We introduce a new generative model that combines latent diffusion with persistent homology to create 3D shapes with high diversity, with a special emphasis on their topological characteristics. Our method involves representing 3D shapes as implicit fields, then employing persistent homology to extract topological features, including Betti numbers and persistence diagrams. The shape generation process consists of two steps. Initially, we employ a transformer-based autoencoding module to embed the implicit representation of each 3D shape into a set of latent vectors. Subsequently, we navigate through the learned latent space via a diffusion model. By strategically incorporating topological features into the diffusion process, our generative module is able to produce a richer variety of 3D shapes with different topological structures. Furthermore, our framework is flexible, supporting generation tasks constrained by a variety of inputs, including sparse and partial point clouds, as well as sketches. By modifying the persistence diagrams, we can alter the topology of the shapes generated from these input modalities.
@article{arxiv.2401.17603,
title = {Topology-Aware Latent Diffusion for 3D Shape Generation},
author = {Jiangbei Hu and Ben Fei and Baixin Xu and Fei Hou and Weidong Yang and Shengfa Wang and Na Lei and Chen Qian and Ying He},
journal= {arXiv preprint arXiv:2401.17603},
year = {2024}
}