CraftsMan3D: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry Refiner

TL;DR

CraftsMan3D introduces a fast, high-fidelity 3D mesh generation system that combines a 3D native diffusion model with interactive refinement, enabling detailed and varied geometries from text or images.

Contribution

The paper presents a novel 3D generation pipeline using a 3D native diffusion model and multi-view conditioning, allowing rapid, high-quality, and editable 3D mesh creation.

Findings

Generates high-quality 3D meshes from text or images

Achieves fast generation with regular mesh topology

Supports interactive geometry refinement

Abstract

We present a novel generative 3D modeling system, coined CraftsMan, which can generate high-fidelity 3D geometries with highly varied shapes, regular mesh topologies, and detailed surfaces, and, notably, allows for refining the geometry in an interactive manner. Despite the significant advancements in 3D generation, existing methods still struggle with lengthy optimization processes, irregular mesh topologies, noisy surfaces, and difficulties in accommodating user edits, consequently impeding their widespread adoption and implementation in 3D modeling software. Our work is inspired by the craftsman, who usually roughs out the holistic figure of the work first and elaborates the surface details subsequently. Specifically, we employ a 3D native diffusion model, which operates on latent space learned from latent set-based 3D representations, to generate coarse geometries with regular mesh topology in seconds. In particular, this process takes as input a text prompt or a reference image and leverages a powerful multi-view (MV) diffusion model to generate multiple views of the coarse geometry, which are fed into our MV-conditioned 3D diffusion model for generating the 3D geometry, significantly improving robustness and generalizability. Following that, a normal-based geometry refiner is used to significantly enhance the surface details. This refinement can be performed automatically, or interactively with user-supplied edits. Extensive experiments demonstrate that our method achieves high efficacy in producing superior-quality 3D assets compared to existing methods. HomePage: https://craftsman3d.github.io/, Code: https://github.com/wyysf-98/CraftsMan