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):

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 Infoalllakes. 1llakes. 1ssand box 1lsand box 1sstora. room 1lstora. room 1sstora. room 2lstora. room 2sstora. room 2 1lstora. room 2 1sstora. room 2 2lstora. room 2 2sstora. room 3lstora. room 3stunnel 1ltunnel 1stunnel 2ltunnel 2stunnel 3ltunnel 3s
sorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
DPM-Stereotwo views1.97
1
0.64
16
2.95
8
0.17
1
0.10
1
4.83
24
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
PMTNettwo views1.99
2
0.32
1
2.21
3
0.39
2
0.23
6
5.08
26
0.49
11
5.84
1
8.22
26
3.07
1
3.29
1
0.73
2
0.75
2
8.18
27
0.94
3
0.00
1
0.00
1
0.00
1
0.00
1
0.03
10
0.00
1
R-Stereotwo views2.44
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
37
17.44
65
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 Traintwo views2.44
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
37
17.44
65
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_ROBtwo views2.69
5
1.40
55
5.34
33
2.31
50
0.75
22
3.14
6
0.06
1
6.11
2
3.87
3
5.34
11
12.18
39
2.34
5
1.22
5
7.84
17
1.48
4
0.03
32
0.00
1
0.00
1
0.00
1
0.35
61
0.03
9
HITNettwo views2.79
6
0.77
17
4.02
19
2.03
39
0.11
3
5.58
30
0.59
14
9.24
11
5.15
7
6.42
16
7.26
11
3.66
6
2.92
16
4.07
4
3.87
28
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
ccstwo views3.04
7
0.39
7
3.08
10
1.78
27
0.52
16
2.04
1
0.50
12
13.09
52
13.71
59
3.54
4
5.36
6
5.50
12
2.45
11
4.81
6
2.88
12
0.09
47
0.08
60
0.12
75
0.10
69
0.20
42
0.50
72
AdaStereotwo views3.09
8
0.58
12
3.04
9
2.84
63
0.48
15
4.08
14
1.29
31
12.16
44
7.77
22
6.03
12
9.62
23
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_4xtwo views3.24
9
1.27
49
5.89
41
1.56
18
0.10
1
5.26
27
1.07
26
10.08
18
5.50
8
6.89
21
7.73
13
4.53
9
4.13
26
5.05
7
5.27
34
0.04
37
0.05
48
0.00
1
0.00
1
0.23
52
0.23
48
DMCAtwo views3.29
10
1.05
33
4.18
22
1.60
21
2.87
69
2.11
2
0.60
15
7.95
7
4.65
6
8.62
32
8.59
19
9.24
31
4.68
33
6.25
8
3.03
14
0.04
37
0.09
64
0.06
69
0.03
50
0.18
39
0.07
18
NOSS_ROBtwo views3.30
11
0.46
8
2.62
4
2.08
40
1.01
34
5.60
31
0.74
22
10.37
25
11.48
48
5.15
9
8.43
18
5.67
13
1.73
8
7.97
19
2.34
9
0.02
23
0.06
54
0.00
1
0.00
1
0.07
20
0.14
39
CFNet_RVCtwo views3.31
12
0.94
28
2.69
5
1.50
16
2.38
59
2.81
4
0.68
20
8.35
8
7.43
18
4.45
6
9.94
24
10.20
37
4.60
31
6.49
9
3.41
22
0.00
1
0.00
1
0.03
60
0.00
1
0.22
48
0.03
9
MLCVtwo views3.44
13
0.88
21
5.60
36
1.39
12
0.25
7
4.36
17
0.33
6
7.25
5
7.28
15
9.17
39
12.24
41
5.09
10
2.47
12
9.15
39
3.23
19
0.00
1
0.00
1
0.00
1
0.00
1
0.10
23
0.02
3
DeepPruner_ROBtwo views3.52
14
1.14
43
4.06
20
1.12
7
1.65
47
3.65
7
0.83
24
13.96
60
4.47
5
7.80
25
10.84
29
7.05
21
2.16
10
8.14
25
3.08
17
0.07
45
0.03
40
0.00
1
0.01
38
0.32
57
0.06
17
STTStereotwo views3.60
15
0.93
27
6.34
48
2.71
61
2.23
58
3.68
10
0.63
19
9.42
12
6.73
11
9.87
46
6.97
9
8.84
30
3.65
19
6.85
10
3.04
15
0.00
1
0.02
35
0.01
43
0.00
1
0.02
4
0.02
3
ccs_robtwo views3.63
16
1.12
42
4.42
24
2.52
54
0.91
30
5.50
29
0.21
4
10.11
21
9.11
32
6.55
19
11.28
33
8.32
28
2.55
13
7.66
14
2.01
8
0.00
1
0.00
1
0.00
1
0.00
1
0.20
42
0.08
21
iResNettwo views3.68
17
0.91
24
7.94
64
2.97
69
0.34
