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	deliv. area 1l	deliv. area 1s	deliv. area 2l	deliv. area 2s	deliv. area 3l	deliv. area 3s	elect. 1l	elect. 1s	elect. 2l	elect. 2s	elect. 3l	elect. 3s	facade 1s	forest 1s	forest 2s	playg. 1l	playg. 1s	playg. 2l	playg. 2s	playg. 3l	playg. 3s	terra. 1s	terra. 2s	terra. 1l	terra. 1s	terra. 2l	terra. 2s

TDLM	0.09 1	0.08 3	0.12 5	0.02 1	0.02 1	0.00 1	0.01 4	0.19 6	0.04 1	0.00 1	0.00 1	0.48 9	0.01 1	0.01 2	0.26 1	0.22 1	0.08 1	0.06 4	0.01 1	0.00 1	0.10 1	0.10 4	0.01 4	0.01 1	0.00 1	0.01 1	0.30 1	0.39 7

CVANet_RVC	0.21 2	0.15 4	0.61 22	0.42 21	0.06 3	0.06 19	0.01 4	1.53 27	0.05 3	0.08 4	0.04 6	0.62 15	0.04 2	0.03 5	0.46 2	0.32 2	0.14 4	0.09 7	0.05 2	0.01 2	0.19 3	0.07 3	0.00 1	0.03 4	0.00 1	0.01 1	0.55 3	0.08 1

AANet_RVC	0.25 3	0.05 2	0.29 8	0.06 3	0.19 6	0.00 1	0.23 26	0.03 2	0.17 8	0.35 13	0.01 5	0.07 2	0.04 2	0.01 2	1.37 5	0.48 4	0.10 2	0.06 4	0.43 6	0.17 9	0.10 1	0.25 5	0.03 10	0.05 5	0.02 3	0.06 4	1.15 6	0.89 16

GANet	0.29 4	0.56 20	0.39 16	0.27 12	0.11 5	0.88 39	0.14 22	0.27 9	0.06 4	0.02 2	0.28 12	1.85 30	0.04 2	0.03 5	0.62 3	0.39 3	0.37 14	0.14 10	0.24 3	0.01 2	0.20 4	0.05 2	0.06 16	0.02 2	0.06 5	0.01 1	0.48 2	0.16 3

RYNet	0.45 5	0.04 1	0.00 1	0.02 1	0.03 2	0.00 1	0.00 1	0.01 1	0.04 1	0.07 3	0.00 1	0.05 1	0.12 9	0.00 1	4.77 43	0.60 5	0.10 2	1.00 45	0.35 5	0.01 2	0.21 5	0.04 1	0.00 1	0.02 2	0.08 7	3.06 32	1.39 7	0.13 2

CFNet	0.57 6	0.46 13	0.64 23	0.43 22	0.34 18	0.04 18	0.00 1	0.58 13	0.09 5	0.66 18	0.05 7	0.64 16	0.07 5	0.05 10	2.25 7	0.65 6	0.35 10	0.06 4	0.73 10	0.34 16	0.85 13	0.73 6	0.00 1	0.08 7	0.45 21	0.16 6	3.22 20	1.51 23

HITNet	0.59 7	0.16 5	0.10 4	0.06 3	0.07 4	0.01 8	0.02 10	1.76 32	0.82 22	0.11 5	0.00 1	0.68 19	0.28 19	0.11 24	2.51 11	1.02 12	0.25 7	0.13 8	0.63 8	0.24 14	1.43 21	1.56 17	0.01 4	0.12 11	0.02 3	0.16 6	3.32 22	0.42 8
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	0.59 7	0.58 21	0.41 18	0.19 8	0.56 25	0.12 24	0.44 30	0.06 3	1.19 31	0.40 14	2.33 39	0.19 3	0.16 12	0.07 15	2.36 8	0.83 7	0.39 15	0.31 20	0.34 4	0.45 23	0.62 9	0.86 9	0.31 38	0.15 12	0.16 12	0.16 6	1.67 9	0.64 11

DMCA-RVC	0.61 9	0.31 8	0.32 11	0.20 9	0.40 20	0.12 24	0.33 27	0.14 5	1.38 34	0.26 8	0.34 15	1.52 29	0.08 8	0.14 27	2.73 12	0.88 8	0.31 9	0.28 18	0.54 7	0.55 28	0.48 6	0.73 6	0.12 23	0.20 15	0.12 10	0.10 5	3.23 21	0.54 10

RASNet	0.63 10	0.18 6	0.57 19	0.41 20	0.28 11	0.10 22	0.05 16	0.94 18	0.14 7	1.07 29	0.09 9	0.48 9	0.34 23	0.02 4	1.28 4	1.47 26	0.35 10	0.21 12	0.99 11	0.02 5	1.15 16	1.53 15	0.10 20	0.34 28	0.22 15	0.30 11	3.55 28	0.73 13

DISCO	0.79 11	0.95 34	0.31 10	0.06 3	0.33 16	0.51 33	0.44 30	0.23 8	0.32 14	1.75 41	0.59 21	0.38 8	0.29 20	0.04 8	2.98 15	1.36 20	0.96 34	0.29 19	3.24 32	0.53 26	0.79 12	1.45 13	0.10 20	0.07 6	0.12 10	0.29 10	2.76 14	0.31 6

NVstereo2D	0.83 12	0.43 11	0.07 3	0.23 10	0.36 19	0.41 32	0.08 18	1.61 30	0.59 18	0.84 21	1.11 29	0.36 6	0.21 17	0.07 15	5.88 54	2.16 42	0.62 22	0.45 26	1.50 16	0.19 10	1.20 17	0.94 12	0.02 6	0.32 24	1.30 31	0.24 9	0.95 4	0.24 5

CFNet_RVC	0.86 13	0.59 22	0.74 28	0.33 14	0.32 15	0.11 23	0.02 10	0.11 4	0.17 8	0.87 24	0.74 25	0.57 14	0.16 12	0.08 19	3.11 17	1.19 19	0.50 17	0.34 22	1.28 14	0.15 7	1.68 26	1.48 14	0.02 6	0.25 16	0.86 29	1.89 27	3.64 30	2.13 27

DLCB_ROB	0.92 14	0.72 27	0.64 23	0.43 22	0.42 21	0.14 27	0.18 24	0.43 10	0.28 12	0.85 22	0.53 18	1.12 25	0.72 42	0.07 15	2.16 6	1.12 16	0.88 32	0.26 15	0.69 9	0.20 11	1.35 20	1.53 15	0.49 50	0.28 19	4.11 55	2.41 29	2.04 11	0.78 14

