论文标题
3D形成的神经小波域扩散
Neural Wavelet-domain Diffusion for 3D Shape Generation
论文作者
论文摘要
本文提出了一种新的3D形状生成方法，可以在小波域中的连续隐式表示上进行直接生成建模。具体而言，我们提出了一个带有一对粗略和细节系数的紧凑型小波表示，通过截短的签名距离函数和多尺度的生物构成波小波，隐式表示3D形状，并制定了一对神经网络：基于生成多种形式的扩散模型的生成器，以弥补的形式，以弥散形状，以弥补均匀的散光均匀的有效量；以及一个细节预测因子，以进一步产生兼容的细节系数量，以丰富具有精细结构和细节的生成形状。定量和定性实验结果都表现出我们方法在产生具有复杂拓扑和结构，干净表面和细节的多样化和高质量形状方面的优越性，超过了最先进的模型的3D代能力。
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.