9
4.44
21
0.48
10
7.70
6
9.74
36
7.72
24
12.74
44
4.03
7
2.87
15
8.05
21
3.37
21
0.02
23
0.01
25
0.00
1
0.00
1
0.10
23
0.09
23
CFNettwo views3.72
18
1.10
39
5.03
29
2.49
53
1.59
44
4.90
25
0.22
5
11.38
34
9.88
38
4.80
7
11.25
32
6.44
17
3.68
20
8.33
28
3.00
13
0.00
1
0.00
1
0.00
1
0.00
1
0.22
48
0.07
18
FADNet-RVC-Resampletwo views3.79
19
1.62
66
12.06
77
1.43
14
0.66
18
5.94
33
2.41
39
10.18
23
8.58
30
6.28
14
4.22
3
5.33
11
4.80
37
7.71
15
3.19
18
0.17
59
0.21
80
0.17
81
0.12
71
0.41
69
0.29
60
NLCA_NET_v2_RVCtwo views3.84
20
1.06
34
5.23
31
2.72
62
3.27
72
4.36
17
0.61
16
10.71
30
7.56
19
8.75
33
7.89
14
9.86
36
3.90
23
7.15
12
3.44
23
0.14
54
0.02
35
0.02
54
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-ROBtwo views3.84
20
1.07
35
5.23
31
2.65
58
2.96
70
4.22
15
0.69
21
10.43
26
7.72
20
8.78
34
8.29
17
9.61
34
4.02
25
7.16
13
3.65
26
0.13
53
0.03
40
0.02
54
0.03
50
0.05
15
0.03
9
FADNet_RVCtwo views3.91
22
1.67
69
12.95
84
0.96
6
0.75
22
5.71
32
0.54
13
10.83
32
6.60
10
3.46
2
8.09
15
4.10
8
3.40
18
9.43
42
6.33
38
0.36
75
0.44
92
0.17
81
0.46
95
0.91
85
0.95
89
FADNet-RVCtwo views3.98
23
1.84
75
12.48
80
1.69
25
0.44
13
4.33
16
1.31
32
11.84
38
7.15
13
3.53
3
3.50
2
10.63
40
4.43
30
9.12
38
6.25
37
0.03
32
0.10
65
0.00
1
0.03
50
0.60
75
0.25
54
HSMtwo views4.00
24
0.79
18
3.16
12
1.59
20
2.17
56
6.77
39
1.11
27
12.28
45
6.35
9
6.75
20
8.11
16
13.90
55
5.37
42
8.85
36
2.71
11
0.00
1
0.00
1
0.00
1
0.00
1
0.02
4
0.02
3
TDLMtwo views4.11
25
1.11
41
3.54
14
1.62
22
1.04
35
3.91
12
7.41
82
10.60
29
10.67
42
6.38
15
12.59
43
5.95
15
4.77
35
8.79
35
3.04
15
0.58
87
0.00
1
0.01
43
0.00
1
0.19
41
0.12
34
CBMV_ROBtwo views4.14
26
0.52
9
3.14
11
1.30
10
0.77
25
6.92
40
1.97
38
10.11
21
9.58
34
8.92
36
14.20
52
7.12
22
5.90
45
8.65
32
3.50
25
0.01
18
0.05
48
0.00
1
0.00
1
0.04
13
0.09
23
CVANet_RVCtwo views4.16
27
1.16
44
3.60
15
1.94
37
1.46
42
3.92
13
4.68
64
10.89
33
8.34
28
7.58
23
10.84
29
10.27
38
6.62
49
8.56
31
2.69
10
0.39
77
0.00
1
0.00
1
0.01
38
0.21
47
0.09
23
HSM-Net_RVCpermissivetwo views4.20
28
0.32
1
2.76
6
0.63
3
0.69
20
6.95
41
1.69
36
11.96
39
8.36
29
8.83
35
12.17
38
15.18
63
4.21
28
6.91
11
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_ROBtwo views4.23
29
1.02
31
4.90
28
2.18
43
0.93
32
2.92
5
0.37
8
15.10
71
16.91
73
7.89
27
10.51
27
7.03
19
3.07
17
8.16
26
3.46
24
0.01
18
0.00
1
0.00
1
0.00
1
0.10
23
0.02
3
FADNettwo views4.23
29
1.65
68
11.75
76
1.64
24
0.80
27
4.80
23
0.77
23
13.76
59
11.65
50
3.97
5
5.24
5
9.62
35
5.14
39
8.40
29
3.78
27
0.21
63
0.04
44
0.07
70
0.05
61
1.14
90
0.10
30
iResNetv2_ROBtwo views4.28
31
1.43
56
7.17
59
2.91
64
1.26
39
4.36
17
1.62
34
13.64
58
10.25
41
9.83
45
11.41
34
7.68
24
4.00
24
7.75
16
1.85
6
0.00
1
0.00
1
0.00
1
0.00
1
0.37
63
0.09
23
StereoDRNet-Refinedtwo views4.46
32
0.62
15
3.80
18
1.92
34
0.40
11
9.35
51
0.15
3
10.02
16
8.83
31
12.69
63
11.62
36
9.34
32
3.87
22
8.06
22
8.02
51
0.00
1
0.00
1
0.01
43
0.05
61
0.20
42
0.26
57
Rohan Chabra, Julian Straub, Chris Sweeney, Richard Newcombe, Henry Fuchs: StereoDRNet. CVPR
NVstereo2Dtwo views4.51
33
0.82
19
6.86
57
3.28
74
3.38
76
8.16
46
3.13
44
10.51
27
15.15
64
4.90
8
6.89
8
7.87
25
4.78
36
9.88
45
3.91
29
0.01
18
0.00
1
0.00
1
0.06
63
0.02
4
0.58
77
DLCB_ROBtwo views4.51
33
0.91
24
3.78
17
2.19
44
1.07
36
6.28
34
3.09
43
9.78
15
7.72
20
10.65
50
12.97
45
13.91
56
3.71
21
8.72
33
5.30
35
0.00
1
0.00
1
0.00
1
0.00
1
0.03
10
0.10
30
RASNettwo views4.52
35
0.61
14
4.42
24
3.42
78
4.68
94
4.58
22
0.99
25
9.54
14
8.01
23
5.28
10
11.42
35
10.34
39
8.88
62
9.28
40
8.68
60
0.15
56
0.00
1
0.00
1
0.00
1
0.03
10
0.04
15
SGM-Foresttwo views4.96
36
0.32
1
2.84
7
1.21
8
0.64
17
10.23
61
6.64
77
11.55
35
10.98
43
10.94
53
13.59
48
11.65
46
4.30
29
8.94
37
4.63
32
0.11
50
0.04
44
0.00
1
0.00
1
0.05
15
0.46
69
Johannes L. Schönberger, Sudipta Sinha, Marc Pollefeys: Learning to Fuse Proposals from Multiple Scanline Optimizations in Semi-Global Matching. ECCV 2018
PA-Nettwo views4.98
37
1.47
58
7.42
61
2.40
51
2.14
55
8.73
48
3.64
53
12.42
46
13.11
55
7.03
22
7.57
12
7.88
26
6.52
48
10.16
47
7.82
49
0.02
23
0.03
40
0.00
1
0.00
1
0.11
27
1.07
92
Zhibo Rao, Mingyi He, Yuchao Dai, Zhelun Shen: Patch Attention Network with Generative Adversarial Model for Semi-Supervised Binocular Disparity Prediction.
AANet_RVCtwo views5.01
38
1.74
70
6.38
49
1.96
38
1.29
41
2.26
3
1.69
36
10.07
17
18.53
76
7.88
26
18.15
67
8.49
29
2.70
14
10.59
51
7.04
43
0.96
97
0.15
75
0.02
54
0.00
1
0.13
31
0.12
34
PSMNet_ROBtwo views5.02
39
1.63
67
6.03
43
1.90
33
1.83
52
9.57
55
6.35
74
15.58
76
7.23
14
6.15
13
10.48
26
12.22
48
4.16
27
8.02
20
8.71
61
0.02
23
0.01
25
0.01
43
0.10
69
0.20
42
0.12
34
CBMVpermissivetwo views5.35
40
0.91
24
3.67
16
1.62
22
0.44
13
10.09
59
7.19
81
12.49
47
12.33
54
12.22
59
14.69
54
10.93
41
6.48
47
8.51
30
4.96
33
0.02
23
0.15
75
0.00
1
0.00
1
0.17
38
0.17
43
Konstantinos Batsos, Changjiang Cai, Philippos Mordohai: CBMV: A Coalesced Bidirectional Matching Volume for Disparity Estimation. Computer Vision and Pattern Recognition (CVPR) 2018
StereoDRNettwo views5.59
41
1.75
71
6.80
56
3.12
71
4.45
89
10.61
63
4.35
60
18.80
86
9.73
35
12.22
59
6.87
7
11.44
44
4.65
32
8.09
24
8.26
56
0.02
23
0.11
67
0.00
1
0.03
50
0.20
42
0.28
59
ETE_ROBtwo views5.80
42
1.77
72
6.33
47
1.44
15
0.78
26
6.43
38
6.90
78
12.53
48
8.08
24
12.93
67
14.89
55
21.13
87
5.87
44
9.83
44
6.57
41
0.04
37
0.01
25
0.00
1
0.02
42
0.08
22
0.33
61
DRN-Testtwo views5.87
43
0.98
29
5.89
41
2.69
60
3.65
81
12.37
70
3.35
47
20.07
97
10.20
40
11.93
58
12.31
42
11.06
43
5.31
41
7.89
18
9.05
63
0.04
37
0.05
48
0.04
65
0.04
59
0.18
39
0.25
54
NCCL2two views5.88
44
1.59
64
5.44
34
1.87
30
0.92
31
9.55
54
11.55
96
12.11
41
9.94
39
9.67
44
8.85
21
22.28
89
7.41
53
8.78
34
7.17
44
0.01
18
0.00
1
0.03
60
0.00
1
0.13
31
0.23
48
NaN_ROBtwo views6.00
45
1.24
47
6.29
46
1.34
11
1.68
49
9.60
56
10.31
92
15.09
69
15.79
67
12.62
62
8.95
22
11.67
47
5.83
43
11.78
59
6.41
40
0.05
42
0.13
72
0.08
71
0.20
77
0.22
48
0.79
85
DANettwo views6.02
46
1.23
46
8.45
66
3.86
86
3.94
83
7.64
45
1.34
33
9.51
13
7.00
12
13.39
69
15.53
58
15.99
66
7.02
52
12.14
60
12.37
79
0.19
61
0.12
71
0.02
54
0.03
50
0.13
31
0.56
76
XPNet_ROBtwo views6.03
47
1.22
45
5.61
37
2.56
57
0.90
29
6.32
35
7.07
79
12.92
51
8.30
27
14.76
74
15.13
57
19.84
82
6.66
51
10.36
48
8.58
59
0.02