HSM	0.97 15	0.30 7	0.87 31	0.54 28	0.46 23	0.00 1	0.01 4	2.93 52	0.30 13	0.13 6	0.56 20	0.65 17	0.13 10	0.05 10	2.97 14	1.08 15	0.66 26	0.17 11	3.26 34	0.35 17	1.78 27	2.03 23	0.04 11	0.33 27	0.38 18	0.81 19	4.16 42	1.10 18

NLCA_NET_v2_RVC	0.99 16	0.82 30	0.34 14	0.18 7	0.43 22	0.03 16	1.10 43	1.20 22	2.50 54	2.06 46	0.11 10	0.69 20	0.07 5	0.54 44	3.65 28	0.91 9	0.19 6	0.22 13	1.65 20	0.15 7	0.73 11	0.92 11	0.08 17	0.18 14	0.11 9	3.29 36	2.58 13	2.09 26
Zhibo Rao, Mingyi He, Yuchao Dai, Zhidong Zhu, Bo Li, and Renjie He.: NLCA-Net: A non-local context attention network for stereo matching.
PDISCO_ROB	1.03 17	0.55 19	0.06 2	0.67 30	0.28 11	0.00 1	0.21 25	0.71 15	0.49 17	1.28 31	0.99 28	0.25 5	0.32 22	0.19 29	3.02 16	2.03 39	0.69 27	1.42 57	2.26 21	0.58 29	2.32 32	3.22 41	0.14 25	0.27 18	1.36 32	0.37 12	3.84 36	0.23 4

STTStereo	1.06 18	0.85 32	0.57 19	0.36 18	0.29 13	0.08 21	0.64 34	0.43 10	1.56 40	1.40 37	0.26 11	1.95 31	0.07 5	0.29 36	4.26 31	1.06 13	0.25 7	0.23 14	1.16 13	0.14 6	1.46 23	0.84 8	0.12 23	0.10 10	0.07 6	1.81 26	3.51 27	4.84 41

PMTNet	1.06 18	1.07 37	1.62 57	0.25 11	0.21 9	0.01 8	0.05 16	1.53 27	0.64 20	0.31 10	0.44 17	0.54 12	0.51 34	0.08 19	3.20 18	2.70 50	0.61 19	0.41 25	2.84 29	0.22 12	4.32 51	2.47 30	0.08 17	0.15 12	0.47 22	1.51 24	1.09 5	1.15 20

iResNet_ROB	1.07 20	0.65 25	0.30 9	0.45 24	0.30 14	0.01 8	0.02 10	3.10 53	0.12 6	1.34 32	0.00 1	0.66 18	0.35 24	0.04 8	4.37 35	1.65 31	0.54 18	0.49 28	5.83 46	0.29 15	1.30 19	0.87 10	0.20 32	0.26 17	0.16 12	0.84 20	3.74 34	1.12 19

Nwc_Net	1.11 21	0.51 15	0.87 31	0.34 16	0.78 29	0.89 40	1.87 48	2.40 42	1.15 29	0.48 16	0.68 23	3.66 40	0.16 12	0.27 34	2.44 9	0.98 10	0.35 10	0.01 1	1.60 17	0.40 18	0.50 7	2.58 32	0.05 14	0.08 7	0.66 26	0.45 14	3.47 25	2.34 28

AF-Net	1.11 21	0.51 15	0.87 31	0.34 16	0.78 29	0.89 40	1.87 48	2.40 42	1.15 29	0.48 16	0.68 23	3.66 40	0.16 12	0.27 34	2.44 9	0.98 10	0.35 10	0.01 1	1.60 17	0.40 18	0.50 7	2.58 32	0.05 14	0.08 7	0.66 26	0.45 14	3.47 25	2.34 28

iResNetv2_ROB	1.26 23	0.75 28	0.32 11	1.29 47	0.33 16	0.02 15	0.02 10	3.19 54	0.20 10	2.00 45	0.29 13	2.24 34	0.41 28	0.06 13	3.64 27	1.45 25	0.75 29	0.13 8	5.77 44	0.43 22	2.86 39	1.71 19	0.16 28	0.37 31	0.38 18	0.47 16	4.08 40	0.72 12

RP	1.29 24	1.06 36	2.32 65	0.84 34	1.16 34	0.39 31	1.53 45	1.89 36	1.68 43	0.29 9	2.21 38	2.25 35	0.13 10	0.40 41	3.31 22	1.07 14	0.61 19	0.05 3	1.61 19	0.40 18	0.65 10	3.05 38	0.11 22	0.29 20	0.29 16	0.92 21	4.24 43	2.04 25

BEATNet_4x	1.40 25	0.54 18	0.27 7	0.13 6	0.27 10	0.01 8	0.10 19	1.80 33	1.74 45	0.41 15	0.53 18	0.82 22	0.59 37	0.54 44	4.30 32	2.92 51	1.87 50	1.84 65	1.39 15	0.71 32	4.68 54	6.21 70	0.02 6	0.81 42	0.21 14	0.40 13	3.69 31	0.96 17

DN-CSS_ROB	1.45 26	0.52 17	1.11 40	0.81 33	0.69 27	0.00 1	0.03 15	2.86 51	0.35 15	1.50 38	3.76 54	0.73 21	0.36 26	0.07 15	2.89 13	1.44 23	1.08 38	0.79 34	8.61 57	0.23 13	3.25 44	1.97 21	0.02 6	0.66 39	0.10 8	0.52 17	3.12 19	1.56 24

DeepPruner_ROB	1.57 27	0.37 10	0.71 26	0.50 26	0.55 24	0.37 30	1.60 46	1.74 31	0.84 24	1.37 34	2.40 41	0.49 11	0.51 34	0.10 23	5.38 49	2.16 42	1.10 39	1.08 48	2.28 22	0.40 18	4.83 58	3.42 42	0.66 58	0.34 28	0.57 25	5.04 51	3.07 15	0.53 9

FADNet-RVC-Resample	1.60 28	0.67 26	0.97 36	0.50 26	0.64 26	0.18 28	1.05 40	1.27 24	0.83 23	0.96 26	0.97 27	5.23 48	0.42 29	1.02 67	4.81 46	1.68 32	1.05 36	1.96 67	3.78 37	1.06 42	1.52 24	2.28 28	0.21 33	1.35 51	0.55 23	3.16 35	2.13 12	2.92 31

