CVApr 30

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

arXiv:2604.2813497.6
Predicted impact top 5% in CV · last 90 daysOriginality Incremental advance
AI Analysis

For 3D content creation, this provides a versatile and controllable regeneration method that outperforms existing approaches.

3D-ReGen introduces a unified framework for regenerating 3D objects from 2D images and initial 3D shapes, supporting tasks like enhancement, reconstruction, and editing. It achieves state-of-the-art performance in controllable 3D generation across multiple tasks.

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 3D-ReGen, 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. 3D-ReGen uses a new conditioning mechanism based on VecSet, which allows the regenerator to update or improve the input geometry with consistent fine-grained details. 3D-ReGen 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 3D-ReGen, achieving state-of-the-art performance in controllable 3D generation across several tasks.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes