Papers › Feature-metric Loss for Self-supervised Learning of Depth and Egomotion

Feature-metric Loss for Self-supervised Learning of Depth and Egomotion

21 Jul 2020ECCV 2020 8arXiv:2007.10603archive 2025-07-28

Chang Shu, Kun Yu, Zhixiang Duan, Kuiyuan Yang

Photometric loss is widely used for self-supervised depth and egomotion estimation. However, the loss landscapes induced by photometric differences are often problematic for optimization, caused by plateau landscapes for pixels in textureless regions or multiple local minima for less discriminative pixels. In this work, feature-metric loss is proposed and defined on feature representation, where the feature representation is also learned in a self-supervised manner and regularized by both first-order and second-order derivatives to constrain the loss landscapes to form proper convergence basins. Comprehensive experiments and detailed analysis via visualization demonstrate the effectiveness of the proposed feature-metric loss. In particular, our method improves state-of-the-art methods on KITTI from 0.885 to 0.925 measured by δ₁ for depth estimation, and significantly outperforms previous method for visual odometry.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

sconlyshootery/FeatDepth officialmentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Depth EstimationMonocular Depth EstimationSelf-Supervised LearningVisual Odometry

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Monocular Depth Estimation KITTI Eigen split unsupervised FeatDepth-MS Delta < 1.25 0.889 #26 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised FeatDepth-MS Delta < 1.25^2 0.963 #26 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised FeatDepth-MS Delta < 1.25^3 0.982 #26 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised FeatDepth-MS RMSE 4.427 #26 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised FeatDepth-MS RMSE log 0.184 #26 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised FeatDepth-MS Sq Rel 0.697 #26 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised FeatDepth-MS absolute relative error 0.099 #26 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised FeatDepth-M absolute relative error 0.104 #35 of 55 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections