AI Paper Atlas

Research map / 3D vision / Depth and stereo

SC-DepthV3: Robust Self-Supervised Monocular Depth Estimation for Dynamic Scenes

Libo Sun, Jia-Wang Bian, Huangying Zhan, Wei Yin, Ian D. Reid, Chunhua Shen

TPAMI 2023 · 3D vision › Depth and stereo · approach: Self-supervised monocular depth · 119 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 dynamic region refinement (DRR) (ablation)SC-DepthV3 on DDAD · DDAD full imageAbsRel: 0.153 -> 0.142Improved
add local structure refinement (LSR) (ablation)SC-DepthV3 on DDAD · DDAD full imageAbsRel: 0.149 -> 0.142Improved
add dynamic region refinement (DRR) (ablation)SC-DepthV3 on BONN · BONN full imageAbsRel: 0.138 -> 0.126Improved
add local structure refinement (LSR) (ablation)SC-DepthV3 on BONN · BONN full imageAbsRel: 0.130 -> 0.126Improved
add dynamic region refinement (DRR) (ablation)SC-DepthV3 on TUM · TUM full imageAbsRel: 0.185 -> 0.163Improved
add local structure refinement (LSR) (ablation)SC-DepthV3 on TUM · TUM full imageAbsRel: 0.195 -> 0.163Improved
add local structure refinement (LSR) (ablation)SC-DepthV3 on iBims-1 · iBims-1AbsRel: 0.152 -> 0.146Improved
use dynamic-focused sampling instead of random sampling in DRR (ablation)DRR · DDAD full imageAbsRel: 0.154 -> 0.149Improved
use confident depth ranking loss instead of original ranking loss (ablation)DRR · DDAD full imageAbsRel: 0.159 -> 0.149Improved
use normal matching loss instead of edge-aware depth smoothness (ablation)LSR · DDAD full imageAbsRel: 0.148 -> 0.142Improved
do not add random sampling to edge-guided sampling (ablation)LSR · DDAD full imageAbsRel: 0.146 -> 0.142Improved
use LeReS ResNet-101 pseudo-depth instead of DPT (ablation)SC-DepthV3 · DDAD full imageAbsRel: 0.151 -> 0.142Improved

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