Saved in:
Bibliographic Details
Main Authors: Park, Geon Yeong, Shapovalov, Roman, Ranjan, Rakesh, Ye, Jong Chul, Vedaldi, Andrea, Nguyen-Phuoc, Thu
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.28134
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • We consider the problem of regenerating 3D objects from 2D images and initial 3D shapes. Most 3D generators operate in a one-shot fashion, converting text or images to a 3D object with limited controllability. We introduce instead MeshReGen, a 3D regenerator that is conditioned on an initial 3D shape. This conceptually simple formulation allows us to support numerous useful tasks, including 3D enhancement, reconstruction, and editing. MeshReGen uses a new conditioning mechanism based on VecSet, which allows the regenerator to update or improve the input geometry with consistent fine-grained details. MeshReGen learns a widely applicable regeneration prior from off-the-shelf 3D datasets via self-supervised pretext tasks and augmentations, without additional annotations. We evaluate both the geometric consistency and fine-grained quality of MeshReGen, achieving state-of-the-art performance in controllable 3D generation across several tasks.