Papers › PlaneDepth: Self-supervised Depth Estimation via Orthogonal Planes

PlaneDepth: Self-supervised Depth Estimation via Orthogonal Planes

4 Oct 2022CVPR 2023 1arXiv:2210.01612archive 2025-07-28

Ruoyu Wang, Zehao Yu, Shenghua Gao

Multiple near frontal-parallel planes based depth representation demonstrated impressive results in self-supervised monocular depth estimation (MDE). Whereas, such a representation would cause the discontinuity of the ground as it is perpendicular to the frontal-parallel planes, which is detrimental to the identification of drivable space in autonomous driving. In this paper, we propose the PlaneDepth, a novel orthogonal planes based presentation, including vertical planes and ground planes. PlaneDepth estimates the depth distribution using a Laplacian Mixture Model based on orthogonal planes for an input image. These planes are used to synthesize a reference view to provide the self-supervision signal. Further, we find that the widely used resizing and cropping data augmentation breaks the orthogonality assumptions, leading to inferior plane predictions. We address this problem by explicitly constructing the resizing cropping transformation to rectify the predefined planes and predicted camera pose. Moreover, we propose an augmented self-distillation loss supervised with a bilateral occlusion mask to boost the robustness of orthogonal planes representation for occlusions. Thanks to our orthogonal planes representation, we can extract the ground plane in an unsupervised manner, which is important for autonomous driving. Extensive experiments on the KITTI dataset demonstrate the effectiveness and efficiency of our method. The code is available at https://github.com/svip-lab/PlaneDepth.

PaperPDFConference PDFCode

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

Code

svip-lab/planedepth officialmentioned in papermentioned on GitHubpytorchNOASSERTION 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

Autonomous DrivingData AugmentationDepth EstimationMonocular Depth Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Monocular Depth Estimation KITTI Eigen split unsupervised PlaneDepth (S + 1280x384) Delta < 1.25 0.911 #2 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised PlaneDepth (S + 1280x384) Delta < 1.25^2 0.968 #2 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised PlaneDepth (S + 1280x384) Delta < 1.25^3 0.984 #2 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised PlaneDepth (S + 1280x384) Mono X #2 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised PlaneDepth (S + 1280x384) RMSE 3.981 #2 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised PlaneDepth (S + 1280x384) RMSE log 0.169 #2 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised PlaneDepth (S + 1280x384) Resolution 1280x384 #2 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised PlaneDepth (S + 1280x384) Sq Rel 0.549 #2 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised PlaneDepth (S + 1280x384) absolute relative error 0.084 #2 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