We present Surf-D, a novel method for generating high-quality 3D shapes as Surfaces with arbitrary topologies using Diffusion models. Previous methods explored shape generation with different representations and they suffer from limited topologies and poor geometry details. To generate high-quality surfaces of arbitrary topologies, we use the Unsigned Distance Field (UDF) as our surface representation to accommodate arbitrary topologies. Furthermore, we propose a new pipeline that employs a point-based AutoEncoder to learn a compact and continuous latent space for accurately encoding UDF and support high-resolution mesh extraction. We further show that our new pipeline significantly outperforms the prior approaches to learning the distance fields, such as the grid-based AutoEncoder, which is not scalable and incapable of learning accurate UDF. In addition, we adopt a curriculum learning strategy to efficiently embed various surfaces. With the pretrained shape latent space, we employ a latent diffusion model to acquire the distribution of various shapes. Extensive experiments are presented on using Surf-D for unconditional generation, category conditional generation, image conditional generation, and text-to-shape tasks. The experiments demonstrate the superior performance of Surf-D in shape generation across multiple modalities as conditions. Visit our project page at https://yzmblog.github.io/projects/SurfD/.
@article{arxiv.2311.17050,
title = {Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Models},
author = {Zhengming Yu and Zhiyang Dou and Xiaoxiao Long and Cheng Lin and Zekun Li and Yuan Liu and Norman Müller and Taku Komura and Marc Habermann and Christian Theobalt and Xin Li and Wenping Wang},
journal= {arXiv preprint arXiv:2311.17050},
year = {2024}
}
Comments
Accepted to ECCV 2024. Project Page: https://yzmblog.github.io/projects/SurfD/