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
R-Stereotwo views2.44
1
0.32
1
1.93
1
0.94
2
0.16
2
3.67
6
0.61
12
6.37
2
3.08
1
9.14
27
17.44
53
1.80
1
0.77
1
1.76
1
0.70
1
0.00
1
0.01
23
0.00
1
0.00
1
0.01
1
0.03
7
R-Stereo Traintwo views2.44
1
0.32
1
1.93
1
0.94
2
0.16
2
3.67
6
0.61
12
6.37
2
3.08
1
9.14
27
17.44
53
1.80
1
0.77
1
1.76
1
0.70
1
0.00
1
0.01
23
0.00
1
0.00
1
0.01
1
0.03
7
DN-CSS_ROBtwo views2.69
3
1.40
47
5.34
29
2.31
39
0.75
16
3.14
4
0.06
1
6.11
1
3.87
3
5.34
5
12.18
29
2.34
3
1.22
3
7.84
12
1.48
3
0.03
30
0.00
1
0.00
1
0.00
1
0.35
53
0.03
7
HITNettwo views2.79
4
0.77
13
4.02
17
2.03
30
0.11
1
5.58
22
0.59
11
9.24
9
5.15
5
6.42
10
7.26
4
3.66
4
2.92
14
4.07
3
3.87
22
0.00
1
0.00
1
0.00
1
0.00
1
0.06
15
0.02
2
AdaStereotwo views3.09
5
0.58
10
3.04
7
2.84
50
0.48
11
4.08
11
1.29
23
12.16
33
7.77
14
6.03
7
9.62
13
5.79
8
1.53
5
4.56
4
1.93
5
0.00
1
0.00
1
0.00
1
0.00
1
0.02
4
0.02
2
Xiao Song, Guorun Yang, Xinge Zhu, Hui Zhou, Zhe Wang, Jianping Shi: AdaStereo: A Simple and Efficient Approach for Adaptive Stereo Matching. ArXiv
NOSS_ROBtwo views3.30
6
0.46
6
2.62
3
2.08
31
1.01
27
5.60
23
0.74
17
10.37
16
11.48
37
5.15
4
8.43
9
5.67
7
1.73
6
7.97
14
2.34
8
0.02
21
0.06
48
0.00
1
0.00
1
0.07
16
0.14
33
CFNet_RVCtwo views3.31
7
0.94
23
2.69
4
1.50
12
2.38
50
2.81
2
0.68
15
8.35
6
7.43
10
4.45
1
9.94
14
10.20
28
4.60
25
6.49
5
3.41
17
0.00
1
0.00
1
0.03
56
0.00
1
0.22
41
0.03
7
ccstwo views3.37
8
1.16
37
3.89
16
2.94
55
0.78
19
4.78
18
0.33
5
9.00
7
7.77
14
5.90
6
10.84
19
7.74
18
2.31
9
7.76
11
1.98
6
0.00
1
0.00
1
0.00
1
0.00
1
0.16
31
0.06
13
MLCVtwo views3.44
9
0.88
17
5.60
32
1.39
9
0.25
4
4.36
13
0.33
5
7.25
4
7.28
9
9.17
29
12.24
30
5.09
6
2.47
10
9.15
31
3.23
14
0.00
1
0.00
1
0.00
1
0.00
1
0.10
19
0.02
2
DeepPruner_ROBtwo views3.52
10
1.14
36
4.06
18
1.12
4
1.65
39
3.65
5
0.83
18
13.96
46
4.47
4
7.80
17
10.84
19
7.05
14
2.16
8
8.14
20
3.08
13
0.07
39
0.03
36
0.00
1
0.01
34
0.32
49
0.06
13
ccs_robtwo views3.63
11
1.12
35
4.42
21
2.52
43
0.91
23
5.50
21
0.21
3
10.11
14
9.11
22
6.55
12
11.28
24
8.32
22
2.55
11
7.66
9
2.01
7
0.00
1
0.00
1
0.00
1
0.00
1
0.20
36
0.08
17
iResNettwo views3.68
12
0.91
20
7.94
56
2.97
56
0.34
6
4.44
17
0.48
10
7.70
5
9.74
26
7.72
16
12.74
33
4.03
5
2.87
13
8.05
16
3.37
16
0.02
21
0.01
23
0.00
1
0.00
1
0.10
19
0.09
19
CFNettwo views3.72
13
1.10
32
5.03
25
2.49
42
1.59
36
4.90
19
0.22
4
11.38
24
9.88
28
4.80
2
11.25
23
6.44
10
3.68
16
8.33
22
3.00
11
0.00
1
0.00
1
0.00
1
0.00
1
0.22
41
0.07
15
NLCA_NET_v2_RVCtwo views3.84
14
1.06
27
5.23
27
2.72
49
3.27
58
4.36
13
0.61
12
10.71
21
7.56
11
8.75
23
7.89
6
9.86
27
3.90
19
7.15
7
3.44
18
0.14
47
0.02
32
0.02
50
0.03
46
0.04
10
0.03
7
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
14
1.07
28
5.23
27
2.65
47
2.96
56
4.22
12
0.69
16
10.43
17
7.72
12
8.78
24
8.29
8
9.61
26
4.02
21
7.16
8
3.65
21
0.13
46
0.03
36
0.02
50
0.03
46
0.05
12
0.03
7
HSMtwo views4.00
16
0.79
14
3.16
9
1.59
15
2.17
48
6.77
28
1.11
19
12.28
34
6.35
6
6.75
13
8.11
7
13.90
44
5.37
33
8.85
29
2.71
10
0.00
1
0.00
1
0.00
1
0.00
1
0.02
4
0.02
2
TDLMtwo views4.11
17
1.11
34
3.54
11
1.62
16
1.04
28
3.91
9
7.41
67
10.60
20
10.67
32
6.38
9
12.59
32
5.95
9
4.77
28
8.79
28
3.04
12
0.58
73
0.00
1
0.01
39
0.00
1
0.19
35
0.12
28
CBMV_ROBtwo views4.14
18
0.52
7
3.14
8
1.30
7
0.77
18
6.92
29
1.97
28
10.11
14
9.58
24
8.92
26
14.20
41
7.12
15
5.90
36
8.65
25
3.50
20
0.01
16
0.05
43
0.00
1
0.00
1
0.04
10
0.09
19
CVANet_RVCtwo views4.16
19
1.16
37
3.60
12
1.94
28
1.46
34
3.92
10
4.68
49
10.89
23
8.34
19
7.58
15
10.84
19
10.27
29
6.62
40
8.56
24
2.69
9
0.39
65
0.00
1
0.00
1
0.01
34
0.21
40
0.09
19
HSM-Net_RVCpermissivetwo views4.20
20
0.32
1
2.76
5
0.63
1
0.69
14
6.95
30
1.69
26
11.96
28
8.36
20
8.83
25
12.17
28
15.18
50
4.21
23
6.91
6
3.30
15
0.02
21
0.02
32
0.00
1
0.00
1
0.01
1
0.01
1
Gengshan Yang, Joshua Manela, Michael Happold, and Deva Ramanan: Hierarchical Deep Stereo Matching on High-resolution Images. CVPR 2019
iResNet_ROBtwo views4.23
21
1.02
25
4.90
24
2.18
34
0.93
25
2.92
3
0.37
8
15.10
56
16.91
59
7.89
19
10.51
17
7.03
12
3.07
15
8.16
21
3.46
19
0.01
16
0.00
1
0.00
1
0.00
1
0.10
19
0.02
2
iResNetv2_ROBtwo views4.28
22
1.43
48
7.17
50
2.91
51
1.26
31
4.36
13
1.62
25
13.64
45
10.25
31
9.83
35
11.41
25
7.68
17
4.00
20
7.75
10
1.85
4
0.00
1
0.00
1
0.00
1
0.00
1
0.37
55
0.09
19
StereoDRNet-Refinedtwo views4.46
23
0.62
12
3.80
15
1.92
25
0.40
8
9.35
40
0.15
2
10.02
12
8.83
21
12.69
51
11.62
26
9.34
24
3.87
18
8.06
17
8.02
39
0.00
1
0.00
1
0.01
39
0.05
54
0.20
36
0.26
48
Rohan Chabra, Julian Straub, Chris Sweeney, Richard Newcombe, Henry Fuchs: StereoDRNet. CVPR
NVstereo2Dtwo views4.51
24
0.82
15
6.86
48
3.28
61
3.38
61
8.16
34
3.13
32
10.51
18
15.15
49
4.90
3
6.89
2
7.87
19
4.78
29
9.88
35
3.91
23
0.01
16
0.00
1
0.00
1
0.06
55
0.02
4
0.58
65
DLCB_ROBtwo views4.51
24
0.91
20
3.78
14
2.19
35
1.07
29
6.28
24
3.09
31
9.78
11
7.72
12
10.65
39
12.97
34
13.91
45
3.71
17
8.72
26
5.30
28
0.00
1
0.00
1
0.00
1
0.00
1
0.03
9
0.10
25
SGM-Foresttwo views4.96
26
0.32
1
2.84
6
1.21
5
0.64
12
10.23
49
6.64
62
11.55
25
10.98
33
10.94
42
13.59
37
11.65
35
4.30
24
8.94
30
4.63
26
0.11
43
0.04
40
0.00
1
0.00
1
0.05
12
0.46
59
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
27
1.47
50
7.42
52
2.40
40
2.14
47
8.73
37
3.64
40
12.42
35
13.11
42
7.03
14
7.57
5
7.88
20
6.52
39
10.16
37
7.82
38
0.02
21
0.03
36
0.00
1
0.00
1
0.11
23
1.07
77
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
28
1.74
57
6.38
43
1.96
29
1.29