PA-Net	1.61 29	0.81 29	1.43 50	0.27 12	1.99 54	0.12 24	0.34 28	0.19 6	1.90 47	0.85 22	0.41 16	0.24 4	0.20 16	0.78 59	4.61 41	1.44 23	0.17 5	0.26 15	1.08 12	0.53 26	1.44 22	3.18 40	0.65 56	0.44 33	0.99 30	7.71 64	1.78 10	9.78 55
Zhibo Rao, Mingyi He, Yuchao Dai, Zhelun Shen: Patch Attention Network with Generative Adversarial Model for Semi-Supervised Binocular Disparity Prediction.
FADNet-RVC	1.64 30	0.31 8	0.64 23	0.33 14	1.19 37	0.01 8	2.53 59	0.57 12	0.22 11	1.03 28	0.32 14	6.04 52	0.29 20	0.32 39	4.47 38	1.90 37	0.62 22	0.78 33	6.45 49	1.80 55	1.85 28	2.02 22	0.19 31	0.52 37	1.78 36	1.74 25	3.10 16	3.15 32

Abc-Net	1.86 31	1.63 44	1.33 46	0.95 41	1.22 39	0.80 36	2.29 55	2.62 48	2.93 57	0.34 11	2.87 49	2.16 32	1.17 46	0.21 30	3.63 24	1.13 17	0.63 24	0.96 43	2.79 27	0.75 33	0.98 14	2.96 36	0.36 43	0.32 24	2.31 42	4.50 46	3.69 31	4.78 38

NCC-stereo	1.86 31	1.63 44	1.33 46	0.95 41	1.22 39	0.80 36	2.29 55	2.62 48	2.93 57	0.34 11	2.87 49	2.16 32	1.17 46	0.21 30	3.63 24	1.13 17	0.63 24	0.96 43	2.79 27	0.75 33	0.98 14	2.96 36	0.36 43	0.32 24	2.31 42	4.50 46	3.69 31	4.78 38

stereogan	1.89 33	2.00 52	1.17 42	1.47 49	2.05 57	1.72 49	0.87 38	1.84 35	1.11 27	1.36 33	1.51 32	5.81 50	0.48 33	0.32 39	3.87 29	1.69 33	0.80 30	0.39 24	3.96 38	0.78 35	1.23 18	4.02 49	0.26 35	0.51 36	0.30 17	1.30 23	6.30 56	3.84 36

FADNet	1.92 34	0.44 12	0.60 21	0.54 28	1.05 33	0.00 1	2.95 63	0.78 16	0.38 16	0.81 20	0.61 22	2.40 36	0.47 32	0.65 54	5.57 51	1.73 34	0.69 27	1.08 48	8.93 59	1.61 53	2.36 34	2.52 31	0.09 19	0.36 30	2.54 47	3.77 41	3.43 24	5.46 42

NCCL2	2.12 35	2.27 56	1.29 43	1.28 46	1.85 51	0.18 28	0.77 37	1.24 23	1.25 33	1.62 39	2.71 46	1.06 23	0.51 34	0.31 37	4.40 36	2.33 46	1.57 44	0.62 30	2.35 23	0.68 31	2.68 38	4.29 53	1.52 71	1.06 44	4.65 59	4.17 43	4.04 39	6.58 48

R-Stereo	2.16 36	1.08 38	1.57 54	0.84 34	0.19 6	0.01 8	0.01 4	2.05 39	1.01 25	1.37 34	2.45 42	1.50 27	0.46 30	0.21 30	3.23 19	4.53 68	1.62 45	1.05 46	7.07 50	1.09 44	4.86 59	5.93 67	0.04 11	0.31 21	2.48 44	4.63 48	3.10 16	5.74 44

R-Stereo Train	2.16 36	1.08 38	1.57 54	0.84 34	0.19 6	0.01 8	0.01 4	2.05 39	1.01 25	1.37 34	2.45 42	1.50 27	0.46 30	0.21 30	3.23 19	4.53 68	1.62 45	1.05 46	7.07 50	1.09 44	4.86 59	5.93 67	0.04 11	0.31 21	2.48 44	4.63 48	3.10 16	5.74 44

GANetREF_RVC	2.43 38	1.69 47	0.81 29	2.04 55	1.16 34	1.02 44	0.10 19	4.72 68	1.44 37	3.62 65	0.06 8	10.03 62	0.69 40	0.09 21	3.63 24	1.36 20	1.06 37	0.94 41	6.44 48	0.46 24	2.32 32	1.74 20	0.17 29	1.35 51	3.41 53	3.75 40	6.55 58	4.82 40
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
RGC	2.44 39	1.98 51	4.87 78	1.54 50	1.65 45	1.74 50	1.05 40	2.02 38	1.43 36	0.88 25	4.42 58	2.52 38	2.42 53	0.58 49	4.33 33	1.63 30	0.91 33	0.48 27	4.28 39	1.08 43	1.94 29	4.01 48	0.15 26	0.72 41	2.19 40	5.22 53	4.90 50	6.96 49

MLCV	2.45 40	0.61 23	0.81 29	2.48 58	1.21 38	0.95 42	0.50 32	3.57 57	0.61 19	3.75 68	4.26 56	5.13 46	3.34 56	0.06 13	4.63 42	1.78 36	1.32 42	0.86 38	10.05 60	1.09 44	2.30 31	3.92 46	0.29 36	2.16 60	1.87 37	3.06 32	4.01 38	1.40 21

RTSC	2.56 41	0.89 33	1.50 51	0.47 25	0.76 28	0.87 38	2.29 55	1.56 29	1.91 48	2.12 47	2.86 48	1.23 26	0.97 45	1.03 69	7.27 67	3.36 61	4.68 74	1.74 62	7.73 53	1.11 47	3.95 48	5.39 61	0.21 33	1.11 47	0.40 20	0.95 22	4.56 47	8.26 54

DeepPrunerF	2.66 42	1.67 46	0.33 13	3.58 66	9.30 87	1.76 51	3.48 66	0.68 14	3.29 60	0.71 19	1.59 34	0.37 7	0.27 18	0.13 25	5.94 55	3.42 64	1.03 35	0.54 29	4.47 40	0.65 30	2.02 30	2.06 24	0.56 53	0.31 21	15.21 85	3.30 37	3.74 34	1.47 22

