AI Paper Atlas

Research map / 3D vision / Human pose estimation

MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization

CVPR 2021 · 3D vision › Human pose estimation · approach: Category-level pose estimation · 36 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Use weighted permutation synchronization (ablation)MultiBodySync · SAPIENEPE3D mean: 6.20 -> 5.03Helped
Use permutation synchronization rather than direct pairwise flow (ablation)MultiBodySync · SAPIENEPE3D mean: 6.20 -> 5.03Helped
Add weighting to permutation synchronization (ablation)MultiBodySync · SAPIENEPE3D mean: 6.08 -> 5.03Helped
Use four iterative-refinement iterations instead of one (ablation)MultiBodySync · SAPIENMulti-Scan mIoU: 62.9 -> 66.7Helped
Use normalized rather than unnormalized motion segmentation synchronization (ablation)MultiBodySync · SAPIENMulti-Scan mIoU: 65.8 -> 66.7Helped
Use normalized rather than unnormalized motion segmentation synchronization (ablation)MultiBodySync · DynLabrigid-flow EPE3DNo clear effect
Add more input views (ablation)MultiBodySync · SAPIENsegmentation accuracyHelped
Use additional iterative-refinement steps (ablation)MultiBodySync · SAPIENsegmentation accuracyHelped

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