33
2.26
1
1.69
26
10.07
13
18.53
62
7.88
18
18.15
55
8.49
23
2.70
12
10.59
40
7.04
34
0.96
83
0.15
66
0.02
50
0.00
1
0.13
27
0.12
28
PSMNet_ROBtwo views5.02
29
1.63
56
6.03
38
1.90
24
1.83
44
9.57
44
6.35
59
15.58
61
7.23
8
6.15
8
10.48
16
12.22
37
4.16
22
8.02
15
8.71
47
0.02
21
0.01
23
0.01
39
0.10
62
0.20
36
0.12
28
CBMVpermissivetwo views5.35
30
0.91
20
3.67
13
1.62
16
0.44
10
10.09
47
7.19
66
12.49
36
12.33
41
12.22
47
14.69
43
10.93
30
6.48
38
8.51
23
4.96
27
0.02
21
0.15
66
0.00
1
0.00
1
0.17
33
0.17
36
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
31
1.75
58
6.80
47
3.12
58
4.45
73
10.61
51
4.35
47
18.80
71
9.73
25
12.22
47
6.87
1
11.44
33
4.65
26
8.09
19
8.26
43
0.02
21
0.11
58
0.00
1
0.03
46
0.20
36
0.28
50
ETE_ROBtwo views5.80
32
1.77
59
6.33
42
1.44
11
0.78
19
6.43
27
6.90
63
12.53
37
8.08
16
12.93
55
14.89
44
21.13
72
5.87
35
9.83
34
6.57
32
0.04
33
0.01
23
0.00
1
0.02
39
0.08
18
0.33
51
DRN-Testtwo views5.87
33
0.98
24
5.89
37
2.69
48
3.65
65
12.37
57
3.35
35
20.07
80
10.20
30
11.93
46
12.31
31
11.06
32
5.31
32
7.89
13
9.05
49
0.04
33
0.05
43
0.04
61
0.04
52
0.18
34
0.25
45
NCCL2two views5.88
34
1.59
53
5.44
30
1.87
21
0.92
24
9.55
43
11.55
82
12.11
30
9.94
29
9.67
34
8.85
11
22.28
73
7.41
43
8.78
27
7.17
35
0.01
16
0.00
1
0.03
56
0.00
1
0.13
27
0.23
41
NaN_ROBtwo views6.00
35
1.24
41
6.29
41
1.34
8
1.68
41
9.60
45
10.31
78
15.09
54
15.79
53
12.62
50
8.95
12
11.67
36
5.83
34
11.78
44
6.41
31
0.05
36
0.13
62
0.08
65
0.20
69
0.22
41
0.79
72
DANettwo views6.02
36
1.23
40
8.45
58
3.86
72
3.94
67
7.64
33
1.34
24
9.51
10
7.00
7
13.39
57
15.53
47
15.99
52
7.02
42
12.14
45
12.37
64
0.19
51
0.12
60
0.02
50
0.03
46
0.13
27
0.56
64
XPNet_ROBtwo views6.03
37
1.22
39
5.61
33
2.56
46
0.90
22
6.32
25
7.07
64
12.92
40
8.30
18
14.76
63
15.13
46
19.84
67
6.66
41
10.36
38
8.58
46
0.02
21
0.04
40
0.00
1
0.03
46
0.11
23
0.24
43
Anonymous Stereotwo views6.16
38
3.15
79
23.75
87
2.97
56
2.48
53
4.39
16
13.30
85
9.21
8
9.86
27
9.56
33
8.76
10
6.79
11
1.99
7
13.50
56
13.04
67
0.01
16
0.05
43
0.00
1
0.06
55
0.22
41
0.19
38
GANettwo views6.22
39
1.07
28
4.07
19
2.27
37
0.89
21
9.19
39
9.52
73
12.02
29
8.13
17
10.72
40
29.09
76
13.86
43
7.52
45
11.00
41
4.39
24
0.36
64
0.00
1
0.02
50
0.02
39
0.12
25
0.08
17
DISCOtwo views6.28
40
0.57
9
5.78
35
3.43
66
1.17
30
11.22
52
3.39
36
12.14
32
16.16
55
6.52
11
11.22
22
16.96
55
6.32
37
19.51
77
10.74
58
0.00
1
0.00
1
0.00
1
0.00
1
0.35
53
0.11
26
RYNettwo views6.34
41
0.89
19
5.88
36
1.41
10
4.48
75
15.97
68
4.18
45
13.41
42
16.49
56
10.81
41
7.00
3
14.33
47
8.72
49
9.43
33
13.71
68
0.00
1
0.01
23
0.00
1
0.00
1
0.02
4
0.07
15
GANetREF_RVCpermissivetwo views6.56
42
2.89
74
7.58
55
3.41
65
0.40
8
12.96
60
9.58
74
15.09
54
17.25
61
10.33
37
10.62
18
12.27
38
8.16
47
12.21
46
4.53
25
0.41
67
0.00
1
0.00
1
0.02
39
3.12
89
0.39
54
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
43
1.80
61
6.25
40
1.26
6
0.94
26
10.08
46
9.02
69
16.00
62
11.51
38
12.74
52
13.02
35
24.77
76
5.25
31
10.56
39
8.02
39
0.04
33
0.05
43
0.00
1
0.02
39
0.10
19
0.25
45
DeepPrunerFtwo views6.75
44
2.69
72
23.31
86
3.68
68
7.16
87
3.78
8
4.29
46
13.42
43
20.13
68
8.13
21
10.46
15
7.18
16
8.06
46
11.10
42
9.44
52
0.24
54
0.15
66
0.29
76
0.42
80
0.66
68
0.45
57
NCC-stereotwo views6.77
45
1.49
51
6.48
44
2.92
53
4.40
70
7.43
31
3.61
39
19.52
78
13.29
43
8.39
22
16.91
50
15.96
51
12.13
61
12.85
52
7.70
37
1.47
85
0.11
58
0.01
39
0.42
80
0.14
30
0.24
43
RPtwo views6.84
46
1.29
45
5.53
31
3.92
73
5.18
80
6.32
25
3.53
37
11.73
27
15.31
51
9.54
32
22.38
64
18.25
61
14.47
69
10.11
36
7.49
36
0.91
82
0.01
23
0.12
68
0.15
65
0.33
50
0.19
38
RGCtwo views6.88
47
2.23
67
6.13
39
4.05
74
4.73
78
8.94
38
2.78
30
15.19
58
11.74
39
11.13
43
19.34
58
17.86
58
10.42
57
13.02
53
8.03
41
0.73
76
0.01
23
0.24
75
0.41
79
0.31
48
0.38
53
STTRV1_RVCtwo views7.02
48
1.10
32
12.88
69
3.32
63
6.92
86
11.90
56
4.00
42
15.07
53
11.94
40
9.51
30
14.57
42
11.63
34
8.73
50
12.65
51
8.06
42
3.32
90
2.75
91
0.41
83
0.12
63
1.38
82
0.11
26
ADCReftwo views7.27
49
1.38
46
16.37
76
2.52
43
3.30
60
11.63
54
3.16
33
10.80
22
9.35
23
13.03
56
25.27
70
8.17
21
8.92
51
8.06
17
21.81
81
0.15
48
0.08
53
0.16
72
0.34
76
0.38
56
0.58
65
G-Nettwo views7.46
50
1.62
55
7.42
52
3.29
62
4.87
79
8.46
35
4.04
43
22.30
84
15.26
50
8.01
20
20.02
59
16.77
54
12.97
65
12.54
50
9.11
50
1.75
86
0.08
53
0.01
39
0.19
68
0.24
45
0.25
45
CSANtwo views7.62
51
1.60
54
6.56
45
1.83
19
0.66
13
12.40
58
10.52
80
14.45
50
21.32
71
14.19
59
15.98
49
17.84
57
13.02
66
12.32
47
8.38
44
0.09
41
0.07
51
0.03
56
0.04
52
0.33
50
0.67
70
stereogantwo views7.69
52
0.88
17
7.08
49
3.49
67
3.93
66
18.98
75
3.23
34
16.52
64
19.58
66
9.93
36
18.92
56
20.50
70
9.04
52
14.07
60
6.14
29
0.26
56
0.04
40
0.21
73
0.03
46
0.63
67
0.33
51
pmcnntwo views7.72
53
1.27
42
9.42
61
2.91
51
3.14
57
9.44
41
6.23
56
12.56
38
16.51
57
14.53
61
24.08
67
27.44
83
8.49
48
9.32
32
8.44
45
0.06
38
0.08
53
0.00
1
0.00
1
0.30
47
0.15
34
CF-Nettwo views7.78
54
1.44
49
6.68
46
3.37
64
4.50
76
8.61
36
2.69
29
17.07
67
20.17
69
9.52
31
24.02
66
20.31
69
14.59
70
11.58
43
9.84
55
0.61
74
0.00
1
0.12
68
0.00
1
0.38
56
0.12
28
PASMtwo views7.90
55
4.22
83
21.97
84
3.25
60
3.29
59
5.39
20
6.57
61
10.57
19
19.09
64
12.77
53
13.92
39
18.11
60
9.51
54
13.79
59
10.77
60
0.19
51
0.45
82
0.29
76
1.08
88
1.49
84
1.19
79
PWCDC_ROBbinarytwo views7.92
56
3.17
80
7.48
54
5.73
86
4.40
70
10.45
50
0.35
7
14.52
51
28.19
80
10.36
38
31.27
79
7.04
13
9.14
53
13.22
55
8.78
48
2.74
89