NOSS_ROB	2.78 43	3.78 70	0.39 16	2.02 54	1.58 44	2.36 56	0.00 1	2.66 50	1.54 39	3.63 66	1.79 37	2.55 39	3.51 57	0.83 62	5.82 53	5.57 77	2.69 56	1.83 64	2.63 26	0.91 39	4.62 52	4.13 50	0.42 46	2.58 64	2.29 41	4.46 45	7.67 65	2.88 30

SGM-Forest	2.81 44	2.03 53	0.36 15	6.32 77	1.79 50	2.66 57	0.02 10	1.42 25	0.77 21	2.52 48	0.96 26	6.57 53	5.74 60	0.31 37	4.36 34	2.94 53	0.61 19	0.33 21	3.08 30	0.47 25	2.46 36	2.73 34	0.84 63	0.45 34	3.66 54	3.74 39	11.30 73	7.44 51
Johannes L. Schönberger, Sudipta Sinha, Marc Pollefeys: Learning to Fuse Proposals from Multiple Scanline Optimizations in Semi-Global Matching. ECCV 2018
PWCDC_ROB	2.82 45	0.49 14	0.17 6	0.38 19	0.79 31	0.03 16	0.10 19	1.16 21	8.93 77	0.14 7	2.49 44	0.55 13	31.02 91	0.57 46	5.58 52	3.32 60	1.73 47	0.91 40	2.53 25	0.88 37	2.92 40	7.18 74	0.15 26	0.53 38	0.55 23	0.69 18	1.43 8	0.88 15

HSM-Net_RVC	2.86 46	1.24 41	1.50 51	2.55 60	1.72 46	0.57 34	0.17 23	3.55 56	1.14 28	3.50 64	6.32 71	7.94 54	2.93 54	0.05 10	3.38 23	2.12 40	1.28 41	0.26 15	3.24 32	1.24 49	3.66 46	3.76 45	0.61 54	2.64 65	4.43 57	6.27 59	5.76 53	5.47 43
Gengshan Yang, Joshua Manela, Michael Happold, and Deva Ramanan: Hierarchical Deep Stereo Matching on High-resolution Images. CVPR 2019
ADCRef	2.96 47	2.78 63	1.02 37	0.70 31	2.21 58	1.96 53	2.42 58	0.96 19	6.10 68	1.94 44	1.15 30	1.08 24	0.74 43	1.32 74	6.01 56	3.38 62	1.34 43	1.15 52	8.41 56	2.09 60	2.59 37	3.60 44	1.88 73	0.71 40	2.81 49	8.00 66	3.42 23	10.24 56

NaN_ROB	3.01 48	1.16 40	1.13 41	0.86 38	3.03 63	0.59 35	0.75 35	3.25 55	2.58 55	0.98 27	1.32 31	21.10 75	0.59 37	1.15 72	4.15 30	1.58 29	0.80 30	0.70 31	2.38 24	1.30 50	1.52 24	2.15 25	0.46 49	1.07 46	2.50 46	6.25 58	4.54 46	13.27 61

XPNet_ROB	3.02 49	2.54 59	1.33 46	0.73 32	1.45 43	1.04 45	0.61 33	0.83 17	1.45 38	1.16 30	3.44 51	26.85 81	0.35 24	0.40 41	3.24 21	2.22 45	3.28 63	0.79 34	3.20 31	1.19 48	2.94 42	5.51 62	0.76 60	0.46 35	0.72 28	2.37 28	9.22 67	3.37 35

ccs	3.29 50	0.63 24	1.94 60	0.99 43	2.02 55	0.06 19	0.01 4	3.87 60	1.79 46	4.48 80	9.13 82	4.94 44	4.74 59	0.87 63	6.01 56	5.69 78	1.83 49	1.39 55	5.37 42	1.03 41	5.86 68	7.35 76	0.32 40	1.56 54	3.32 52	6.28 60	4.08 40	3.36 34

ADCP+	3.47 51	2.05 54	2.64 68	1.31 48	1.93 52	1.19 46	3.99 67	1.07 20	9.83 79	1.78 42	5.75 67	8.79 58	0.37 27	0.90 64	5.04 48	2.20 44	0.44 16	0.90 39	5.82 45	0.88 37	2.38 35	3.43 43	0.33 41	0.41 32	3.03 51	12.72 78	3.59 29	10.90 57

FC-DCNN	3.82 52	4.38 74	5.67 85	9.61 83	4.14 69	8.01 80	3.26 64	4.21 61	1.69 44	2.95 56	1.54 33	5.87 51	2.09 52	0.13 25	4.40 36	2.15 41	2.54 55	1.11 50	3.38 35	0.82 36	3.11 43	2.20 26	0.65 56	3.29 67	6.33 69	4.91 50	6.98 61	7.80 53

ADCL	3.91 53	3.61 68	2.28 63	1.76 52	1.76 49	3.09 60	4.16 68	1.98 37	13.71 86	2.81 54	5.14 63	2.47 37	0.65 39	1.10 71	5.38 49	2.55 48	2.02 51	2.20 69	6.41 47	2.08 59	4.87 61	4.20 51	1.40 69	1.06 44	6.69 70	6.60 61	4.33 45	11.16 59

FADNet_RVC	3.95 54	2.06 55	1.30 44	3.33 64	3.36 65	0.99 43	2.06 53	2.30 41	1.39 35	1.72 40	4.72 60	9.29 59	5.82 62	1.76 79	8.23 81	3.12 56	2.98 59	4.27 81	16.83 68	3.30 73	4.99 64	5.51 62	0.63 55	1.39 53	1.45 33	3.14 34	4.86 48	5.92 46

LALA_ROB	4.04 55	4.73 76	1.42 49	1.16 45	1.93 52	2.17 55	1.04 39	1.80 33	2.48 53	2.74 51	5.87 68	33.34 83	0.69 40	0.78 59	6.02 58	2.33 46	3.21 62	1.82 63	3.66 36	1.88 56	3.40 45	4.99 56	0.34 42	1.03 43	1.91 38	3.61 38	8.50 66	6.20 47

iResNet	4.14 56	0.84 31	0.71 26	2.34 57	2.59 59	4.58 67	1.07 42	4.67 66	1.21 32	3.72 67	3.61 52	12.28 64	16.06 75	0.03 5	6.64 64	3.14 57	2.35 54	1.89 66	16.43 67	2.53 65	3.76 47	2.90 35	0.17 29	3.88 72	1.66 35	4.23 44	5.19 51	3.23 33

