Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/FeatDepth-MS

FeatDepth-MS

Reported on 14 benchmarks across 2 tasks · 1 paper · 12 SOTA

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

Computer Vision7 results

Depth EstimationonKITTI Eigen split unsupervised
Delta < 1.25· 2020-07-21
0.889
best: 0.94 (SPIdepth)
SOTA
Feature-metric Loss for Self-supervised Learning of Depth and Egomotion arXiv:2007.10603
Depth EstimationonKITTI Eigen split unsupervised
Delta < 1.25^2· 2020-07-21
0.963
best: 0.973 (SPIdepth)
SOTA
Feature-metric Loss for Self-supervised Learning of Depth and Egomotion arXiv:2007.10603
Depth EstimationonKITTI Eigen split unsupervised
Delta < 1.25^3· 2020-07-21
0.982
best: 0.986 (Jasmine)
SOTA
Feature-metric Loss for Self-supervised Learning of Depth and Egomotion arXiv:2007.10603
Depth EstimationonKITTI Eigen split unsupervised
RMSE log· 2020-07-21
0.184
best: 0.153 (SPIdepth)
SOTA
Feature-metric Loss for Self-supervised Learning of Depth and Egomotion arXiv:2007.10603
Depth EstimationonKITTI Eigen split unsupervised
Sq Rel· 2020-07-21
0.697
best: 0.785 (Dyna-DM)
SOTA
Feature-metric Loss for Self-supervised Learning of Depth and Egomotion arXiv:2007.10603
Depth EstimationonKITTI Eigen split unsupervised
absolute relative error· 2020-07-21
0.099
best: 0.071 (SPIdepth)
SOTA
Feature-metric Loss for Self-supervised Learning of Depth and Egomotion arXiv:2007.10603
Depth EstimationonKITTI Eigen split unsupervised
RMSE· 2020-07-21
4.427
best: 3.662 (SPIdepth)
Feature-metric Loss for Self-supervised Learning of Depth and Egomotion arXiv:2007.10603

Methodology7 results

3DonKITTI Eigen split unsupervised
Delta < 1.25· 2020-07-21
0.889
best: 0.94 (SPIdepth)
SOTA
Feature-metric Loss for Self-supervised Learning of Depth and Egomotion arXiv:2007.10603
3DonKITTI Eigen split unsupervised
Delta < 1.25^2· 2020-07-21
0.963
best: 0.973 (SPIdepth)
SOTA
Feature-metric Loss for Self-supervised Learning of Depth and Egomotion arXiv:2007.10603
3DonKITTI Eigen split unsupervised
Delta < 1.25^3· 2020-07-21
0.982
best: 0.986 (Jasmine)
SOTA
Feature-metric Loss for Self-supervised Learning of Depth and Egomotion arXiv:2007.10603
3DonKITTI Eigen split unsupervised
RMSE log· 2020-07-21
0.184
best: 0.153 (SPIdepth)
SOTA
Feature-metric Loss for Self-supervised Learning of Depth and Egomotion arXiv:2007.10603
3DonKITTI Eigen split unsupervised
Sq Rel· 2020-07-21
0.697
best: 0.785 (Dyna-DM)
SOTA
Feature-metric Loss for Self-supervised Learning of Depth and Egomotion arXiv:2007.10603
3DonKITTI Eigen split unsupervised
absolute relative error· 2020-07-21
0.099
best: 0.071 (SPIdepth)
SOTA
Feature-metric Loss for Self-supervised Learning of Depth and Egomotion arXiv:2007.10603
3DonKITTI Eigen split unsupervised
RMSE· 2020-07-21
4.427
best: 3.662 (SPIdepth)
Feature-metric Loss for Self-supervised Learning of Depth and Egomotion arXiv:2007.10603