Spring Dataset and Benchmark Logo

Spring: L. Mehl, J. Schmalfuss, A. Jahedi, Y. Nalivayko, A. Bruhn — University of Stuttgart

RobustSpring: V. Oei, J. Schmalfuss, L. Mehl, M. Bartsch, S. Agnihotri, M. Keuper, A. Bulling, A. Bruhn — University of Stuttgart, University of Mannheim, MPI for Informatics

Not logged in | Login | Create Account

GANet (K)

March 7, 2025, 11:25 a.m.  —  Public

đŸ’¡ submitted by spring team | F. Zhang, V. Prisacariu, R. Yang, and P. HS Torr. "GA-Net: Guided Aggregation Net for End-to-end Stereo Matching." In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019.

 

Stereo

1px
total
1px
low-detail
1px
high-detail
1px
matched
1px
unmatched
1px
not sky
1px
sky
1px
s0-10
1px
s10-40
1px
s40+
27.912 27.732 38.811 25.560 74.617 23.282 98.285 38.298 20.155 31.369
 
Abs
total
Abs
low-detail
Abs
high-detail
Abs
matched
Abs
unmatched
Abs
not sky
Abs
sky
Abs
s0-10
Abs
s10-40
Abs
s40+
5.287 5.283 5.508 4.278 25.314 2.182 52.472 11.075 2.328 3.142
 
D1
total
D1
low-detail
D1
high-detail
D1
matched
D1
unmatched
D1
not sky
D1
sky
D1
s0-10
D1
s10-40
D1
s40+
11.561 11.537 12.979 9.365 55.152 7.363 75.363 18.740 8.314 7.637

Robustness Evaluation (Overall)

1px
total
Abs
total
D1
total
44.710 6.440 10.860

Robustness per Corruption

Robustness Evaluation (Per-Corruption)

Corruption 1px Abs D1
Brightness 12.460 2.480 4.610
Contrast 18.020 2.720 5.490
Saturate 16.690 3.530 5.770
Defocus Blur 41.320 3.290 4.680
Gaussian Blur 47.970 3.550 4.980
Glass Blur 71.450 4.330 5.180
Motion Blur 16.990 2.270 4.260
Zoom Blur 74.290 8.180 14.800
Gaussian Noise 49.200 7.900 13.170
Impulse Noise 51.640 8.180 12.700
Speckle Noise 55.360 7.640 13.630
Shot Noise 49.360 6.950 11.980
Pixelate 62.710 4.000 4.600
JPEG Compression 65.920 7.410 11.190
Elastic Transform 87.380 6.890 8.860
Fog 21.360 9.690 12.450
Frost 39.740 9.840 20.930
Rain 49.080 11.440 22.550
Snow 35.160 11.830 22.940
Spatter 28.000 6.750 12.420
reference frame
Reference Frame
color visualization of disparity 1
Disparity 1 visualization
grayscale visualization of disparity 1 error
Disparity 1 error
reference frame
Reference Frame
color visualization of disparity 1
Disparity 1 visualization
grayscale visualization of disparity 1 error
Disparity 1 error
reference frame
Reference Frame
color visualization of disparity 1
Disparity 1 visualization
grayscale visualization of disparity 1 error
Disparity 1 error
reference frame
Reference Frame
color visualization of disparity 1
Disparity 1 visualization
grayscale visualization of disparity 1 error
Disparity 1 error
reference frame
Reference Frame
color visualization of disparity 1
Disparity 1 visualization
grayscale visualization of disparity 1 error
Disparity 1 error
reference frame
Reference Frame
color visualization of disparity 1
Disparity 1 visualization
grayscale visualization of disparity 1 error
Disparity 1 error
reference frame
Reference Frame
color visualization of disparity 1
Disparity 1 visualization
grayscale visualization of disparity 1 error
Disparity 1 error
reference frame
Reference Frame
color visualization of disparity 1
Disparity 1 visualization
grayscale visualization of disparity 1 error
Disparity 1 error
reference frame
Reference Frame
color visualization of disparity 1
Disparity 1 visualization
grayscale visualization of disparity 1 error
Disparity 1 error
reference frame
Reference Frame
color visualization of disparity 1
Disparity 1 visualization
grayscale visualization of disparity 1 error
Disparity 1 error
Error visualization color code
blue to white to red error visualization color code