Neural Wavelet-domain Diffusion for 3D Shape Generation
This work addresses 3D shape generation for applications like computer graphics and design, offering a novel method that improves quality and detail over existing approaches, though it is incremental in its domain-specific focus.
The paper tackles 3D shape generation by proposing a neural wavelet-domain diffusion approach that uses coarse and detail coefficient volumes to represent shapes, resulting in diverse and high-quality shapes with complex topology and fine details, exceeding state-of-the-art models.
This paper presents a new approach for 3D shape generation, enabling direct generative modeling on a continuous implicit representation in wavelet domain. Specifically, we propose a compact wavelet representation with a pair of coarse and detail coefficient volumes to implicitly represent 3D shapes via truncated signed distance functions and multi-scale biorthogonal wavelets, and formulate a pair of neural networks: a generator based on the diffusion model to produce diverse shapes in the form of coarse coefficient volumes; and a detail predictor to further produce compatible detail coefficient volumes for enriching the generated shapes with fine structures and details. Both quantitative and qualitative experimental results manifest the superiority of our approach in generating diverse and high-quality shapes with complex topology and structures, clean surfaces, and fine details, exceeding the 3D generation capabilities of the state-of-the-art models.