99.99 119	99.95 119

DPSM_ROB	99.95 121	100.00 120	100.00 121	99.76 119	100.00 119	100.00 119	100.00 119	100.00 121	100.00 119	100.00 121	100.00 118	100.00 121	100.00 119	100.00 121	100.00 121	99.21 118	100.00 119	100.00 118	100.00 119	99.99 119	99.95 119

LSM0	100.00 123	100.00 120	100.00 121	100.00 123	100.00 119	100.00 119	100.00 119	100.00 121	100.00 119	100.00 121	100.00 118	100.00 121	100.00 119	100.00 121	100.00 121	100.00 122	100.00 119	100.00 118	100.00 119	100.00 121	99.99 121

FADE		17.27 112		10.46 110	9.90 111			35.80 114	53.05 114	20.32 90		26.54 96		39.35 113		30.62 115	14.22 115	38.39 115	37.63 115	5.22 109	5.56 108

MSMDNet													1.26 6

Low-res two-view benchmark