Papers › Auto-Rectify Network for Unsupervised Indoor Depth Estimation
Auto-Rectify Network for Unsupervised Indoor Depth Estimation
Jia-Wang Bian, Huangying Zhan, Naiyan Wang, Tat-Jun Chin, Chunhua Shen, Ian Reid
Single-View depth estimation using the CNNs trained from unlabelled videos has shown significant promise. However, excellent results have mostly been obtained in street-scene driving scenarios, and such methods often fail in other settings, particularly indoor videos taken by handheld devices. In this work, we establish that the complex ego-motions exhibited in handheld settings are a critical obstacle for learning depth. Our fundamental analysis suggests that the rotation behaves as noise during training, as opposed to the translation (baseline) which provides supervision signals. To address the challenge, we propose a data pre-processing method that rectifies training images by removing their relative rotations for effective learning. The significantly improved performance validates our motivation. Towards end-to-end learning without requiring pre-processing, we propose an Auto-Rectify Network with novel loss functions, which can automatically learn to rectify images during training. Consequently, our results outperform the previous unsupervised SOTA method by a large margin on the challenging NYUv2 dataset. We also demonstrate the generalization of our trained model in ScanNet and Make3D, and the universality of our proposed learning method on 7-Scenes and KITTI datasets.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Monocular Depth Estimation | NYU-Depth V2 | SC-DepthV2 | Delta < 1.25 | 0.820 | #59 of 85 | Archive leaderboard | report |
| Monocular Depth Estimation | NYU-Depth V2 | SC-DepthV2 | Delta < 1.25^2 | 0.956 | #59 of 85 | Archive leaderboard | report |
| Monocular Depth Estimation | NYU-Depth V2 | SC-DepthV2 | RMSE | 0.532 | #59 of 85 | Archive leaderboard | report |
| Monocular Depth Estimation | NYU-Depth V2 | SC-DepthV2 | absolute relative error | 0.138 | #59 of 85 | Archive leaderboard | report |
| Monocular Depth Estimation | NYU-Depth V2 | SC-DepthV2 | log 10 | 0.059 | #59 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