AI Paper Atlas

Research map / 3D vision / Depth and stereo

Instance-Level Video Depth in Groups Beyond Occlusions

Yuan Liang, Yang Zhou, Ziming Sun, Tianyi Xiang, Guiqing Li, Shengfeng He

ICCV 2025 · 3D vision › Depth and stereo · approach: Self-supervised monocular depth · 0 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 Holistic Depth Initialization (ablation)DepthAnything V2 + DPT baseline · GID test setRMS: 0.4357 -> 0.4188Improved
add Holistic Depth Initialization (ablation)DepthAnything V2 + DPT baseline · GID test setREL: 0.0524 -> 0.0506Improved
add Instance-Aware Depth Rectification (ablation)Baseline+H · GID test setRMS: 0.4188 -> 0.397Improved
add Instance-Aware Depth Rectification (ablation)Baseline+H · GID test setREL: 0.0506 -> 0.045Improved
add Instance-Aware Depth Rectification (ablation)Baseline+H · GID test setsigma1 accuracy: 0.9784 -> 0.983Improved
use 2 meter depth range partition instead of 1 meter (ablation)Holistic initialization · GID test setRMS: 0.426 -> 0.419Improved
use 3 meter depth range partition instead of 2 meter (ablation)Holistic initialization · GID test setRMS: 0.419 -> 0.431Hurt
add Ldist to Lobj (ablation)Instance-aware rectification · GID test setRMS: 0.407 -> 0.397Improved
add Lobj to Ldist (ablation)Instance-aware rectification · GID test setRMS: 0.412 -> 0.397Improved
add Ldist to Lobj (ablation)Instance-aware rectification · GID test setsigma1 accuracy: 0.974 -> 0.983Improved
use InstanceDepth instead of DepthAnything V2 on static indoor dataInstanceDepth · NYU Depth V2 testRMS: 0.206 -> 0.202No clear effect
use InstanceDepth instead of DepthAnything V2InstanceDepth · GID test setRMS: 0.435 -> 0.397Improved

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