0.02
32
0.00
1
0.00
1
1.31
81
0.17
36
ADCP+two views8.09
57
1.79
60
14.50
73
1.54
13
4.28
69
16.57
70
5.20
51
12.80
39
11.20
35
12.83
54
17.07
51
11.02
31
10.80
59
17.59
72
23.18
84
0.03
30
0.05
43
0.01
39
0.18
66
0.39
60
0.81
73
PWC_ROBbinarytwo views8.24
58
3.13
77
12.74
68
2.43
41
4.43
72
7.51
32
1.22
20
16.63
65
19.24
65
16.08
65
28.29
74
13.99
46
10.16
56
13.63
58
14.06
69
0.42
70
0.00
1
0.05
63
0.00
1
0.59
65
0.27
49
MDST_ROBtwo views8.37
59
0.32
1
9.03
59
4.18
76
2.42
52
26.86
87
6.14
54
19.36
75
13.52
44
27.09
85
22.75
65
9.47
25
4.74
27
15.06
65
6.34
30
0.02
21
0.02
32
0.00
1
0.00
1
0.02
4
0.13
32
XQCtwo views8.43
60
3.58
81
16.40
77
2.92
53
2.17
48
13.22
62
3.60
38
14.64
52
25.86
77
11.87
45
12.04
27
15.06
49
10.67
58
15.24
66
19.41
74
0.39
65
0.08
53
0.05
63
0.07
57
0.84
71
0.45
57
FBW_ROBtwo views8.50
61
1.03
26
7.98
57
1.93
27
1.28
32
13.10
61
6.23
56
22.50
85
18.98
63
18.82
70
14.91
45
19.06
64
10.04
55
18.41
74
9.83
54
0.62
75
0.22
71
1.82
91
0.82
86
0.99
75
1.36
82
RTSCtwo views9.15
62
3.00
76
13.57
72
3.72
70
1.76
43
11.82
55
0.46
9
16.95
66
36.83
88
15.80
64
15.53
47
12.91
40
7.46
44
20.01
79
21.76
80
0.31
61
0.13
62
0.01
39
0.08
58
0.57
63
0.41
56
WCMA_ROBtwo views9.21
63
0.87
16
7.37
51
2.54
45
2.13
46
13.59
63
5.80
53
11.64
26
14.01
45
24.43
83
32.99
83
27.09
82
18.02
72
12.51
49
9.85
56
0.81
79
0.07
51
0.01
39
0.01
34
0.16
31
0.23
41
MSMD_ROBtwo views9.28
64
1.09
31
4.65
23
1.58
14
0.39
7
16.52
69
4.41
48
13.60
44
14.87
48
22.34
76
39.89
90
25.67
78
20.71
82
12.42
48
6.98
33
0.34
63
0.03
36
0.00
1
0.00
1
0.05
12
0.09
19
ADCPNettwo views9.54
65
2.39
69
31.46
89
2.09
32
1.60
37
16.71
72
6.39
60
12.11
30
11.45
36
13.53
58
21.45
62
19.41
65
10.94
60
14.38
62
21.54
79
0.27
59
1.16
86
0.39
82
1.49
91
0.58
64
1.45
83
SHDtwo views9.61
66
2.60
71
12.46
67
3.69
69
3.54
63
9.47
42
1.25
21
20.16
81
37.84
91
18.19
69
21.24
61
16.96
55
12.83
64
14.47
64
16.05
72
0.32
62
0.13
62
0.01
39
0.08
58
0.38
56
0.48
60
PDISCO_ROBtwo views9.62
67
1.99
64
11.51
64
9.88
91
9.61
92
21.48
80
3.83
41
19.33
74
28.49
81
11.27
44
14.17
40
19.92
68
5.02
30
16.35
70
9.18
51
5.28
92
0.41
79
0.14
71
0.09
61
2.05
87
2.36
88
SGM_RVCbinarytwo views10.08
68
0.60
11
3.42
10
2.30
38
0.32
5
19.41
76
6.33
58
18.95
72
14.64
46
25.14
84
24.32
68
33.34
88
18.79
76
19.86
78
12.55
66
0.25
55
0.26
74
0.22
74
0.24
72
0.34
52
0.40
55
Heiko Hirschmueller: Stereo processing by semiglobal matching and mutual information. TPAMI 2008, Volume 30(2), pp. 328-341
DPSNettwo views10.14
69
1.88
63
16.82
78
1.85
20
1.73
42
24.84
85
17.20
94
19.92
79
27.41
79
12.23
49
13.62
38
16.52
53
18.35
73
14.42
63
12.50
65
0.78
77
0.54
84
0.08
65
0.25
73
1.18
78
0.59
68
ADCLtwo views10.16
70
2.11
65
19.36
82
1.92
25
1.88
45
22.23
81
8.91
68
14.04
47
23.56
74
14.62
62
26.19
71
12.75
39
13.59
68
16.06
69
22.95
83
0.26
56
0.18
69
0.75
86
0.65
83
0.69
69
0.58
65
ADCMidtwo views10.24
71
3.13
77
20.70
83
2.21
36
2.39
51
11.23
53
6.19
55
14.17
48
11.19
34
23.20
82
22.25
63
17.89
59
19.54
78
18.51
75
26.21
87
0.45
71
0.42
81
1.10
88
1.29
89
1.56
86
1.18
78
SANettwo views10.64
72
1.86
62
10.91
63
1.76
18
0.71
15
14.62
66
9.23
72
19.18
73
37.14
89
19.22
71
27.96
73
25.86
79
19.11
77
13.02
53
10.63
57
0.08
40
0.06
48
0.03
56
0.02
39
0.62
66
0.81
73
FC-DCNNcopylefttwo views10.72
73
0.52
7
4.27
20
1.88
22
1.63
38
17.18
73
5.29
52
18.20
69
19.69
67
28.50
86
34.51
85
34.03
89
21.48
85
15.89
68
11.15
62
0.03
30
0.01
23
0.02
50
0.01
34
0.07
16
0.09
19
AnyNet_C32two views10.98
74
5.58
85
22.79
85
4.16
75
5.83
82
15.64
67
14.30
87
13.18
41
17.15
60
16.44
67
20.52
60
14.68
48
13.44
67
22.46
81
30.08
92
0.17
50
0.26
74
0.36
80
0.36
77
1.23
79
0.91
75
MeshStereopermissivetwo views11.52
75
1.52
52
4.55
22
1.89
23
1.46
34
19.87
78
5.11
50
20.66
82
15.91
54
32.67
91
34.51
85
39.34
94
21.15
83
18.74
76
12.10
63
0.11
43
0.06
48
0.01
39
0.00
1
0.45
62
0.22
40
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
Nwc_Nettwo views12.96
76
2.43
70
15.29
75
4.46
79
3.56
64
24.49
84
12.36
84
27.85
92
21.14
70
14.50
60
27.22
72
22.84
74
20.00
81
31.34
90
29.17
91
0.78
77
0.12
60
0.00
1
0.01
34
0.95
74
0.63
69
ADCStwo views13.02
77
4.93
84
28.38
88
3.17
59
2.67
55
13.61
64
10.83
81
18.70
70
33.46
85
22.59
77
24.78
69
19.59
66
18.51
75
23.40
83
32.16
94
0.10
42
0.19
70
0.37
81
0.18
66
1.26
80
1.46
84
Abc-Nettwo views13.06
78
3.78
82
19.11
80
4.54
80
4.15
68
20.62
79
14.20
86
27.91
93
21.69
72
19.32
72
39.81
89
25.95
80
23.31
87
17.98
73
15.83
71
0.45
71
0.14
65
0.01
39
0.08
58
1.13
77
1.27
80
MFMNet_retwo views13.29
79
8.60
90
18.29
79
9.75
90
7.25
89
19.65
77
14.84
90
20.71
83
30.72
83
23.03
80
28.77
75
18.85
63
26.09
90
13.55
57
9.82
53
2.44
88
1.35
89
0.34
79
0.23
71
4.78
92
6.69
92
LSMtwo views14.01
80
5.95
86
33.49
90
6.78
88
43.61
98
10.22
48
9.98
77
15.16
57
22.93
73
23.07
81
32.34
82
18.52
62
12.67
62
15.45
67
11.10
61
0.16
49
0.51
83
0.09
67
0.32
74
1.08
76
16.85
97
SAMSARAtwo views14.63
81
2.74
73
12.38
66
12.65
94
6.74
85
36.50
93
72.93
100
19.36
75
23.77
75
16.20
66
13.04
36
29.21
84
12.78
63
16.98
71
15.21
70
0.11
43
0.26
74
0.03
56
0.14
64
0.76
70
0.77
71
SPS-STEREOcopylefttwo views15.04
82
6.23
87
13.21
71
11.34
93
11.65
95
23.30
83
7.15
65
24.16
87
15.65
52
31.78
90
29.19
77
31.62
86
21.32
84
24.62
84
19.50
75
7.59
94
4.19
95
3.22
92
1.48
90
6.99
95
6.54
91
K. Yamaguchi, D. McAllester, R. Urtasun: Efficient Joint Segmentation, Occlusion Labeling, Stereo and Flow Estimation. ECCV 2014
PVDtwo views15.44
83
2.93
75
14.67
74
4.21
77
3.39
