AI Paper Atlas

Research map / 3D vision / Face and shape

3D-ReGen: A Unified 3D Geometry Regeneration Framework

Geon Yeong Park, Roman Shapovalov, Rakesh Ranjan, Jong Chul Ye, Andrea Vedaldi, Thu Nguyen-Phuoc

ECCV 2026 · 3D vision › Face and shape · approach: 3D shape generative modeling

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
regenerate with MeshReGen instead of leaving input shapecoarse decomposed objects · 3D shape enhancementMV-ImageReward: 0.1716 -> 0.3394Improved
regenerate with MeshReGen instead of DetailGen3Dcoarse decomposed objects · 3D shape enhancementULIP-3D: 0.2294 -> 0.2626Improved
add MeshReGen refinement to VGGT predictions (4 views)VGGT · GSO reconstructionChamfer distance: 0.1276 -> 0.0081Improved
add MeshReGen refinement to VGGT predictions (1 view)VGGT · GSO reconstructionChamfer distance: 0.1286 -> 0.0135Improved
more input views for MeshReGen (1 to 4)VGGT + MeshReGen · GSO reconstructionF-score: 0.3658 -> 0.4913Improved
MeshReGen with 4 views versus AssetGen on PSNRVGGT + MeshReGen · GSO reconstruction (4 views)PSNR: 24.3809 -> 24.2754No clear effect
use MeshReGen instead of Hunyuan3D-Omni (1 view)GSO reconstruction · GSO reconstruction (1 view)Chamfer distance: 0.0173 -> 0.0135Improved
use input-space conditioning instead of additional cross-attention (ablation)MeshReGen · Conditioning ablationChamfer distance: 0.0066 -> 0.0044Improved
use input-space conditioning instead of extended cross-attention (ablation)MeshReGen · Conditioning ablationChamfer distance: 0.0271 -> 0.0044Improved
use coarse-shape embedding conditioning instead of additively injecting zL into noisy latents (ablation)MeshReGen · Conditioning ablationF-score: 0.5259 -> 0.7538Improved
condition on sampled point clouds instead of coarse embeddings in cross-attention (ablation)MeshReGen · Conditioning ablationChamfer distance: 0.0066 -> 0.0162Hurt
keep original diffusion parameterization instead of flow mapping from coarse to clean latents (ablation)MeshReGen · Diffusion parameterization ablationF-score: 0.6026 -> 0.7003Improved

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