Research map / 3D vision / Depth and stereo
RA-Depth: Resolution Adaptive Self-Supervised Monocular Depth Estimation
Mu He, Le Hui, Yikai Bian, Jian Ren, Jin Xie, Jian Yang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add arbitrary-scale data augmentation (AS-Aug) (ablation) | Baseline · KITTI at 640x192 | SqRel: 0.866 -> 0.716 | Improved |
| add arbitrary-scale data augmentation (AS-Aug) (ablation) | Baseline · KITTI avg over four test resolutions | SqRel: 1.239 -> 0.730 | Improved |
| add Dual HRNet (ablation) | Baseline · KITTI at 640x192 | SqRel: 0.866 -> 0.746 | Improved |
| add Dual HRNet (ablation) | Baseline · KITTI avg over four test resolutions | SqRel: 1.239 -> 0.994 | Improved |
| add cross-scale depth consistency loss (ablation) | RA-Depth w/o CS-Loss · KITTI at 640x192 | SqRel: 0.732 -> 0.632 | Improved |
| add cross-scale depth consistency loss (ablation) | RA-Depth w/o CS-Loss · KITTI avg over four test resolutions | SqRel: 0.724 -> 0.651 | Improved |
| add Dual HRNet to full model (ablation) | RA-Depth w/o D-HRNet · KITTI at 640x192 | SqRel: 0.651 -> 0.632 | Improved |
| add Dual HRNet to full model (ablation) | RA-Depth w/o D-HRNet · KITTI avg over four test resolutions | RMSElog: 0.177 -> 0.177 | No clear effect |
| use AS-Aug instead of Bian-Aug augmentation (ablation) | Baseline · KITTI avg over four test resolutions | SqRel: 0.847 -> 0.742 | Improved |
| generate three images instead of one with AS-Aug (ablation) | Baseline + AS-Aug · KITTI avg over four test resolutions | SqRel: 0.742 -> 0.730 | Improved |
| add ImageNet pretrained weights to full RA-Depth (ablation) | RA-Depth · KITTI at 640x192 | SqRel: 0.806 -> 0.632 | Improved |
| add RA-Depth components without pretraining (ablation) | Baseline w/o pt · KITTI avg over four test resolutions | SqRel: 2.179 -> 0.856 | Improved |
Later papers that compared with this method
1 later accepted paper reports RA-Depth as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Shading Meets Motion: Self-supervised Indoor 3D Reconstruction Via Simultaneous Shape-from-Shading and Structure-from-Motion (CVPR 2025 · better on 4 of 4 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- HR-Depth: High Resolution Self-Supervised Monocular Depth Estimation (AAAI 2021 · similarity 0.90)
- Digging Into Self-Supervised Monocular Depth Estimation (ICCV 2019 · similarity 0.90)
- High-Precision Self-Supervised Monocular Depth Estimation with Rich-Resource Prior (ECCV 2024 · similarity 0.90)
- Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging (CVPR 2021 · similarity 0.89)
- BRNet: Exploring Comprehensive Features for Monocular Depth Estimation (ECCV 2022 · similarity 0.89)
- A Simple yet Universal Framework for Depth Completion (NeurIPS 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
