H-Net (Ours) Full Eigen

Reported on 6 benchmarks across 2 tasks · 1 paper · 6 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision3 results

Depth EstimationonKITTI 2015
Absolute relative error (AbsRel)· 2021-04-22
0.076
SOTA
H-Net: Unsupervised Attention-based Stereo Depth Estimation Leveraging Epipolar Geometry arXiv:2104.11288
Depth EstimationonKITTI 2015
RMSE· 2021-04-22
0.04025
SOTA
H-Net: Unsupervised Attention-based Stereo Depth Estimation Leveraging Epipolar Geometry arXiv:2104.11288
Depth EstimationonKITTI 2015
Sq Rel· 2021-04-22
0.607
SOTA
H-Net: Unsupervised Attention-based Stereo Depth Estimation Leveraging Epipolar Geometry arXiv:2104.11288

Methodology3 results

3DonKITTI 2015
Absolute relative error (AbsRel)· 2021-04-22
0.076
SOTA
H-Net: Unsupervised Attention-based Stereo Depth Estimation Leveraging Epipolar Geometry arXiv:2104.11288
3DonKITTI 2015
RMSE· 2021-04-22
0.04025
SOTA
H-Net: Unsupervised Attention-based Stereo Depth Estimation Leveraging Epipolar Geometry arXiv:2104.11288
3DonKITTI 2015
Sq Rel· 2021-04-22
0.607
SOTA
H-Net: Unsupervised Attention-based Stereo Depth Estimation Leveraging Epipolar Geometry arXiv:2104.11288