23
0.04
44
0.00
1
0.03
50
0.11
27
0.24
51
Anonymous Stereotwo views6.16
48
3.15
92
23.75
101
2.97
69
2.48
63
4.39
20
13.30
98
9.21
10
9.86
37
9.56
43
8.76
20
6.79
18
1.99
9
13.50
71
13.04
82
0.01
18
0.05
48
0.00
1
0.06
63
0.22
48
0.19
45
GANettwo views6.22
49
1.07
35
4.07
21
2.27
47
0.89
28
9.19
50
9.52
87
12.02
40
8.13
25
10.72
51
29.09
90
13.86
54
7.52
55
11.00
55
4.39
30
0.36
75
0.00
1
0.02
54
0.02
42
0.12
29
0.08
21
DISCOtwo views6.28
50
0.57
11
5.78
39
3.43
79
1.17
37
11.22
65
3.39
48
12.14
43
16.16
69
6.52
18
11.22
31
16.96
69
6.32
46
19.51
92
10.74
73
0.00
1
0.00
1
0.00
1
0.00
1
0.35
61
0.11
32
RYNettwo views6.34
51
0.89
23
5.88
40
1.41
13
4.48
91
15.97
81
4.18
57
13.41
54
16.49
70
10.81
52
7.00
10
14.33
58
8.72
60
9.43
42
13.71
83
0.00
1
0.01
25
0.00
1
0.00
1
0.02
4
0.07
18
GANetREF_RVCpermissivetwo views6.56
52
2.89
87
7.58
63
3.41
77
0.40
11
12.96
73
9.58
88
15.09
69
17.25
75
10.33
48
10.62
28
12.27
49
8.16
57
12.21
61
4.53
31
0.41
79
0.00
1
0.00
1
0.02
42
3.12
103
0.39
64
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_ROBtwo views6.58
53
1.80
74
6.25
45
1.26
9
0.94
33
10.08
58
9.02
84
16.00
77
11.51
49
12.74
64
13.02
46
24.77
91
5.25
40
10.56
50
8.02
51
0.04
37
0.05
48
0.00
1
0.02
42
0.10
23
0.25
54
DeepPrunerFtwo views6.75
54
2.69
85
23.31
100
3.68
81
7.16
103
3.78
11
4.29
58
13.42
55
20.13
83
8.13
28
10.46
25
7.18
23
8.06
56
11.10
56
9.44
65
0.24
65
0.15
75
0.29
89
0.42
91
0.66
78
0.45
67
edge stereotwo views6.76
55
1.01
30
6.76
55
2.20
45
2.45
62
6.41
37
2.45
40
14.84
67
11.98
53
15.29
75
18.31
68
22.02
88
12.56
76
10.82
52
7.49
45
0.03
32
0.06
54
0.11
74
0.03
50
0.30
54
0.14
39
NCC-stereotwo views6.77
56
1.49
59
6.48
50
2.92
66
4.40
85
7.43
42
3.61
51
19.52
93
13.29
56
8.39
30
16.91
61
15.96
64
12.13
74
12.85
66
7.70
47
1.47
100
0.11
67
0.01
43
0.42
91
0.14
35
0.24
51
Abc-Nettwo views6.77
56
1.49
59
6.48
50
2.92
66
4.40
85
7.43
42
3.61
51
19.52
93
13.29
56
8.39
30
16.91
61
15.96
64
12.13
74
12.85
66
7.70
47
1.47
100
0.11
67
0.01
43
0.42
91
0.14
35
0.24
51
RPtwo views6.84
58
1.29
53
5.53
35
3.92
87
5.18
96
6.32
35
3.53
49
11.73
37
15.31
65
9.54
42
22.38
75
18.25
76
14.47
83
10.11
46
7.49
45
0.91
96
0.01
25
0.12
75
0.15
74
0.33
58
0.19
45
RGCtwo views6.88
59
2.23
81
6.13
44
4.05
88
4.73
95
8.94
49
2.78
42
15.19
73
11.74
51
11.13
54
19.34
70
17.86
73
10.42
69
13.02
68
8.03
53
0.73
90
0.01
25
0.24
88
0.41
90
0.31
56
0.38
63
Nwc_Nettwo views6.97
60
1.25
48
6.63
53
3.82
85
3.37
75
10.83
64
1.67
35
19.56
95
11.35
46
8.36
29
23.62
77
17.19
71
11.44
73
11.21
57
8.08
55
0.80
92
0.00
1
0.00
1
0.02
42
0.13
31
0.09
23
STTRV1_RVCtwo views7.02
61
1.10
39
12.88
82
3.32
75
6.92
102
11.90
69
4.00
55
15.07
68
11.94
52
9.51
40
14.57
53
11.63
45
8.73
61
12.65
65
8.06
54
3.32
106
2.75
106
0.41
97
0.12
71
1.38
95
0.11
32
ADCReftwo views7.27
62
1.38
54
16.37
90
2.52
54
3.30
74
11.63
67
3.16
45
10.80
31
9.35
33
13.03
68
25.27
85
8.17
27
8.92
63
8.06
22
21.81
97
0.15
56
0.08
60
0.16
80
0.34
87
0.38
64
0.58
77
CSANtwo views7.62
63
1.60
65
6.56
52
1.83
28
0.66
18
12.40
71
10.52
94
14.45
64
21.32
85
14.19
71
15.98
60
17.84
72
13.02
80
12.32
62
8.38
57
0.09
47
0.07
58
0.03
60
0.04
59
0.33
58
0.67
83
stereogantwo views7.69
64
0.88
21
7.08
58
3.49
80
3.93
82
18.98
88
3.23
46
16.52
79
19.58
81
9.93
47
18.92
69
20.50
85
9.04
64
14.07
75
6.14
36
0.26
67
0.04
44
0.21
86
0.03
50
0.63
77
0.33
61
pmcnntwo views7.72
65
1.27
49
9.42
69
2.91
64
3.14
71
9.44
52
6.23
71
12.56
49
16.51
71
14.53
72
24.08
79
27.44
97
8.49
58
9.32
41
8.44
58
0.06
44
0.08
60
0.00
1
0.00
1
0.30
54
0.15
41
AF-Nettwo views7.78
66
1.44
57
6.68
54
3.37
76
4.50
92
8.61
47
2.69
41
17.07
82
20.17
84
9.52
41
24.02
78
20.31
84
14.59
84
11.58
58
9.84
70
0.61
88
0.00
1
0.12
75
0.00
1
0.38
64
0.12
34
PASMtwo views7.90
67
4.22
96
21.97
98
3.25
73
3.29
73
5.39
28
6.57
76
10.57
28
19.09
78
12.77
65
13.92
50
18.11
75
9.51
66
13.79
74
10.77
75
0.19
61
0.45
93
0.29
89
1.08
102
1.49
97
1.19
94
PWCDC_ROBbinarytwo views7.92
68
3.17
94
7.48
62
5.73
99
4.40
85
10.45
62
0.35
7
14.52
65
28.19
93
10.36
49
31.27
93
7.04
20
9.14
65
13.22
70
8.78
62
2.74
105
0.02
35
0.00
1
0.00
1
1.31
94
0.17
43
ADCP+two views8.09
69
1.79
73
14.50
88
1.54
17
4.28
84
16.57
83
5.20
66
12.80
50
11.20
45
12.83
66
17.07
63
11.02
42
10.80
71
17.59
88
23.18
100
0.03
32
0.05
48
0.01
43
0.18
75
0.39
68
0.81
86
SuperBtwo views8.10
70
3.15
92
24.67
102
2.65
58
1.23
38
9.88
57
4.29
58
10.18
23
30.07
96
11.53
56
12.18
39
6.12
16
6.65
50
10.50
49
14.47
85
0.14
54
0.11
67
0.35
93
0.25
81
13.06
111
0.48
70
PWC_ROBbinarytwo views8.24
71
3.13
90
12.74
81
2.43
52
4.43
88
7.51
44
1.22
28
16.63
80
19.24
79
16.08
77
28.29
88
13.99
57
10.16
68
13.63
73
14.06
84
0.42
82
0.00
1
0.05
67
0.00
1
0.59
74
0.27
58
MDST_ROBtwo views8.37
72
0.32
1
9.03
67
4.18
91
2.42
61
26.86
100
6.14
69
19.36
90
13.52
58
27.09
98
22.75
76
9.47
33
4.74
34
15.06
80
6.34
39
0.02
23
0.02
35
0.00
1
0.00
1
0.02
4
0.13
38
G-Nettwo views8.41
73
1.54
62
10.97
72
5.73
99
3.60
79
26.19
97
4.41
61
10.10
19
7.42
16
19.71
85
24.99
83
14.38
59
15.83
85
10.99
53
9.53
66
0.50
85
0.46
94
0.19
84
0.25
81
0.80
82
0.66
81
STTStereo_v2two views8.41
73
1.54
62
10.97
72
5.73
99
3.60
79
26.19
97
4.41
61
10.10
19
7.42
16
19.71
85
24.99
83
14.38
59
15.83
85
10.99
53
9.53
66
0.50
85
0.46
94
0.19
84
0.25
81
0.80
82
0.66
81
XQCtwo views8.43
75
3.58
95
16.40
91
2.92
66
2.17
56
13.22
75
3.60
50
14.64
66
25.86
90
11.87
57
12.04
37
15.06
62
10.67
70
15.24
81
19.41
90
0.39
77
0.08
60
0.05
67
0.07
65
0.84
84
0.45
67
FBW_ROBtwo views8.50
76
1.03
32
7.98
65
1.93
36
1.28
40
13.10
74
6.23
71
22.50
101
18.98
77
18.82
82
14.91
56
19.06
79
10.04
67
18.41
89
9.83
69
0.62
89
0.22
81
1.82
107
0.82
100
0.99
88
1.36
96
RTSCtwo views9.15
77
3.00
89
13.57
86
3.72
83
1.76
51
11.82
68
0.46
9
16.95
81
36.83
103
15.80
76
15.53
58
12.91
51
7.46
54
20.01
94
21.76
96
0.31
72
0.13
72
0.01
43
0.08
66
0.57
72
0.41
66
WCMA_ROBtwo views9.21
78
0.87
20
7.37
60
2.54
56
2.13
54
13.59
76
5.80
68
11.64
36
14.01
60
24.43
96
32.99
97
27.09
96
18.02
88
12.51
64
9.85
71
0.81
93
0.07
58
0.01
43
0.01
38
0.16
37
0.23
48
MSMD_ROBtwo views9.28
79
1.09
38
4.65
27
1.58
19
0.39
10
16.52
82
4.41
61
13.60
56
14.87
63
22.34
89
39.89
104
25.67
93
20.71
97
12.42
63
6.98
42
0.34
74
0.03
40
0.00
1
0.00
1
0.05
15
0.09
23
ADCPNettwo views9.54
80
2.39
83
31.46
104
2.09
41
1.60
45
16.71
85
6.39
75
12.11
41
11.45