62
17.43
74
4.16
44
27.84
91
48.84
95
31.02
89
43.54
94
29.76
85
30.81
93
25.97
86
21.40
78
0.23
53
0.41
79
0.04
61
0.33
75
0.41
61
1.33
81
SGM+DAISYtwo views15.62
84
7.26
89
19.28
81
8.94
89
10.11
94
26.25
86
10.49
79
19.36
75
14.65
47
30.64
88
33.59
84
33.00
87
22.32
86
24.96
85
16.42
73
7.90
95
6.25
96
4.51
93
3.37
92
5.86
94
7.20
93
NVStereoNet_ROBtwo views16.04
85
6.75
88
12.90
70
6.37
87
7.42
90
12.89
59
9.74
75
22.78
86
25.12
76
30.32
87
46.19
96
34.37
90
25.38
88
21.48
80
21.38
77
5.94
93
3.10
93
6.07
94
10.09
96
4.01
90
8.54
95
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
86
10.81
93
59.36
95
4.42
78
2.49
54
30.06
89
15.15
92
17.51
68
16.51
57
17.88
68
37.69
88
24.04
75
17.54
71
29.60
89
33.29
95
0.28
60
0.38
77
0.43
84
0.42
80
2.57
88
1.98
85
ELAS_RVCcopylefttwo views16.54
87
2.26
68
10.09
62
5.50
85
4.46
74
28.28
88
16.72
93
25.55
88
33.54
86
40.19
93
40.30
92
36.68
92
30.03
91
29.40
88
20.61
76
0.98
84
1.21
87
0.86
87
0.70
84
1.39
83
2.16
86
A. Geiger, M. Roser, R. Urtasun: Efficient large-scale stereo matching. ACCV 2010
ELAScopylefttwo views16.72
88
2.14
66
9.23
60
4.92
82
4.53
77
32.66
92
15.11
91
27.40
89
28.68
82
40.27
94
44.90
95
38.33
93
30.50
92
26.44
87
21.94
82
0.88
80
1.23
88
0.67
85
0.89
87
1.49
84
2.18
87
A. Geiger, M. Roser, R. Urtasun: Efficient large-scale stereo matching. ACCV 2010
LE_ROBtwo views16.73
89
1.28
44
11.61
65
3.72
70
1.65
39
16.67
71
9.17
70
14.39
49
55.91
98
63.81
98
40.86
93
35.94
91
37.73
97
14.24
61
26.87
88
0.05
36
0.10
57
0.13
70
0.22
70
0.12
25
0.15
34
SGM-ForestMtwo views16.99
90
1.08
30
5.74
34
2.12
33
0.75
16
31.63
91
12.21
83
27.80
90
32.25
84
37.88
92
39.99
91
52.96
98
35.20
96
33.60
92
24.47
85
0.26
56
0.39
78
0.31
78
0.39
78
0.26
46
0.53
63
DispFullNettwo views17.47
91
26.01
95
33.98
91
22.58
96
20.86
96
13.84
65
1.28
22
16.50
63
26.27
78
19.97
73
17.17
52
20.52
71
18.49
74
22.86
82
10.76
59
5.13
91
2.83
92
30.72
97
7.72
94
20.86
96
11.01
96
RTSAtwo views18.87
92
9.32
91
86.48
98
4.95
83
6.10
83
42.08
95
14.70
88
15.49
59
41.06
92
22.65
78
32.32
80
13.77
41
19.54
78
37.98
93
28.96
89
0.41
67
0.23
72
0.00
1
0.02
39
0.91
72
0.50
61
RTStwo views18.87
92
9.32
91
86.48
98
4.95
83
6.10
83
42.08
95
14.70
88
15.49
59
41.06
92
22.65
78
32.32
80
13.77
41
19.54
78
37.98
93
28.96
89
0.41
67
0.23
72
0.00
1
0.02
39
0.91
72
0.50
61
MANEtwo views19.47
94
1.27
42
5.07
26
4.69
81
5.55
81
30.49
90
9.94
76
34.01
94
37.27
90
44.13
96
51.57
98
52.51
97
40.41
98
33.58
91
24.81
86
0.89
81
0.86
85
1.11
89
9.72
95
0.38
56
1.06
76
FADEtwo views25.68
95
17.27
94
50.60
94
10.46
92
9.90
93
22.50
82
9.17
70
35.80
96
53.05
97
20.32
75
19.01
57
26.54
81
34.42
94
39.35
95
33.52
96
30.62
98
14.22
97
38.39
98
37.63
98
5.22
93
5.56
90
MADNet+two views27.07
