Papers › Learning to Recover 3D Scene Shape from a Single Image

Learning to Recover 3D Scene Shape from a Single Image

17 Dec 2020CVPR 2021 1arXiv:2012.09365archive 2025-07-28

Wei Yin, Jianming Zhang, Oliver Wang, Simon Niklaus, Long Mai, Simon Chen, Chunhua Shen

Despite significant progress in monocular depth estimation in the wild, recent state-of-the-art methods cannot be used to recover accurate 3D scene shape due to an unknown depth shift induced by shift-invariant reconstruction losses used in mixed-data depth prediction training, and possible unknown camera focal length. We investigate this problem in detail, and propose a two-stage framework that first predicts depth up to an unknown scale and shift from a single monocular image, and then use 3D point cloud encoders to predict the missing depth shift and focal length that allow us to recover a realistic 3D scene shape. In addition, we propose an image-level normalized regression loss and a normal-based geometry loss to enhance depth prediction models trained on mixed datasets. We test our depth model on nine unseen datasets and achieve state-of-the-art performance on zero-shot dataset generalization. Code is available at: https://git.io/Depth

PaperPDFConference PDFCode

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

Code

aim-uofa/AdelaiDepth officialmentioned on GitHubpytorch 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

3D Scene ReconstructionDepth EstimationDepth PredictionIndoor Monocular Depth EstimationMonocular Depth EstimationSingle-View 3D Reconstruction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Depth Estimation DIODE LeRes Delta < 1.25 0.234 #2 of 2 Archive leaderboard report
Depth Estimation ScanNetV2 LeReS absolute relative error 0.095 #3 of 3 Archive leaderboard report
Indoor Monocular Depth Estimation DIODE LeReS Delta < 1.25^3 0.900 #1 of 2 Archive leaderboard report
Monocular Depth Estimation ETH3D LeReS Delta < 1.25 0.0777 #9 of 10 Archive leaderboard report
Monocular Depth Estimation ETH3D LeReS absolute relative error 0.0171 #9 of 10 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split LeReS Delta < 1.25 0.784 #77 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split LeReS absolute relative error 0.149 #77 of 79 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 LeReS Delta < 1.25 0.916 #39 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 LeReS absolute relative error 0.09 #39 of 85 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