DetailGen3D: Generative 3D Geometry Enhancement via Data-Dependent Flow

Ken Deng, Yuan-Chen Guo, Jingxiang Sun, Zi-Xin Zou, Yangguang Li, Xin Cai, Yan-Pei Cao, Yebin Liu, Ding Liang

Keywords: 3D Geometry Refinement, Data-Dependent Flow, Token Matching

TL;DR: We introduce a large flow-based 3D generative model for geometry refinement.

Abstract: Modern 3D generation methods can rapidly create shapes from sparse or single views, but their outputs often lack geometric detail due to computational constraints. We present DetailGen3D, a generative approach specifically designed to enhance these synthetically generated 3D shapes. Our key insight is to model the coarse-to-fine transformation directly through data-dependent flows in latent space, avoiding the computational overhead of large-scale 3D generative models. We introduce a token matching strategy that ensures accurate spatial correspondence during refinement, enabling local detail synthesis while preserving global structure. By carefully designing our training data to match the characteristics of neural-generated shapes, our method effectively enhances shapes produced by various 3D generation and reconstruction approaches, from single-view to sparse multi-view scenarios. Extensive experiments demonstrate that DetailGen3D achieves high-fidelity geometric detail synthesis while maintaining efficiency in training.

Submission Number: 4