47
13.53
70
21.45
73
19.41
80
10.94
72
14.38
77
21.54
95
0.27
70
1.16
100
0.39
96
1.49
105
0.58
73
1.45
97
SHDtwo views9.61
81
2.60
84
12.46
79
3.69
82
3.54
78
9.47
53
1.25
29
20.16
98
37.84
106
18.19
81
21.24
72
16.96
69
12.83
79
14.47
79
16.05
87
0.32
73
0.13
72
0.01
43
0.08
66
0.38
64
0.48
70
PDISCO_ROBtwo views9.62
82
1.99
78
11.51
74
9.88
107
9.61
108
21.48
92
3.83
54
19.33
89
28.49
94
11.27
55
14.17
51
19.92
83
5.02
38
16.35
85
9.18
64
5.28
108
0.41
89
0.14
79
0.09
68
2.05
100
2.36
104
MFN_U_SF_DS_RVCtwo views9.78
83
4.27
97
14.47
87
2.29
48
2.85
68
23.40
95
13.62
99
13.60
56
19.54
80
19.42
84
24.27
80
16.74
68
8.59
59
17.05
87
7.98
50
1.25
99
1.68
104
0.17
81
2.63
107
0.72
80
1.04
90
SGM_RVCbinarytwo views10.08
84
0.60
13
3.42
13
2.30
49
0.32
8
19.41
89
6.33
73
18.95
87
14.64
61
25.14
97
24.32
81
33.34
103
18.79
92
19.86
93
12.55
81
0.25
66
0.26
84
0.22
87
0.24
80
0.34
60
0.40
65
Heiko Hirschmueller: Stereo processing by semiglobal matching and mutual information. TPAMI 2008, Volume 30(2), pp. 328-341
DPSNettwo views10.14
85
1.88
77
16.82
92
1.85
29
1.73
50
24.84
96
17.20
108
19.92
96
27.41
92
12.23
61
13.62
49
16.52
67
18.35
89
14.42
78
12.50
80
0.78
91
0.54
98
0.08
71
0.25
81
1.18
91
0.59
80
ADCLtwo views10.16
86
2.11
79
19.36
95
1.92
34
1.88
53
22.23
93
8.91
83
14.04
61
23.56
87
14.62
73
26.19
86
12.75
50
13.59
82
16.06
84
22.95
99
0.26
67
0.18
78
0.75
100
0.65
96
0.69
79
0.58
77
ADCMidtwo views10.24
87
3.13
90
20.70
96
2.21
46
2.39
60
11.23
66
6.19
70
14.17
62
11.19
44
23.20
95
22.25
74
17.89
74
19.54
94
18.51
90
26.21
103
0.45
83
0.42
91
1.10
103
1.29
103
1.56
99
1.18
93
SANettwo views10.64
88
1.86
76
10.91
71
1.76
26
0.71
21
14.62
79
9.23
86
19.18
88
37.14
104
19.22
83
27.96
87
25.86
94
19.11
93
13.02
68
10.63
72
0.08
46
0.06
54
0.03
60
0.02
42
0.62
76
0.81
86
FC-DCNNcopylefttwo views10.72
89
0.52
9
4.27
23
1.88
31
1.63
46
17.18
86
5.29
67
18.20
84
19.69
82
28.50
99
34.51
100
34.03
104
21.48
100
15.89
83
11.15
77
0.03
32
0.01
25
0.02
54
0.01
38
0.07
20
0.09
23
AnyNet_C32two views10.98
90
5.58
99
22.79
99
4.16
89
5.83
98
15.64
80
14.30
100
13.18
53
17.15
74
16.44
79
20.52
71
14.68
61
13.44
81
22.46
96
30.08
108
0.17
59
0.26
84
0.36
94
0.36
88
1.23
92
0.91
88
MeshStereopermissivetwo views11.52
91
1.52
61
4.55
26
1.89
32
1.46
42
19.87
91
5.11
65
20.66
99
15.91
68
32.67
104
34.51
100
39.34
109
21.15
98
18.74
91
12.10
78
0.11
50
0.06
54
0.01
43
0.00
1
0.45
71
0.22
47
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
ADCStwo views13.02
92
4.93
98
28.38
103
3.17
72
2.67
66
13.61
77
10.83
95
18.70
85
33.46
99
22.59
90
24.78
82
19.59
81
18.51
91
23.40
99
32.16
110
0.10
49
0.19
79
0.37
95
0.18
75
1.26
93
1.46
98
MFMNet_retwo views13.29
93
8.60
105
18.29
93
9.75
106
7.25
105
19.65
90
14.84
104
20.71
100
30.72
97
23.03
93
28.77
89
18.85
78
26.09
105
13.55
72
9.82
68
2.44
103
1.35
103
0.34
92
0.23
79
4.78
106
6.69
107
LSMtwo views14.01
94
5.95
100
33.49
105
6.78
104
43.61
113
10.22
60
9.98
91
15.16
72
22.93
86
23.07
94
32.34
96
18.52
77
12.67
77
15.45
82
11.10
76
0.16
58
0.51
97
0.09
73
0.32
85
1.08
89
16.85
112
SAMSARAtwo views14.63
95
2.74
86
12.38
78
12.65
110
6.74
101
36.50
106
72.93
114
