AI Paper Atlas

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

ECCV 2022 · 3D vision › Depth and stereo · approach: Self-supervised monocular depth · 86 citations (OpenAlex)

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 changedWhereMeasuredEffect
add arbitrary-scale data augmentation (AS-Aug) (ablation)Baseline · KITTI at 640x192SqRel: 0.866 -> 0.716Improved
add arbitrary-scale data augmentation (AS-Aug) (ablation)Baseline · KITTI avg over four test resolutionsSqRel: 1.239 -> 0.730Improved
add Dual HRNet (ablation)Baseline · KITTI at 640x192SqRel: 0.866 -> 0.746Improved
add Dual HRNet (ablation)Baseline · KITTI avg over four test resolutionsSqRel: 1.239 -> 0.994Improved
add cross-scale depth consistency loss (ablation)RA-Depth w/o CS-Loss · KITTI at 640x192SqRel: 0.732 -> 0.632Improved
add cross-scale depth consistency loss (ablation)RA-Depth w/o CS-Loss · KITTI avg over four test resolutionsSqRel: 0.724 -> 0.651Improved
add Dual HRNet to full model (ablation)RA-Depth w/o D-HRNet · KITTI at 640x192SqRel: 0.651 -> 0.632Improved
add Dual HRNet to full model (ablation)RA-Depth w/o D-HRNet · KITTI avg over four test resolutionsRMSElog: 0.177 -> 0.177No clear effect
use AS-Aug instead of Bian-Aug augmentation (ablation)Baseline · KITTI avg over four test resolutionsSqRel: 0.847 -> 0.742Improved
generate three images instead of one with AS-Aug (ablation)Baseline + AS-Aug · KITTI avg over four test resolutionsSqRel: 0.742 -> 0.730Improved
add ImageNet pretrained weights to full RA-Depth (ablation)RA-Depth · KITTI at 640x192SqRel: 0.806 -> 0.632Improved
add RA-Depth components without pretraining (ablation)Baseline w/o pt · KITTI avg over four test resolutionsSqRel: 2.179 -> 0.856Improved

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy