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
sort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysorted bysort bysort bysort bysort by
CF-Nettwo views7.78
53
1.44
48
6.68
46
3.37
63
4.50
76
8.61
36
2.69
29
17.07
66
20.17
68
9.52
30
24.02
64
20.31
68
14.59
69
11.58
43
9.84
54
0.61
74
0.00
1
0.12
68
0.00
1
0.38
56
0.12
27
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
50
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
47
Rohan Chabra, Julian Straub, Chris Sweeney, Richard Newcombe, Henry Fuchs: StereoDRNet. CVPR
TDLMtwo views4.11
17
1.11
33
3.54
11
1.62
16
1.04
28
3.91
9
7.41
66
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
27
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
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
CVANet_RVCtwo views4.16
19
1.16
36
3.60
12
1.94
28
1.46
34
3.92
10
4.68
48
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
ccs_robtwo views3.63
11
1.12
34
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
ccstwo views3.37
8
1.16
36
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
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
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
48
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
64
iResNetv2_ROBtwo views4.28
22
1.43
47
7.17
50
2.91
51
1.26
31
4.36
13
1.62
25
13.64
45
10.25
31
9.83
34
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
GANetREF_RVCpermissivetwo views6.56
42
2.89
73
7.58
55
3.41
64
0.40
8
12.96
59
9.58
72
15.09
53
17.25
60
10.33
36
10.62
18
12.27
37
8.16
47
12.21
46
4.53
25
0.41
67
0.00
1
0.00
1
0.02
39
3.12
88
0.39
53
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
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
43
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
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
GANettwo views6.22
39
1.07
28
4.07
19
2.27
37
0.89
21
9.19
39
9.52
71
12.02
29
8.13
17
10.72
39
29.09
74
13.86
42
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
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
55
16.91
58
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
PWC_ROBbinarytwo views8.24
57
3.13
76
12.74
68
2.43
41
4.43
72
7.51
32
1.22
20
16.63
64
19.24
64
16.08
64
28.29
72
13.99
45
10.16
55
13.63
57
14.06
68
0.42
70
0.00
1
0.05
63
0.00
1
0.59
65
0.27
48
DISCOtwo views6.28
40
0.57
9
5.78
35
3.43
65
1.17
30
11.22
52
3.39
36
12.14
32
16.16
54
6.52
11
11.22
22
16.96
54
6.32
37
19.51
76
10.74
57
0.00
1
0.00
1
0.00
1
0.00
1
0.35
53
0.11
26
DN-CSS_ROBtwo views2.69
3
1.40
46
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
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
38
12.97
34
13.91
44
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
NCCL2two views5.88
34
1.59
52
5.44
30
1.87
21
0.92
24
9.55
43
11.55
80
12.11
30
9.94
29
9.67
33
8.85
11
22.28
72
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
40
RPtwo views6.84
46
1.29
44
5.53
31
3.92
72
5.18
80
6.32
25
3.53
37
11.73
27
15.31
50
9.54
31
22.38
62
18.25
60
14.47
68
10.11
36
7.49
36
0.91
82
0.01
23
0.12
68
0.15
64
0.33
50
0.19
37
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
52
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
ETE_ROBtwo views5.80
32
1.77
58
6.33
42
1.44
11
0.78
19
6.43
27
6.90
62
12.53
37
8.08
16
12.93
54
14.89
43
21.13
71
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
50
FC-DCNNcopylefttwo views10.72
72
0.52
7
4.27
20
1.88
22
1.63
38
17.18
72
5.29
51
18.20
68
19.69
66
28.50
84
34.51
83
34.03
87
21.48
84
15.89
67
11.15
61
0.03
30
0.01
23
0.02
50
0.01
34
0.07
16
0.09
19
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
52
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
RYNettwo views6.34
41
0.89
19
5.88
36
1.41
10
4.48
75
15.97
67
4.18
44
13.41
42
16.49
55
10.81
40
7.00
3
14.33
46
8.72
49
9.43
33
13.71
67
0.00
1
0.01
23
0.00
1
0.00
1
0.02
4
0.07
15
PSMNet_ROBtwo views5.02
29
1.63
55
6.03
38
1.90
24
1.83
44
9.57
44
6.35
58
15.58
60
7.23
8
6.15
8
10.48
16
12.22
36
4.16
22
8.02
15
8.71
46
0.02
21
0.01
23
0.01
39
0.10
62
0.20
36
0.12
27
RGCtwo views6.88
47
2.23
66
6.13
39
4.05
73
4.73
78
8.94
38
2.78
30
15.19
57
11.74
39
11.13
42
19.34
56
17.86
57
10.42
56
13.02
52
8.03
41
0.73
76
0.01
23
0.24
75
0.41
78
0.31
48
0.38
52
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
MDST_ROBtwo views8.37
58
0.32
1
9.03
59
4.18
75
2.42
52
26.86
85
6.14
53
19.36
74
13.52
43
27.09
83
22.75
63
9.47
25
4.74
27
15.06
64
6.34
30
0.02
21
0.02
32
0.00
1
0.00
1
0.02
4
0.13
31
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.
PWCDC_ROBbinarytwo views7.92
55
3.17
79
7.48
54
5.73
85
4.40
70
10.45
50
0.35
7
14.52
51
28.19
79
10.36
37
31.27
77
7.04
13
9.14
52
13.22
54
8.78
47
2.74
89
0.02
32
0.00
1
0.00
1
1.31
81
0.17
35
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
49
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
MSMD_ROBtwo views9.28
63
1.09
31
4.65
23
1.58
14
0.39
7
16.52
68
4.41
47
13.60
44
14.87
47
22.34
74
39.89
88
25.67
77
20.71
81
12.42
48
6.98
33
0.34
63
0.03
36
0.00
1
0.00
1
0.05
12
0.09
19
DeepPruner_ROBtwo views3.52
10
1.14
35
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
PA-Nettwo views4.98
27
1.47
49
7.42
52
2.40
40
2.14
47
8.73
37
3.64
40
12.42
35
13.11
41
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
76
Zhibo Rao, Mingyi He, Yuchao Dai, Zhelun Shen: Patch Attention Network with Generative Adversarial Model for Semi-Supervised Binocular Disparity Prediction.
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
stereogantwo views7.69
51
0.88
17
7.08
49
3.49
66
3.93
66
18.98
74
3.23
34
16.52
63
19.58
65
9.93
35
18.92
55
20.50
69
9.04
51
14.07
59
6.14
29
0.26
56
0.04
40
0.21
73
0.03
46
0.63
67
0.33
50
XPNet_ROBtwo views6.03
37
1.22
38
5.61
33
2.56
46
0.90
22
6.32
25
7.07
63
12.92
40
8.30
18
14.76
62
15.13
45
19.84
66
6.66
41
10.36
38
8.58
45
0.02
21
0.04
40
0.00
1
0.03
46
0.11
23
0.24
42
SGM-Foresttwo views4.96
26
0.32
1
2.84
6
1.21
5
0.64
12
10.23
49
6.64
61
11.55
25
10.98
33
10.94
41
13.59
37
11.65
34
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
58
Johannes L. Schönberger, Sudipta Sinha, Marc Pollefeys: Learning to Fuse Proposals from Multiple Scanline Optimizations in Semi-Global Matching. ECCV 2018
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
Anonymous Stereotwo views6.16
38
3.15
78
23.75
86
2.97
56
2.48
53
4.39
16
13.30
83
9.21
8
9.86
27
9.56
32
8.76
10
6.79
11
1.99
7
13.50
55
13.04
66
0.01
16
0.05
43
0.00
1
0.06
55
0.22
41
0.19
37
DRN-Testtwo views5.87
33
0.98
24
5.89
37
2.69
48
3.65
65
12.37
56
3.35
35
20.07
79
10.20
30
11.93
45
12.31
31
11.06
32
5.31
32
7.89
13
9.05
48
0.04
33
0.05
43
0.04
61
0.04
52
0.18
34
0.25
44
LALA_ROBtwo views6.58
43
1.80
60
6.25
40
1.26
6
0.94
26
10.08
46
9.02
68
16.00
61
11.51
38
12.74
51
13.02
35
24.77
75
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
44
ADCP+two views8.09
56
1.79
59
14.50
72
1.54
13
4.28
69
16.57
69
5.20
50
12.80
39
11.20
35
12.83
53
17.07
50
11.02
31
10.80
58
17.59
71
23.18
83
0.03
30
0.05
43
0.01
39
0.18
65
0.39
60