19.36
90
23.77
88
16.20
78
13.04
47
29.21
98
12.78
78
16.98
86
15.21
86
0.11
50
0.26
84
0.03
60
0.14
73
0.76
81
0.77
84
SPS-STEREOcopylefttwo views15.04
96
6.23
101
13.21
85
11.34
109
11.65
111
23.30
94
7.15
80
24.16
103
15.65
66
31.78
103
29.19
91
31.62
101
21.32
99
24.62
100
19.50
91
7.59
110
4.19
111
3.22
108
1.48
104
6.99
110
6.54
106
K. Yamaguchi, D. McAllester, R. Urtasun: Efficient Joint Segmentation, Occlusion Labeling, Stereo and Flow Estimation. ECCV 2014
PVDtwo views15.44
97
2.93
88
14.67
89
4.21
92
3.39
77
17.43
87
4.16
56
27.84
108
48.84
111
31.02
102
43.54
108
29.76
100
30.81
108
25.97
102
21.40
94
0.23
64
0.41
89
0.04
65
0.33
86
0.41
69
1.33
95
SGM+DAISYtwo views15.62
98
7.26
104
19.28
94
8.94
105
10.11
110
26.25
99
10.49
93
19.36
90
14.65
62
30.64
101
33.59
98
33.00
102
22.32
101
24.96
101
16.42
88
7.90
111
6.25
112
4.51
109
3.37
108
5.86
108
7.20
108
NVStereoNet_ROBtwo views16.04
99
6.75
102
12.90
83
6.37
103
7.42
106
12.89
72
9.74
89
22.78
102
25.12
89
30.32
100
46.19
110
34.37
105
25.38
103
21.48
95
21.38
93
5.94
109
3.10
109
6.07
110
10.09
112
4.01
104
8.54
110
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_C01two views16.12
100
10.81
109
59.36
110
4.42
93
2.49
64
30.06
102
15.15
106
17.51
83
16.51
71
17.88
80
37.69
103
24.04
90
17.54
87
29.60
105
33.29
111
0.28
71
0.38
87
0.43
98
0.42
91
2.57
102
1.98
100
MSC_U_SF_DS_RVCtwo views16.41
101
6.93
103
21.83
97
5.94
102
2.81
67
38.71
107
14.59
101
24.55
104
34.87
101
33.66
105
34.35
99
29.24
99
24.20
102
22.59
97
17.95
89
2.52
104
2.81
107
1.17
105
1.51
106
5.89
109
2.16
101
ELAS_RVCcopylefttwo views16.54
102
2.26
82
10.09
70
5.50
98
4.46
90
28.28
101
16.72
107
25.55
105
33.54
100
40.19
107
40.30
106
36.68
107
30.03
106
29.40
104
20.61
92
0.98
98
1.21
101
0.86
102
0.70
98
1.39
96
2.16
101
A. Geiger, M. Roser, R. Urtasun: Efficient large-scale stereo matching. ACCV 2010
ELAScopylefttwo views16.72
103
2.14
80
9.23
68
4.92
95
4.53
93
32.66
105
15.11
105
27.40
106
28.68
95
40.27
108
44.90
109
38.33
108
30.50
107
26.44
103
21.94
98
0.88
94
1.23
102
0.67
99
0.89
101
1.49
97
2.18
103
A. Geiger, M. Roser, R. Urtasun: Efficient large-scale stereo matching. ACCV 2010
LE_ROBtwo views16.73
104
1.28
52
11.61
75
3.72
83
1.65
47
16.67
84
9.17
85
14.39
63
55.91
112
63.81
112
40.86
107
35.94
106
37.73
111
14.24
76
26.87
104
0.05
42
0.10
65
0.13
78
0.22
78
0.12
29
0.15
41
SGM-ForestMtwo views16.99
105
1.08
37
5.74
38
2.12
42
0.75
22
31.63
104
12.21
97
27.80
107
32.25
98
37.88
106
39.99
105
52.96
112
35.20
110
33.60
107
24.47
101
0.26
67
0.39
88
0.31
91
0.39
89
0.26
53
0.53
75
DispFullNettwo views17.47
106
26.01
111
33.98
106
22.58
112
20.86
112
13.84
78
1.28
30
16.50
78
26.27
91
19.97
87
17.17
64
20.52
86
18.49
90
22.86
98
10.76
74
5.13
107
2.83
108
30.72
112
7.72
110
20.86
112
11.01
111
RTStwo views18.87
107
9.32
107
86.48
112
4.95
96
6.10
99
42.08
109
14.70
102
15.49
74
41.06
108
22.65
91
32.32
94
13.77
52
19.54
94
37.98
108
28.96
105
0.41
79
0.23
82
0.00
1
0.02
42
0.91
85
0.50
72
RTSAtwo views18.87
107
9.32
107
86.48
112
4.95
96
6.10
99
42.08
109
14.70
102
15.49
74
41.06
108
22.65
91
32.32
94
13.77
52
19.54
94
37.98
108
28.96
105
0.41
79
0.23
82
0.00
1
0.02
42
0.91
85
0.50
72
MANEtwo views19.47
109
1.27
49
5.07
30
4.69
94
5.55
97
30.49
103
9.94
90
34.01
110
37.27
105
44.13
109
51.57
113
52.51
111
40.41
112
33.58
106
24.81
102
0.89
95
0.86
99
1.11
104
9.72
111
0.38
64
1.06
91
BEATNet-Init1two views23.31
110
9.03
106
41.67
107
4.17
90
2.53
65
45.68
111
19.47
109
33.43
109
38.45
107
47.59
111
49.10
111
59.31
113
41.80
113
38.35
110
29.21
107
0.47
84
0.50
96
0.81
101
0.66
97
2.10
101
1.86
99
MADNet+two views27.07
111
33.84
112
90.97
114
20.14
111
7.47
107
48.43
112
47.10
111
35.43
111
36.46
102
20.11
88
30.05
92
25.29
92
35.08
109
45.50
112
50.28
112
2.13
102
2.00
105
1.19
106
0.76
99
4.71
105
4.43
105
PWCKtwo views30.53
112
44.32
113
47.25
109
29.76
113
7.23
104
40.78
108
27.10
110
44.73
112
44.32
110
47.31
110
36.37
102
47.16
110
26.05
104
41.26
111
31.87
109
21.83
112
4.03
110
29.50
111
4.67
109
27.17
113
7.80
109
DPSimNet_ROBtwo views53.45
113
64.73
114
44.39
108
53.97
114
45.39
114
53.66
113
54.83
112
55.15
113
57.87
113
64.16
113
50.83
112
63.40
114
53.34
114
46.45
113
65.81
113
63.13
114
26.54
114
57.94
114
51.11
114
45.52
114
50.69
113
MADNet++two views82.84
114
82.38
115
73.57
111
87.72
115
82.97
115
93.14
114
69.15
113
86.42
114
82.50
114
93.46
114
86.70
114
86.28
115
80.92
115
88.34
114
88.84
114
86.83
115
84.17
115
72.64
115
68.92
115
80.47
115
81.42
114
MEDIAN_ROBtwo views98.41
115
99.70
116
99.30
116
97.09
116
97.02
116
96.89
115
95.77
116
97.66
115
97.28
115
98.79
117
98.94
115
99.18
116
98.14
116
96.89
115
96.88
115
99.96
118
99.16
116
100.00
116
99.99
116
99.69
116
99.88
115
AVERAGE_ROBtwo views99.62
116
99.95
117
98.81
115
100.00
121
100.00
117
98.08
116
95.47
115
100.00
118
100.00
116
100.00
118
100.00
116
100.00
119
100.00
117
100.00
118
99.99
116
100.00
120
100.00
117
100.00
116
100.00
117
100.00
119
100.00
119
DGTPSM_ROBtwo views99.90
117
100.00
118
99.99
117
99.99
119
100.00
117
100.00
117
100.00
117
99.97
116
100.00
116
98.35
115
100.00
116
99.84
117
100.00
117
99.98
116
99.99
116
99.99
119
100.00
117
100.00
116
100.00
117
100.00
119
100.00
119
DPSMNet_ROBtwo views99.91
118
100.00
118
99.99
117
99.99
119
100.00
117
100.00
117
100.00
117
99.98
117
100.00
116
98.35
115
100.00
116
99.84
117
100.00
117
99.98
116
99.99
116
100.00
120
100.00
117
100.00
116
100.00
117
100.00
119
100.00
119
DPSM_ROBtwo views99.95
119
100.00
118
100.00
119
99.76
117
100.00
117
100.00
117
100.00
117
100.00
118
100.00
116
100.00
118
100.00
116
100.00
119
100.00
117
100.00
118
100.00
119
99.21
116
100.00
117
100.00
116
100.00
117
99.99
117
99.95
116
DPSMtwo views99.95
119
100.00
118
100.00
119
99.76
117
100.00
117
100.00
117
100.00
117
100.00
118
100.00
116
100.00
118
100.00
116
100.00
119
100.00
117
100.00
118
100.00
119
99.21
116
100.00
117
100.00
116
100.00
117
99.99
117
99.95
116
LSM0two views100.00
121
100.00
118
100.00
119
100.00
121
100.00
117
100.00
117
100.00
117
100.00
118
100.00
116
100.00
118
100.00
116
100.00
119
100.00
117
100.00
118
100.00
119
100.00
120
100.00
117
100.00
116
100.00
117
100.00
119
99.99
118
MSMDNettwo views1.26
6
FADEtwo views17.27
110
10.46
108
9.90
109
26.54
95
30.62
113
14.22
113
38.39
113
37.63
113
5.22
107