96
33.84
96
90.97
100
20.14
95
7.47
91
48.43
97
47.10
96
35.43
95
36.46
87
20.11
74
30.05
78
25.29
77
35.08
95
45.50
97
50.28
98
2.13
87
2.00
90
1.19
90
0.76
85
4.71
91
4.43
89
PWCKtwo views30.53
97
44.32
98
47.25
93
29.76
97
7.23
88
40.78
94
27.10
95
44.73
97
44.32
94
47.31
97
36.37
87
47.16
95
26.05
89
41.26
96
31.87
93
21.83
96
4.03
94
29.50
96
4.67
93
27.17
97
7.80
94
edge stereotwo views42.36
98
35.18
97
61.87
96
36.69
98
34.28
97
64.01
99
49.25
97
49.10
98
51.11
96
41.69
95
62.57
99
47.20
96
43.96
99
46.98
99
45.63
97
23.51
97
25.35
98
23.07
95
25.55
97
40.35
98
39.91
98
DPSimNet_ROBtwo views53.45
99
64.73
99
44.39
92
53.97
99
45.39
99
53.66
98
54.83
98
55.15
99
57.87
99
64.16
99
50.83
97
63.40
99
53.34
100
46.45
98
65.81
99
63.13
99
26.54
99
57.94
99
51.11
99
45.52
99
50.69
99
MADNet++two views82.84
100
82.38
100
73.57
97
87.72
100
82.97
100
93.14
100
69.15
99
86.42
100
82.50
100
93.46
100
86.70
100
86.28
100
80.92
101
88.34
100
88.84
100
86.83
100
84.17
100
72.64
100
68.92
100
80.47
100
81.42
100
MEDIAN_ROBtwo views98.41
101
99.70
101
99.30
102
97.09
101
97.02
101
96.89
101
95.77
102
97.66
101
97.28
101
98.79
103
98.94
101
99.18
101
98.14
102
96.89
101
96.88
101
99.96
103
99.16
101
100.00
101
99.99
101
99.69
101
99.88
101
AVERAGE_ROBtwo views99.62
102
99.95
102
98.81
101
100.00
106
100.00
102
98.08
102
95.47
101
100.00
104
100.00
102
100.00
104
100.00
102
100.00
104
100.00
103
100.00
104
99.99
102
100.00
105
100.00
102
100.00
101
100.00
102
100.00
104
100.00
105
DGTPSM_ROBtwo views99.90
103
100.00
103
99.99
103
99.99
104
100.00
102
100.00
103
100.00
103
99.97
102
100.00
102
98.35
101
100.00
102
99.84
102
100.00
103
99.98
102
99.99
102
99.99
104
100.00
102
100.00
101
100.00
102
100.00
104
100.00
105
DPSMNet_ROBtwo views99.91
104
100.00
103
99.99
103
99.99
104
100.00
102
100.00
103
100.00
103
99.98
103
100.00
102
98.35
101
100.00
102
99.84
102
100.00
103
99.98
102
99.99
102
100.00
105
100.00
102
100.00
101
100.00
102
100.00
104
100.00
105
DPSMtwo views99.95
105
100.00
103
100.00
105
99.76
102
100.00
102
100.00
103
100.00
103
100.00
104
100.00
102
100.00
104
100.00
102
100.00
104
100.00
103
100.00
104
100.00
105
99.21
101
100.00
102
100.00
101
100.00
102
99.99
102
99.95
102
DPSM_ROBtwo views99.95
105
100.00
103
100.00
105
99.76
102
100.00
102
100.00
103
100.00
103
100.00
104
100.00
102
100.00
104
100.00
102
100.00
104
100.00
103
100.00
104
100.00
105
99.21
101
100.00
102
100.00
101
100.00
102
99.99
102
99.95
102
LSM0two views100.00
107
100.00
103
100.00
105
100.00
106
100.00
102
100.00
103
100.00
103
100.00
104
100.00
102
100.00
104
100.00
102
100.00
104
100.00
103
100.00
104
100.00
105
100.00
105
100.00
102
100.00
101
100.00
102
100.00
104
99.99
104
MSMDNettwo views1.26
4