AI Paper Atlas

Research map / 3D vision / Depth and stereo

Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels

Jiahao Lu, Jiayi Xu, WENBO HU, Ruijie Zhu, Chengfeng Zhao, Sai Kit Yeung, Ying Shan, Yuan Liu

ECCV 2026 · 3D vision › Depth and stereo · approach: Learned optical and scene flow · 15 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
train with 2D flow supervision in addition to 3D data (ablation)Track4World · scene flow decoder ablation (avg)EPE3D: 0.6511 -> 0.2056Improved
add target lifting (lifted target samples) (ablation)Track4World · scene flow decoder ablation (avg)EPE3D: 0.3017 -> 0.2056Improved
use iterative refinement instead of single-step regression (ablation)Track4World · scene flow decoder ablation (avg)EPE3D: 0.2356 -> 0.2056Improved
add auxiliary 3D correlation and trajectory priors (ablation)Track4World · scene flow decoder ablation (avg)EPE3D: 0.2201 -> 0.2056Improved
use hybrid 2D flow plus Z-displacement instead of heuristic 2D flow + depth (ablation)Track4World · scene flow decoder ablation (avg)EPE3D: 0.8210 -> 0.2056Improved
use hybrid formulation instead of pure 3D flow regression (ablation)Track4World · scene flow decoder ablation (avg)EPE3D: 0.2815 -> 0.2056Improved
replace 2D-to-3D correlation with traditional 3D correlation (ablation)Track4World · ADT dense tracking, 16 framesmemory / time: 3.4s -> OOMHurt
swap backbone initialization from MoGe to Pi3 to DA3 (ablation)Track4World · avg scene flowEPE3D: 0.3180 -> 0.2569 -> 0.2056Improved
Track4World vs best prior on world-coordinate 3D trackingTrack4World · 3D tracking world coords L-50APD: 0.4668 -> 0.5323Improved
Track4World vs CoTracker3 on 2D trackingTrack4World · TAP-Vid KineticsAJ: 55.8 -> 59.1Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most 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

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