AI Paper Atlas

Research map / 3D vision / Depth and stereo

Self-supervised Monocular Depth Estimation: Let's Talk About The Weather

Kieran Saunders, George Vogiatzis, Luis J. Manso

ICCV 2023 · 3D vision › Depth and stereo · approach: Self-supervised monocular depth · 59 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
naively train Monodepth2 on weather-augmented data (ablation)Monodepth2 · KITTI sunny testAbs Rel: 0.115 -> 0.118Hurt
naive augmented training on bad-weather test (ablation)Monodepth2 · KITTI bad weatherAbs Rel: 0.249 -> 0.140Improved
train in (unaugmented, augmented) pairs instead of augmented only (ablation)Robust-Depth · KITTI bad weatherAbs Rel: 0.140 -> 0.155Hurt
add semi-augmented depth warping using unaugmented images (ablation)Robust-Depth · KITTI bad weatherAbs Rel: 0.155 -> 0.135Improved
use unaugmented pose for warping augmented images (ablation)Robust-Depth · KITTI bad weatherAbs Rel: 0.155 -> 0.138Improved
add bi-directional pseudo-supervision depth loss L_PS (ablation)Robust-Depth · KITTI bad weatherAbs Rel: 0.155 -> 0.139Improved
add pseudo-supervised pose loss (ablation)Robust-Depth · KITTI bad weatherAbs Rel: 0.155 -> 0.146Improved
combine all components with MonoViT backboneRobust-Depth · NuScenes-NightAbs Rel: 0.313 -> 0.276 (vs MonoViT)Improved
train on weather augmentation then test on sunny/cloudy DrivingStereoRobust-Depth (ResNet18) · DrivingStereo SunnyAbs Rel: 0.177 -> 0.185Hurt
use positional augmentations only (ablation)Robust-Depth · KITTI sunnyAbs Rel: 0.115 -> 0.111Improved
use individual positional augmentation (vertical, tile, erase, scale) alone (ablation)Monodepth2 · KITTI sunnyAbs Rel: 0.120 vertical; 0.117 tile vs 0.115 baselineNo clear effect

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