H-Net (Ours)

Reported on 4 benchmarks across 2 tasks · 1 paper · 2 SOTA

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

Computer Vision2 results

Depth EstimationonKITTI 2015
Absolute relative error (AbsRel)· 2021-04-22
0.094
best: 0.076 (H-Net (Ours) Full Eigen)
SOTA
H-Net: Unsupervised Attention-based Stereo Depth Estimation Leveraging Epipolar Geometry arXiv:2104.11288
Depth EstimationonKITTI 2015
Sq Rel· 2021-04-22
0.6
best: 0.607 (H-Net (Ours) Full Eigen)
H-Net: Unsupervised Attention-based Stereo Depth Estimation Leveraging Epipolar Geometry arXiv:2104.11288

Methodology2 results

3DonKITTI 2015
Absolute relative error (AbsRel)· 2021-04-22
0.094
best: 0.076 (H-Net (Ours) Full Eigen)
SOTA
H-Net: Unsupervised Attention-based Stereo Depth Estimation Leveraging Epipolar Geometry arXiv:2104.11288
3DonKITTI 2015
Sq Rel· 2021-04-22
0.6
best: 0.607 (H-Net (Ours) Full Eigen)
H-Net: Unsupervised Attention-based Stereo Depth Estimation Leveraging Epipolar Geometry arXiv:2104.11288