0.81
72
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
32
SANettwo views10.64
71
1.86
61
10.91
63
1.76
18
0.71
15
14.62
65
9.23
70
19.18
72
37.14
88
19.22
70
27.96
71
25.86
78
19.11
76
13.02
52
10.63
56
0.08
40
0.06
48
0.03
56
0.02
39
0.62
66
0.81
72
MeshStereopermissivetwo views11.52
74
1.52
51
4.55
22
1.89
23
1.46
34
19.87
77
5.11
49
20.66
81
15.91
53
32.67
89
34.51
83
39.34
92
21.15
82
18.74
75
12.10
62
0.11
43
0.06
48
0.01
39
0.00
1
0.45
62
0.22
39
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
WCMA_ROBtwo views9.21
62
0.87
16
7.37
51
2.54
45
2.13
46
13.59
62
5.80
52
11.64
26
14.01
44
24.43
81
32.99
81
27.09
80
18.02
71
12.51
49
9.85
55
0.81
79
0.07
51
0.01
39
0.01
34
0.16
31
0.23
40
CSANtwo views7.62
50
1.60
53
6.56
45
1.83
19
0.66
13
12.40
57
10.52
78
14.45
50
21.32
70
14.19
58
15.98
48
17.84
56
13.02
65
12.32
47
8.38
43
0.09
41
0.07
51
0.03
56
0.04
52
0.33
50
0.67
69
G-Nettwo views7.46
49
1.62
54
7.42
52
3.29
62
4.87
79
8.46
35
4.04
42
22.30
83
15.26
49
8.01
20
20.02
57
16.77
53
12.97
64
12.54
50
9.11
49
1.75
86
0.08
53
0.01
39
0.19
67
0.24
45
0.25
44
pmcnntwo views7.72
52
1.27
41
9.42
61
2.91
51
3.14
57
9.44
41
6.23
55
12.56
38
16.51
56
14.53
60
24.08
65
27.44
81
8.49
48
9.32
32
8.44
44
0.06
38
0.08
53
0.00
1
0.00
1
0.30
47
0.15
33
ADCReftwo views7.27
48
1.38
45
16.37
75
2.52
43
3.30
60
11.63
54
3.16
33
10.80
22
9.35
23
13.03
55
25.27
68
8.17
21
8.92
50
8.06
17
21.81
80
0.15
48
0.08
53
0.16
72
0.34
75
0.38
56
0.58
64
XQCtwo views8.43
59
3.58
80
16.40
76
2.92
53
2.17
48
13.22
61
3.60
38
14.64
52
25.86
76
11.87
44
12.04
27
15.06
48
10.67
57
15.24
65
19.41
73
0.39
65
0.08
53
0.05
63
0.07
57
0.84
71
0.45
56
LE_ROBtwo views16.73
88
1.28
43
11.61
65
3.72
69
1.65
39
16.67
70
9.17
69
14.39
49
55.91
96
63.81
96
40.86
91
35.94
89
37.73
95
14.24
60
26.87
87
0.05
36
0.10
57
0.13
70
0.22
69
0.12
25
0.15
33
NCC-stereotwo views6.77
45
1.49
50
6.48
44
2.92
53
4.40
70
7.43
31
3.61
39
19.52
77
13.29
42
8.39
22
16.91
49
15.96
50
12.13
60
12.85
51
7.70
37
1.47
85
0.11
58
0.01
39
0.42
79
0.14
30
0.24
42
StereoDRNettwo views5.59
31
1.75
57
6.80
47
3.12
58
4.45
73
10.61
51
4.35
46
18.80
70
9.73
25
12.22
46
6.87
1
11.44
33
4.65
26
8.09
19
8.26
42
0.02
21
0.11
58
0.00
1
0.03
46
0.20
36
0.28
49
Nwc_Nettwo views12.96
75
2.43
69
15.29
74
4.46
78
3.56
64
24.49
82
12.36
82
27.85
91
21.14
69
14.50
59
27.22
70
22.84
73
20.00
80
31.34
89
29.17
90
0.78
77
0.12
60
0.00
1
0.01
34
0.95
74
0.63
68
DANettwo views6.02
36
1.23
39
8.45
