AI Paper Atlas

Research map / 3D vision / Face and shape

Feed-Forward Multi-view Multi-person Reconstruction with Contrastive Human-Aware 3D Representation

Yuanwang Yang, Buzhen Huang, Zongxuan Ren, Jing Huang, Kun Li

IJCV 2026 · 3D vision › Face and shape · approach: Full-body avatar reconstruction · 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 unified 3D feature space (ablation)full framework · EgoHumansCA-MPJPE: 3.12 -> 0.95Improved
add unified 3D feature space (ablation)full framework · EgoHumansPA-MPJPE: 2.53 -> 0.18Improved
add reprojection-based enhancement (ablation)full framework · EgoHumansCA-MPJPE: 1.28 -> 0.95Improved
add reprojection-based enhancement (ablation)full framework · EgoHumansPA-MPJPE: 1.74 -> 0.18Improved
add spatial contrastive learning (SCL) (ablation)full framework · EgoHumansCA-MPJPE: 1.94 -> 0.95Improved
add spatial contrastive learning (SCL) (ablation)full framework · EgoHumansGA-MPJPE: 0.49 -> 0.30Improved
replace VGGT backbone with AnySplat (ablation)full framework · EgoHumansCA-MPJPE: 0.95 -> 1.02No clear effect
learned 3D human confidence instead of 2D mask fusion (ablation)token-level human confidence · single-person datasetPrecision: 0.420 -> 0.886Improved
learned 3D human confidence instead of 2D mask fusiontoken-level human confidence · single-person datasetRecall: 0.989 -> 0.825Hurt
learned 3D human confidence instead of 2D mask fusiontoken-level human confidence · single-person datasetPR-AUC: 0.006 -> 0.863Improved
use spatial contrastive features instead of VGGT pose-aware ReIDassociation · cross-view associationAIDP: 82.02 -> 98.54Improved
feed-forward method instead of HSfM optimizationOurs vs HSfM · runtime, 1 input frameTime (s): 170 -> 0.209Improved

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