SHD	4.34 57	1.02 35	2.50 66	1.71 51	1.33 41	1.46 47	2.01 50	4.90 69	4.30 66	2.63 49	4.99 62	4.39 43	9.41 67	0.58 49	8.20 79	4.81 71	4.43 73	2.44 73	13.01 65	2.95 70	5.61 67	6.88 73	0.30 37	3.26 66	4.11 55	5.16 52	3.88 37	10.98 58

CSAN	4.46 58	2.36 58	1.57 54	3.12 62	3.32 64	1.64 48	0.76 36	4.59 65	4.37 67	3.80 70	2.84 47	17.58 72	10.47 69	0.96 66	4.80 45	1.75 35	2.06 52	1.16 53	5.69 43	2.34 63	2.93 41	2.40 29	0.43 47	2.56 63	4.64 58	11.45 76	7.53 64	13.44 62

ETE_ROB	4.62 59	4.04 72	1.52 53	1.14 44	2.02 55	2.70 58	1.28 44	1.50 26	4.25 65	1.89 43	5.88 69	37.95 88	0.84 44	1.42 77	4.94 47	2.66 49	3.81 68	0.95 42	4.84 41	1.63 54	4.01 49	5.32 60	0.67 59	1.14 48	2.03 39	3.84 42	15.25 80	7.23 50

XQC	4.76 60	3.14 65	1.63 58	3.31 63	3.69 67	3.46 63	2.94 62	6.02 75	3.05 59	2.64 50	5.51 65	5.67 49	7.46 63	1.41 76	8.02 72	4.65 70	3.59 65	1.49 59	10.75 61	2.91 66	4.96 63	6.67 72	0.41 45	1.91 56	7.13 74	10.47 75	11.17 72	4.51 37

MSMDNet	4.98 61	2.59 61	3.57 71	2.54 59	0.90 32	3.99 64	1.63 47	4.52 64	1.56 40	4.54 81	18.92 100	20.82 74	12.09 70	0.60 53	6.57 63	5.84 79	2.28 53	1.52 60	7.08 52	1.94 58	6.09 69	6.12 69	0.31 38	2.29 61	1.47 34	2.83 31	4.25 44	7.49 52

CBMV	5.52 62	3.65 69	1.32 45	3.46 65	2.86 62	2.04 54	0.41 29	3.64 58	2.63 56	4.09 74	2.36 40	14.13 67	3.70 58	0.57 46	7.16 66	6.19 83	4.26 71	2.36 72	8.76 58	1.44 51	6.43 70	4.53 55	0.54 52	5.62 81	4.85 60	6.08 56	19.41 84	26.62 86
Konstantinos Batsos, Changjiang Cai, Philippos Mordohai: CBMV: A Coalesced Bidirectional Matching Volume for Disparity Estimation. Computer Vision and Pattern Recognition (CVPR) 2018
RTS	5.53 63	1.46 42	0.94 34	0.90 39	1.73 47	4.08 65	4.63 72	2.53 45	3.41 61	2.79 52	1.70 35	8.18 55	1.27 48	0.72 55	7.83 69	4.87 72	7.37 86	2.34 70	18.33 69	2.92 67	4.78 55	5.88 65	1.04 64	1.31 49	6.74 71	22.88 97	6.66 59	22.00 76

RTSA	5.53 63	1.46 42	0.94 34	0.90 39	1.73 47	4.08 65	4.63 72	2.53 45	3.41 61	2.79 52	1.70 35	8.18 55	1.27 48	0.72 55	7.83 69	4.87 72	7.37 86	2.34 70	18.33 69	2.92 67	4.78 55	5.88 65	1.04 64	1.31 49	6.74 71	22.88 97	6.66 59	22.00 76

AnyNet_C32	5.68 65	1.96 49	2.91 69	1.78 53	2.71 61	3.17 61	5.76 77	4.31 62	12.56 81	3.07 58	7.17 73	4.22 42	1.70 50	2.19 80	8.22 80	5.98 81	5.69 79	4.43 85	12.45 64	2.93 69	9.72 85	8.57 85	1.84 72	3.46 69	6.24 68	9.82 73	6.26 55	14.21 63

CBMV_ROB	6.09 66	2.65 62	2.29 64	8.35 80	5.74 76	5.08 68	2.76 61	5.03 71	2.35 51	3.78 69	4.70 59	21.22 76	13.56 73	0.09 21	6.04 59	3.70 66	2.84 57	1.39 55	11.35 62	8.80 90	4.92 62	3.11 39	0.43 47	2.10 59	7.06 73	10.12 74	12.96 75	11.93 60

ADCPNet	6.67 67	1.97 50	3.86 74	2.75 61	6.19 80	3.07 59	7.60 84	5.21 72	8.03 74	3.82 71	7.92 76	5.17 47	13.78 74	2.98 84	8.10 75	6.12 82	4.35 72	2.04 68	18.50 71	4.74 78	7.04 74	7.43 77	2.98 80	1.91 56	8.96 77	14.04 83	7.02 63	14.47 65

AMNet	6.77 68	3.87 71	2.62 67	4.00 70	5.86 77	6.75 74	3.31 65	2.51 44	2.47 52	3.44 62	6.68 72	9.34 60	2.05 51	7.44 96	4.79 44	9.81 94	13.48 95	7.65 95	7.95 55	7.83 85	11.47 89	7.62 80	2.74 78	4.18 73	5.52 63	8.25 68	13.24 76	17.97 71

ADCMid	6.83 69	4.46 75	4.95 79	2.16 56	4.31 72	5.71 72	7.29 81	8.83 76	12.78 83	3.11 59	8.10 78	9.83 61	9.65 68	2.84 81	8.51 83	5.42 76	4.68 74	2.83 75	18.87 74	3.22 71	7.09 75	7.70 81	5.37 88	2.33 62	5.12 62	8.71 70	5.21 52	15.24 66

PWC_ROB	7.15 70	1.85 48	5.57 83	0.85 37	1.17 36	1.95 52	4.77 74	2.56 47	17.27 96	3.83 72	7.66 75	4.97 45	39.20 99	0.81 61	8.35 82	4.96 75	6.51 82	4.27 81	15.99 66	4.39 75	7.48 77	7.59 79	0.53 51	4.79 78	2.74 48	2.63 30	7.01 62	23.26 79

MFN_U_SF_DS_RVC	7.30 71	3.59 67	1.09 39	9.20 81	3.71 68	7.69 78	7.51 83	10.81 81	8.52 75	4.93 83	4.20 55	16.73 71	9.30 66	5.45 94	8.09 74	3.29 59	1.80 48	1.13 51	18.77 72	2.10 61	6.48 71	7.49 78	3.17 84	1.74 55	12.06 83	14.29 84	9.71 69	14.36 64

FBW_ROB	7.98 72	9.24 87	5.57 83	20.21 91	8.25 85	12.08 85	8.09 85	4.92 70	1.58 42	3.30 61	5.15 64	13.88 66	3.03 55	7.45 97	6.23 60	1.49 27	2.89 58	0.79 34	33.18 91	1.93 57	5.24 65	4.40 54	9.43 95	8.29 91	4.88 61	7.69 63	4.88 49	21.40 74

pmcnn	8.05 73	2.96 64	2.25 62	6.23 75	5.03 73	6.98 75	4.33 70	4.70 67	2.02 50	4.19 75	9.20 84	19.11 73	20.39 81	0.73 57	7.05 65	6.73 84	6.29 81	4.51 86	22.54 81	4.66 77	9.62 84	5.08 58	4.46 87	4.23 74	5.99 64	5.22 53	17.26 82	25.55 85

ADCS	9.93 74	5.64 79	4.82 77	3.95 69	6.05 79	6.17 73	5.70 76	9.47 78	15.68 87	4.19 75	7.98 77	12.91 65	17.41 76	3.94 91	10.52 92	11.68 98	10.14 88	7.14 94	24.46 85	8.67 89	13.95 95	13.00 98	2.94 79	6.15 84	9.75 80	17.65 89	10.70 71	17.41 68

SGM_RVC	10.08 75	10.50 89	3.60 72	16.68 86	8.80 86	14.87 87	7.11 80	9.19 77	6.25 69	4.06 73	7.33 74	24.89 78	18.29 78	0.57 46	4.57 40	1.98 38	3.30 64	1.17 54	20.75 77	2.20 62	4.80 57	2.23 27	2.29 75	3.65 70	17.68 90	13.31 80	33.30 94	28.67 88
Heiko Hirschmueller: Stereo processing by semiglobal matching and mutual information. TPAMI 2008, Volume 30(2), pp. 328-341
MDST_ROB	10.13 76	16.70 96	3.04 70	29.06 95	9.34 88	20.66 93	5.02 75	5.90 74	1.98 49	3.16 60	2.70 45	11.22 63	28.15 87	0.18 28	6.30 61	1.37 22	1.21 40	0.34 22	7.74 54	1.01 40	4.67 53	3.95 47	1.92 74	1.94 58	26.55 94	19.78 91	37.02 97	22.50 78

SANet	10.32 77	4.15 73	6.27 86	5.51 73	5.49 75	8.58 82	2.27 54	15.41 91	13.03 85	2.83 55	9.09 81	60.35 102	25.50 84	2.93 83	8.06 73	3.02 55	7.05 83	3.86 80	11.43 63	3.25 72	5.27 66	5.02 57	2.60 77	7.27 89	11.08 81	12.57 77	13.36 77	23.31 80

MFN_U_SF_RVC	10.34 78	6.17 84	3.69 73	9.55 82	5.13 74	12.52 86	10.34 88	12.25 84	7.05 70	12.23 97	14.31 91	22.82 77	13.03 71	8.82 98	11.37 96	4.87 72	3.83 70	3.31 77	39.34 95	5.97 81	8.56 82	8.81 86	1.45 70	6.40 86	9.49 79	8.57 69	9.56 68	19.71 72

ccs_rob	10.35 79	5.69 80	2.14 61	4.64 72	2.67 60	5.53 71	6.85 79	4.40 63	4.18 64	5.98 87	10.34 86	26.00 79	37.16 97	3.25 87	19.47 103	10.00 95	11.64 93	3.40 78	48.57 98	13.46 94	7.76 78	10.45 91	0.80 61	4.63 76	2.91 50	6.10 57	6.08 54	15.43 67

G-Net	10.87 80	4.96 77	9.71 90	3.77 67	4.24 70	7.37 76	2.01 50	10.08 79	15.80 89	4.95 84	15.59 93	48.52 97	9.05 64	0.58 49	8.11 77	8.67 89	5.49 76	4.42 83	23.80 82	15.66 97	8.01 80	8.23 83	3.06 82	5.14 79	6.15 66	13.92 81	22.56 86	23.75 81

STTStereo_v2	10.87 80	4.96 77	9.71 90	3.77 67	4.24 70	7.37 76	2.01 50	10.08 79	15.80 89	4.95 84	15.59 93	48.52 97	9.05 64	0.58 49	8.11 77	8.67 89	5.49 76	4.42 83	23.80 82	15.66 97	8.01 80	8.23 83	3.06 82	5.14 79	6.15 66	13.92 81	22.56 86	23.75 81

MSC_U_SF_DS_RVC	10.98 82	10.59 90	6.33 87	17.49 87	6.29 81	7.85 79	10.69 89	18.03 95	23.43 103	11.13 96	4.86 61	14.66 68	5.81 61	9.65 100	9.78 88	5.91 80	3.18 61	5.17 87	39.06 94	7.03 84	7.92 79	9.81 90	7.04 89	7.22 88	14.77 84	8.85 71	6.40 57	17.43 69

edge stereo	11.35 83	6.83 85	10.52 92	14.06 84	12.00 92	16.55 89	12.81 91	12.42 86	7.44 72	6.06 88	15.12 92	38.81 90	17.75 77	1.25 73	7.59 68	7.29 86	5.73 80	3.11 76	25.18 86	4.53 76	6.71 72	8.01 82	4.16 85	3.71 71	8.94 76	7.65 62	13.41 78	28.72 89

SGM-ForestM	11.60 84	15.35 94	4.54 75	19.02 89	8.08 84	18.74 92	10.83 90	12.03 82	7.24 71	3.01 57	6.09 70	36.06 87	23.95 82	0.75 58	4.47 38	1.51 28	3.60 66	0.75 32	20.06 76	1.60 52	4.23 50	1.65 18	1.36 68	3.34 68	25.09 93	20.48 93	34.27 96	25.03 84

AnyNet_C01	12.12 85	6.13 83	5.39 81	6.24 76	6.03 78	5.20 69	9.20 86	12.30 85	16.87 93	5.85 86	9.03 80	26.16 80	18.91 79	4.53 93	11.14 95	12.98 99	16.27 96	15.82 101	34.24 92	10.36 92	16.44 96	13.34 99	7.06 90	6.93 87	11.61 82	9.46 72	9.77 70	19.91 73

PVD	12.14 86	5.88 81	8.51 89	7.70 79	6.65 82	10.05 83	6.16 78	21.11 100	19.74 99	3.44 62	8.69 79	16.07 69	27.50 86	2.86 82	8.93 85	7.52 88	11.20 91	6.11 92	24.24 84	6.83 83	11.08 86	11.21 93	1.11 66	5.71 82	15.30 86	21.90 95	17.71 83	34.49 94

MeshStereo	13.21 87	10.28 88	5.53 82	24.29 94	14.71 93	17.26 90	7.30 82	12.03 82	7.47 73	4.66 82	9.13 82	38.56 89	29.80 88	0.45 43	9.43 87	7.37 87	3.76 67	2.44 73	18.85 73	2.41 64	12.93 93	7.18 74	1.21 67	5.79 83	22.04 92	16.38 87	33.15 93	32.34 92
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
DPSNet	14.25 88	3.23 66	1.83 59	7.63 78	7.22 83	10.44 84	4.19 69	5.68 73	8.64 76	4.20 77	3.75 53	72.37 104	26.68 85	4.43 92	10.42 90	10.25 97	10.56 89	8.02 96	58.50 102	8.44 88	11.36 88	8.93 87	16.95 100	10.34 96	18.62 91	15.80 86	14.33 79	21.91 75

MFMNet_re	16.26 89	13.95 92	7.70 88	24.27 93	9.34 88	33.99 100	17.43 93	12.42 86	19.62 98	10.23 95	13.58 90	39.02 91	13.47 72	1.40 75	10.73 93	10.12 96	29.43 102	12.22 98	31.31 88	10.07 91	17.19 97	9.15 88	8.44 93	9.02 93	8.97 78	5.68 55	24.08 88	36.04 96

STStereo	19.12 90	25.20 100	16.96 102	40.13 100	26.93 100	32.21 98	21.77 99	19.35 98	16.49 92	7.75 92	17.60 97	46.83 95	36.96 96	1.06 70	8.10 75	2.99 54	3.81 68	1.57 61	31.85 89	5.18 80	6.77 73	5.31 59	3.04 81	9.71 95	29.57 95	23.01 99	40.22 98	35.81 95

ELAS_RVC	19.26 91	19.85 98	14.31 97	33.92 97	22.40 96	33.39 99	19.24 97	15.07 89	10.89 80	8.20 93	17.30 96	54.84 101	32.79 93	3.23 86	8.72 84	3.46 65	11.25 92	6.19 93	19.97 75	7.86 86	12.63 92	12.02 96	9.45 96	10.70 97	30.22 97	22.17 96	41.23 100	38.75 99
A. Geiger, M. Roser, R. Urtasun: Efficient large-scale stereo matching. ACCV 2010
SAMSARA	19.29 92	2.55 60	5.07 80	4.09 71	3.44 66	3.26 62	4.38 71	15.32 90	9.58 78	4.44 78	5.63 66	8.73 57	24.82 83	3.30 89	10.45 91	6.81 85	5.49 76	3.46 79	21.26 78	4.77 79	17.96 99	24.74 104	0.82 62	4.77 77	80.12 107	91.25 107	77.91 106	76.45 106

MADNet+	19.30 93	7.92 86	15.32 99	17.51 88	11.42 91	8.09 81	18.41 95	28.03 103	17.21 95	12.46 98	12.08 87	33.63 84	30.37 89	9.62 99	18.64 102	14.89 101	25.78 100	10.10 97	40.05 96	16.50 99	17.34 98	12.76 97	9.48 97	18.60 102	35.02 103	20.22 92	21.19 85	38.41 97

ELAS	19.48 94	22.90 99	14.50 98	35.26 99	24.25 99	31.48 97	19.80 98	16.72 93	15.91 91	7.71 91	15.62 95	48.88 99	30.47 90	3.20 85	9.19 86	3.39 63	10.97 90	5.79 90	21.49 79	6.53 82	11.69 90	11.90 95	9.30 94	9.63 94	32.86 98	24.17 100	41.19 99	41.31 100
A. Geiger, M. Roser, R. Urtasun: Efficient large-scale stereo matching. ACCV 2010
MANE	19.83 95	17.14 97	15.43 100	34.46 98	23.74 98	25.27 95	17.85 94	19.50 99	17.04 94	6.13 89	12.40 88	41.03 92	35.23 95	3.36 90	7.87 71	8.98 91	7.09 84	29.77 104	21.81 80	3.71 74	9.51 83	5.54 64	2.50 76	8.83 92	34.12 100	27.95 102	51.25 101	47.85 102

SPS-STEREO	20.13 96	14.92 93	11.88 93	19.84 90	20.39 94	18.24 91	9.27 87	16.06 92	19.74 99	19.91 102	20.06 102	33.66 85	37.68 98	7.23 95	13.17 99	16.66 103	26.75 101	16.01 102	32.30 90	23.65 103	30.25 104	22.84 103	13.67 98	13.47 100	16.56 88	15.26 85	29.55 91	24.45 83
K. Yamaguchi, D. McAllester, R. Urtasun: Efficient Joint Segmentation, Occlusion Labeling, Stereo and Flow Estimation. ECCV 2014
SGM+DAISY	20.91 97	16.10 95	12.43 94	22.81 92	21.80 95	24.45 94	18.63 96	17.89 94	12.77 82	18.42 101	19.55 101	30.39 82	40.48 100	11.67 101	12.56 98	15.10 102	25.73 99	12.69 99	34.93 93	21.56 102	26.12 103	22.15 102	21.16 101	12.73 99	17.44 89	13.30 79	33.35 95	28.26 87

LE_ROB	22.46 98	10.87 91	12.67 95	32.44 96	37.93 101	31.36 96	33.43 101	23.22 101	21.14 102	6.73 90	17.81 98	52.15 100	50.94 105	1.56 78	6.43 62	2.92 51	3.14 60	1.46 58	30.14 87	8.43 87	7.23 76	4.28 52	7.08 91	25.69 103	34.50 102	36.15 103	53.30 102	53.30 103

