This table lists the benchmark results for the low-res two-view scenario. This benchmark evaluates the Middlebury stereo metrics:

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.

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
CBMVtwo views0.19
1
0.14
2
0.17
1
0.18
2
0.10
1
0.20
1
0.11
1
0.29
1
0.30
1
0.29
1
0.30
1
0.30
1
0.23
1
0.27
1
0.19
1
0.13
1
0.15
2
0.17
2
0.16
2
0.10
1
0.10
1
MeshStereopermissivetwo views0.27
2
0.13
1
0.18
2
0.15
1
0.11
2
0.32
2
0.24
2
0.40
2
0.36
2
0.52
2
0.57
2
0.67
3
0.40
2
0.35
2
0.26
2
0.14
2
0.13
1
0.13
1
0.11
1
0.11
2
0.10
1
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
ELAScopylefttwo views0.41
3
0.29
3
0.33
3
0.27
3
0.24
3
0.60
3
0.36
3
0.50
3
0.50
4
0.71
5
0.79
5
0.67
3
0.54
3
0.51
3
0.42
3
0.22
3
0.20
3
0.27
3
0.26
3
0.26
3
0.25
3
A. Geiger, M. Roser, R. Urtasun: Efficient large-scale stereo matching. ACCV 2010
SGM-STEREOtwo views0.56
4
0.57
4
0.65
4
0.40
4
0.54
4
0.66
5
0.49
5
0.56
4
0.45
3
0.66
3
0.69
4
0.67
3
0.56
4
0.63
5
0.56
4
0.59
4
0.48
5
0.50
4
0.50
5
0.52
4
0.58
4
SPS-STEREOcopylefttwo views0.57
5
0.58
5
0.65
4
0.45
5
0.55
5
0.62
4
0.44
4
0.62
5
0.50
4
0.68
4
0.64
3
0.66
2
0.57
5
0.61
4
0.60
5
0.62
5
0.47
4
0.51
5
0.49
4
0.55
5
0.58
4
K. Yamaguchi, D. McAllester, R. Urtasun: Efficient Joint Segmentation, Occlusion Labeling, Stereo and Flow Estimation. ECCV 2014