Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916334490615808 |
|---|---|
| author | Yu, Zhengming Dou, Zhiyang Long, Xiaoxiao Lin, Cheng Li, Zekun Liu, Yuan Müller, Norman Komura, Taku Habermann, Marc Theobalt, Christian Li, Xin Wang, Wenping |
| author_facet | Yu, Zhengming Dou, Zhiyang Long, Xiaoxiao Lin, Cheng Li, Zekun Liu, Yuan Müller, Norman Komura, Taku Habermann, Marc Theobalt, Christian Li, Xin Wang, Wenping |
| contents | 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/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_17050 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Models Yu, Zhengming Dou, Zhiyang Long, Xiaoxiao Lin, Cheng Li, Zekun Liu, Yuan Müller, Norman Komura, Taku Habermann, Marc Theobalt, Christian Li, Xin Wang, Wenping Computer Vision and Pattern Recognition Graphics 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/. |
| title | Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Models |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2311.17050 |