DetailGen3D: Generative 3D Geometry Enhancement via Data-Dependent Flow
This addresses the need for more detailed 3D shapes in generation and reconstruction tasks, but it is incremental as it builds on existing methods by refining their outputs.
The paper tackles the problem of generated 3D shapes lacking geometric detail due to computational constraints, and presents DetailGen3D, which enhances these shapes via data-dependent flows in latent space, achieving high-fidelity detail synthesis while maintaining training efficiency.
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 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 synthesized coarse shapes, our method can effectively enhance shapes produced by various 3D generation and reconstruction approaches, from single-view to sparse multi-view inputs. Extensive experiments demonstrate that DetailGen3D achieves high-fidelity geometric detail synthesis while maintaining efficiency in training.