58
3.86
71
3.94
67
7.64
33
1.34
24
9.51
10
7.00
7
13.39
56
15.53
46
15.99
51
7.02
42
12.14
45
12.37
63
0.19
51
0.12
60
0.02
50
0.03
46
0.13
27
0.56
63
SHDtwo views9.61
65
2.60
70
12.46
67
3.69
68
3.54
63
9.47
42
1.25
21
20.16
80
37.84
90
18.19
68
21.24
59
16.96
54
12.83
63
14.47
63
16.05
71
0.32
62
0.13
62
0.01
39
0.08
58
0.38
56
0.48
59
RTSCtwo views9.15
61
3.00
75
13.57
71
3.72
69
1.76
43
11.82
55
0.46
9
16.95
65
36.83
87
15.80
63
15.53
46
12.91
39
7.46
44
20.01
78
21.76
79
0.31
61
0.13
62
0.01
39
0.08
58
0.57
63
0.41
55
NaN_ROBtwo views6.00
35
1.24
40
6.29
41
1.34
8
1.68
41
9.60
45
10.31
76
15.09
53
15.79
52
12.62
49
8.95
12
11.67
35
5.83
34
11.78
44
6.41
31
0.05
36
0.13
62
0.08
65
0.20
68
0.22
41
0.79
71
Abc-Nettwo views13.06
77
3.78
81
19.11
79
4.54
79
4.15
68
20.62
78
14.20
84
27.91
92
21.69
71
19.32
71
39.81
87
25.95
79
23.31
86
17.98
72
15.83
70
0.45
71
0.14
65
0.01
39
0.08
58
1.13
77
1.27
79
CBMVpermissivetwo views5.35
30
0.91
20
3.67
13
1.62
16
0.44
10
10.09
47
7.19
65
12.49
36
12.33
40
12.22
46
14.69
42
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
35
Konstantinos Batsos, Changjiang Cai, Philippos Mordohai: CBMV: A Coalesced Bidirectional Matching Volume for Disparity Estimation. Computer Vision and Pattern Recognition (CVPR) 2018
AANet_RVCtwo views5.01
28
1.74
56
6.38
43
1.96
29
1.29
33
2.26
1
1.69
26
10.07
13
18.53
61
7.88
18
18.15
54
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
27
DeepPrunerFtwo views6.75
44
2.69
71
23.31
85
3.68
67
7.16
86
3.78
8
4.29
45
13.42
43
20.13
67
8.13
21
10.46
15
7.18
16
8.06
46
11.10
42
9.44
51
0.24
54
0.15
66
0.29
76
0.42
79
0.66
68
0.45
56
ADCLtwo views10.16
69
2.11
64
19.36
81
1.92
25
1.88
45
22.23
80
8.91
67
14.04
47
23.56
73
14.62
61
26.19
69
12.75
38
13.59
67
16.06
68
22.95
82
0.26
56
0.18
69
0.75
85
0.65
82
0.69
69
0.58
64
ADCStwo views13.02
76
4.93
83
28.38
87
3.17
59
2.67
55
13.61
63
10.83
79
18.70
69
33.46
84
22.59
75
24.78
67
19.59
65
18.51
74
23.40
82
32.16
93
0.10
42
0.19
70
0.37
81
0.18
65
1.26
80
1.46
83
FBW_ROBtwo views8.50
60
1.03
26
7.98
57
1.93
27
1.28
32
13.10
60
6.23
55
22.50
84
18.98
62
18.82
69
14.91
44
19.06
63
10.04
54
18.41
73
9.83
53
0.62
75
0.22
71
1.82
90
0.82
85
0.99
75
1.36
81
RTSAtwo views18.87
91
9.32
90
86.48
96
4.95
82
6.10
83
42.08
93
14.70
86
15.49
58
41.06
91
22.65
76
32.32
78
13.77
40
19.54
77
37.98
92
28.96
88
0.41
67
0.23
72
0.00
1
0.02
39
0.91
72
0.50
60
RTStwo views18.87
91
9.32
90
86.48
96
4.95
82
6.10
83
42.08
93
14.70
86
15.49
58
41.06
91
22.65
76
32.32
78
13.77
40
19.54
77
37.98
92
28.96
88
0.41
67
0.23
72
0.00
1
0.02
39
0.91
72
0.50
60
AnyNet_C32two views10.98
73
5.58
84
22.79
84
4.16
74
5.83
82
15.64
66
14.30
85
13.18
41
17.15
59
16.44
66
20.52
58
14.68
47
13.44
66
22.46
80
30.08
91
0.17
50
0.26
74
0.36
80
0.36
76
1.23
79
0.91
74
SGM_RVCbinarytwo views10.08
67
0.60
11
3.42
10
2.30
38
0.32
5
19.41
75
6.33
57
18.95
71
14.64
45
25.14
82
24.32
66
33.34
86
18.79
75
19.86
77
12.55
65
0.25
55
0.26
74
0.22
74
0.24
71
0.34
52
0.40
54
Heiko Hirschmueller: Stereo processing by semiglobal matching and mutual information. TPAMI 2008, Volume 30(2), pp. 328-341
SAMSARAtwo views14.63
80
2.74
72
12.38
66
12.65
92
6.74
85
36.50
91
72.93
98
19.36
74
23.77
74
16.20
65
13.04
36
29.21
82
12.78
62
16.98
70
15.21
69
0.11
43
0.26
74
0.03
56
0.14
63
0.76
70
0.77
70
AnyNet_C01two views16.12
85
10.81
92
59.36
93
4.42
77
2.49
54
30.06
87
15.15
90
17.51
67
16.51
56
17.88
67
37.69
86
24.04
74
17.54
70
29.60
88
33.29
94
0.28
60
0.38
77
0.43
83
0.42
79
2.57
87
1.98
84
SGM-ForestMtwo views16.99
89
1.08
30
5.74
34
2.12
33
0.75
16
31.63
89
12.21
81
27.80
89
32.25
83
37.88
90
39.99
89
52.96
96
35.20
94
33.60
91
24.47
84
0.26
56
0.39
78
0.31
78
0.39
77
0.26
46
0.53
62
PVDtwo views15.44
82
2.93
74
14.67
73
4.21
76
3.39
62
17.43
73
4.16
43
27.84
90
48.84
94
31.02
87
43.54
92
29.76
83
30.81
92
25.97
85
21.40
77
0.23
53
0.41
79
0.04
61
0.33
74
0.41
61
1.33
80
PDISCO_ROBtwo views9.62
66
1.99
63
11.51
64
9.88
90
9.61
91
21.48
79
3.83
41
19.33
73
28.49
80
11.27
43
14.17
40
19.92
67
5.02
30
16.35
69
9.18
50
5.28
91
0.41
79
0.14
71
0.09
61
2.05
86
2.36
87
ADCMidtwo views10.24
70
3.13
76
20.70
82
2.21
36
2.39
51
11.23
53
6.19
54
14.17
48
11.19
34
23.20
80
22.25
61
17.89
58
19.54
77
18.51
74
26.21
86
0.45
71
0.42
81
1.10
87
1.29
88
1.56
85
1.18
77
PASMtwo views7.90
54
4.22
82
21.97
83
3.25
60
3.29
59
5.39
20
6.57
60
10.57
19
19.09
63
12.77
52
13.92
39
18.11
59
9.51
53
13.79
58
10.77
59
0.19
51
0.45
82
0.29
76
1.08
87
1.49
83
1.19
78
LSMtwo views14.01
79
5.95
85
33.49
89
6.78
87
43.61
96
10.22
48
9.98
75
15.16
56
22.93
72
23.07
79
32.34
80
18.52
61
12.67
61
15.45
66
11.10
60
0.16
49
0.51
83
0.09
67
0.32
73
1.08
76
16.85
95
DPSNettwo views10.14
68
1.88
62
16.82
77
1.85
20
1.73
42
24.84
83
17.20
92
19.92
78
27.41
78
12.23
48
13.62
38
16.52
52
18.35
72
14.42
62
12.50
64
0.78
77
0.54
84
0.08
65
0.25
72
1.18
78
0.59
67
MANEtwo views19.47
93
1.27
41
5.07
26
4.69
80
5.55
81
30.49
88
9.94
74
34.01
93
37.27
89
44.13
94
51.57
96
52.51
95
40.41
96
33.58
90
24.81
85
0.89
81
0.86
85
1.11
88
9.72
94
0.38
56
1.06
75
ADCPNettwo views9.54
64
2.39
68
31.46
88
2.09
32
1.60
37
16.71
71
6.39
59
12.11
30
11.45
36
13.53
57
21.45
60
19.41
64
10.94
59
14.38
61
21.54
78
0.27
59
1.16
86
0.39
82
1.49
90
0.58
64
1.45
82
ELAS_RVCcopylefttwo views16.54
86
2.26
67
10.09
62
5.50
84
4.46
74
28.28
86
16.72
91
25.55
87
33.54
85
40.19
91
40.30
90
36.68
90
30.03
90
29.40
87
20.61
75
0.98
84
1.21
87
0.86
86
0.70
83
1.39
82
2.16
85
A. Geiger, M. Roser, R. Urtasun: Efficient large-scale stereo matching. ACCV 2010
ELAScopylefttwo views16.72
87
2.14
65
9.23
60
4.92
81
4.53
77
32.66
90
15.11
89
27.40
88
28.68
81
40.27
92
44.90
93
38.33
91
30.50
91
26.44
86
21.94
81
0.88
80
1.23
88
0.67
84
0.89
86
1.49
83
2.18
86
A. Geiger, M. Roser, R. Urtasun: Efficient large-scale stereo matching. ACCV 2010
MFMNet_retwo views13.29
78
8.60
89
18.29
78
9.75
89
7.25
88
19.65
76
14.84
88
20.71
82
30.72
82
23.03
78
28.77
73
18.85
62
26.09
89
13.55
56
9.82
52
2.44
88
1.35
89
0.34
79
0.23
70
4.78
91
6.69
90
MADNet+two views27.07
94
33.84
94
90.97
98
20.14
93
7.47
90
48.43
95
47.10
94
35.43
94
36.46
86
20.11
73
30.05
76
25.29
76
35.08
93
45.50
95
50.28
96
2.13
87
2.00
90
1.19
89
0.76
84
4.71
90
4.43
88
DispFullNettwo views17.47
90
26.01
93
33.98
90
22.58
94
20.86
94
13.84
64
1.28
22
16.50
62
26.27
77
19.97
72
17.17
51
20.52
70
18.49
73
22.86
81
10.76
58
5.13
90
2.83
91
30.72
96
7.72
93
20.86
94
11.01
94
NVStereoNet_ROBtwo views16.04
84
6.75
87
12.90
69
6.37
86
7.42
89
12.89
58
9.74
73
22.78
85
25.12
75
30.32
85
46.19
94
34.37
88
25.38
87
21.48
79
21.38
76
5.94
92
3.10
92
6.07
93
10.09
95
4.01
89
8.54
93
Nikolai Smolyanskiy, Alexey Kamenev, Stan Birchfield: On the Importance of Stereo for Accurate Depth Estimation: An Efficient Semi-Supervised Deep Neural Network Approach. Arxiv
PWCKtwo views30.53
95
44.32
96
47.25
92
29.76
95
7.23
87
40.78
92
27.10
93
44.73
95
44.32
93
47.31
95
36.37
85
47.16
93
26.05
88
41.26
94
31.87
92
21.83
95
4.03
93
29.50
95
4.67
92
27.17
95
7.80
92
SPS-STEREOcopylefttwo views15.04
81
6.23
86
13.21
70
11.34
91
11.65
93
23.30
81
7.15
64
24.16
86
15.65
51
31.78
88
29.19
75
31.62
84
21.32
83
24.62
83
19.50
74
7.59
93
4.19
94
3.22
91
1.48
89
6.99
93
6.54
89
K. Yamaguchi, D. McAllester, R. Urtasun: Efficient Joint Segmentation, Occlusion Labeling, Stereo and Flow Estimation. ECCV 2014
SGM+DAISYtwo views15.62
83
7.26
88
19.28
80