LSM0	22.48 99	6.09 82	4.65 76	14.89 85	10.39 90	16.43 88	13.29 92	23.38 102	15.69 88	14.75 100	18.69 99	35.79 86	33.70 94	0.93 65	73.52 106	85.94 106	13.36 94	5.62 89	55.67 101	16.83 100	21.95 101	18.82 101	4.28 86	8.01 90	16.44 87	16.43 88	28.65 89	32.66 93

BEATNet-Init1	23.62 100	27.86 101	13.22 96	44.78 101	23.54 97	38.58 101	23.96 100	18.57 96	18.15 97	9.17 94	13.26 89	47.63 96	48.00 104	3.29 88	12.31 97	9.22 92	7.35 85	5.48 88	48.70 99	19.34 101	12.33 91	11.24 94	7.11 92	11.28 98	33.76 99	21.63 94	60.52 104	47.50 101

DispFullNet	26.27 101	39.81 102	17.89 103	52.75 102	38.74 102	45.03 102	55.21 103	13.74 88	12.89 84	13.75 99	9.88 85	43.75 94	32.46 92	86.51 106	11.01 94	13.68 100	29.48 103	16.23 103	51.78 100	14.64 95	13.87 94	10.46 92	14.59 99	6.22 85	8.62 75	8.03 67	16.08 81	32.10 91

PSMNet_ROB	31.36 102	48.75 103	16.32 101	64.48 106	46.97 104	60.77 105	61.30 104	19.02 97	20.70 101	27.57 104	24.90 103	41.43 93	42.18 101	83.15 105	13.95 100	4.06 67	17.90 97	5.94 91	42.51 97	15.37 96	11.21 87	9.54 89	57.95 105	14.27 101	29.64 96	19.74 90	29.38 90	17.81 70

PWCK	38.25 103	63.47 106	23.98 104	73.60 107	41.23 103	60.98 106	51.31 102	54.00 105	35.86 104	26.51 103	39.23 104	62.00 103	46.09 102	26.43 102	14.46 101	9.53 93	30.80 104	12.71 100	83.96 105	28.46 104	23.42 102	13.60 100	47.98 103	30.51 104	34.48 101	27.91 101	31.53 92	38.61 98

DPSimNet_ROB	58.77 104	55.98 104	59.21 106	62.88 105	73.92 105	60.20 104	64.84 106	28.34 104	91.63 107	80.59 106	52.65 105	74.49 105	47.24 103	90.64 107	55.91 105	45.99 105	54.62 105	42.30 105	68.03 103	59.25 105	51.18 105	59.54 106	44.54 102	45.19 105	44.85 104	61.56 104	56.15 103	55.05 104

CC-Net-ROB	70.08 105	57.59 105	33.20 105	55.61 103	76.68 106	84.28 107	62.79 105	83.71 107	83.30 106	76.21 105	74.67 106	74.97 106	61.84 106	62.54 104	41.03 104	41.52 104	86.04 106	88.34 107	89.47 106	90.97 106	75.66 106	54.62 105	53.92 104	50.83 106	74.81 106	79.04 106	83.52 107	94.87 108

MADNet++	76.54 106	72.15 107	83.11 107	61.53 104	81.21 107	58.42 103	69.47 107	68.24 106	78.58 105	85.63 107	92.37 107	80.60 107	85.04 107	36.71 103	81.19 107	89.82 107	88.15 107	69.64 106	82.54 104	91.39 107	92.32 107	93.48 107	65.75 106	90.26 107	59.09 105	74.29 105	74.25 105	61.32 105

MEDIAN_ROB	97.56 107	99.08 108	98.39 108	100.00 108	99.99 108	100.00 110	100.00 110	99.49 110	98.31 108	100.00 110	99.95 110	97.97 110	96.05 108	99.97 108	99.41 108	98.43 108	98.53 108	98.66 108	99.88 109	97.95 108	93.38 108	96.45 108	100.00 107	97.23 108	86.96 108	92.33 108	89.80 108	95.90 109

AVERAGE_ROB	98.95 108	100.00 111	99.79 109	100.00 108	100.00 109	100.00 110	100.00 110	100.00 111	100.00 109	100.00 110	100.00 111	100.00 113	100.00 111	100.00 109	99.77 109	99.85 109	100.00 111	100.00 111	100.00 110	100.00 111	98.12 109	99.51 109	100.00 107	100.00 109	93.43 109	93.75 109	94.35 109	93.16 107

DGTPSM_ROB	99.52 109	99.77 109	100.00 110	100.00 108	100.00 109	100.00 110	100.00 110	99.17 108	100.00 109	99.31 108	99.64 109	91.36 108	99.13 109	100.00 109	99.94 110	100.00 110	99.82 109	99.99 109	99.53 107	99.99 109	99.80 111	99.66 110	100.00 107	100.00 109	100.00 110	100.00 110	100.00 110	100.00 110

DPSMNet_ROB	99.53 110	99.78 110	100.00 110	100.00 108	100.00 109	100.00 110	100.00 110	99.17 108	100.00 109	99.31 108	99.63 108	91.42 109	99.14 110	100.00 109	99.94 110	100.00 110	99.82 109	99.99 109	99.62 108	99.99 109	99.79 110	99.66 110	100.00 107	100.00 109	100.00 110	100.00 110	100.00 110	100.00 110

DPSM_ROB	99.92 111	100.00 111	100.00 110	100.00 108	100.00 109	98.97 108	98.99 108	100.00 111	100.00 109	100.00 110	100.00 111	99.90 111	100.00 111	100.00 109	100.00 112	100.00 110	100.00 111	100.00 111	100.00 110	100.00 111	100.00 112	100.00 112	100.00 107	100.00 109	100.00 110	100.00 110	100.00 110	100.00 110

DPSM	99.92 111	100.00 111	100.00 110	100.00 108	100.00 109	98.97 108	98.99 108	100.00 111	100.00 109	100.00 110	100.00 111	99.90 111	100.00 111	100.00 109	100.00 112	100.00 110	100.00 111	100.00 111	100.00 110	100.00 111	100.00 112	100.00 112	100.00 107	100.00 109	100.00 110	100.00 110	100.00 110	100.00 110

STTRV1_RVC		2.31 57	1.06 38	5.61 74	1.39 42	5.42 70	2.59 60	3.68 59	3.77 63	4.47 79	4.40 57	16.44 70	20.14 80	1.02 67	9.83 89	3.26 58	18.06 98	0.81 37		11.45 93	18.05 100	6.27 71		4.23 74	6.12 65	7.90 65	11.99 74	28.90 90

Low-res two-view benchmark