8.94
88
10.11
92
26.25
84
10.49
77
19.36
74
14.65
46
30.64
86
33.59
82
33.00
85
22.32
85
24.96
84
16.42
72
7.90
94
6.25
95
4.51
92
3.37
91
5.86
92
7.20
91
edge stereotwo views42.36
96
35.18
95
61.87
94
36.69
96
34.28
95
64.01
97
49.25
95
49.10
96
51.11
95
41.69
93
62.57
97
47.20
94
43.96
97
46.98
97
45.63
95
23.51
96
25.35
96
23.07
94
25.55
96
40.35
96
39.91
96
DPSimNet_ROBtwo views53.45
97
64.73
97
44.39
91
53.97
97
45.39
97
53.66
96
54.83
96
55.15
97
57.87
97
64.16
97
50.83
95
63.40
97
53.34
98
46.45
96
65.81
97
63.13
97
26.54
97
57.94
97
51.11
97
45.52
97
50.69
97
MADNet++two views82.84
98
82.38
98
73.57
95
87.72
98
82.97
98
93.14
98
69.15
97
86.42
98
82.50
98
93.46
98
86.70
98
86.28
98
80.92
99
88.34
98
88.84
98
86.83
98
84.17
98
72.64
98
68.92
98
80.47
98
81.42
98
MEDIAN_ROBtwo views98.41
99
99.70
99
99.30
100
97.09
99
97.02
99
96.89
99
95.77
100
97.66
99
97.28
99
98.79
101
98.94
99
99.18
99
98.14
100
96.89
99
96.88
99
99.96
101
99.16
99
100.00
99
99.99
99
99.69
99
99.88
99
DPSMNet_ROBtwo views99.91
102
100.00
101
99.99
101
99.99
102
100.00
100
100.00
101
100.00
101
99.98
101
100.00
100
98.35
99
100.00
100
99.84
100
100.00
101
99.98
100
99.99
100
100.00
103
100.00
100
100.00
99
100.00
100
100.00
102
100.00
103
LSM0two views100.00
105
100.00
101
100.00
103
100.00
104
100.00
100
100.00
101
100.00
101
100.00
102
100.00
100
100.00
102
100.00
100
100.00
102
100.00
101
100.00
102
100.00
103
100.00
103
100.00
100
100.00
99
100.00
100
100.00
102
99.99
102
AVERAGE_ROBtwo views99.62
100
99.95
100
98.81
99
100.00
104
100.00
100
98.08
100
95.47
99
100.00
102
100.00
100
100.00
102
100.00
100
100.00
102
100.00
101
100.00
102
99.99
100
100.00
103
100.00
100
100.00
99
100.00
100
100.00
102
100.00
103
DGTPSM_ROBtwo views99.90
101
100.00
101
99.99
101
99.99
102
100.00
100
100.00
101
100.00
101
99.97
100
100.00
100
98.35
99
100.00
100
99.84
100
100.00
101
99.98
100
99.99
100
99.99
102
100.00
100
100.00
99
100.00
100
100.00
102
100.00
103
DPSMtwo views99.95
103
100.00
101
100.00
103
99.76
100
100.00
100
100.00
101
100.00
101
100.00
102
100.00
100
100.00
102
100.00
100
100.00
102
100.00
101
100.00
102
100.00
103
99.21
99
100.00
100
100.00
99
100.00
100
99.99
100
99.95
100
DPSM_ROBtwo views99.95
103
100.00
101
100.00
103
99.76
100
100.00
100
100.00
101
100.00
101
100.00
102
100.00
100
100.00
102
100.00
100
100.00
102
100.00
101
100.00
102
100.00
103
99.21
99
100.00
100
100.00
99
100.00
100
99.99
100
99.95
100
MSMDNettwo views1.26
4