FrePolad: Frequency-Rectified Point Latent Diffusion for Point Cloud Generation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914867220316160 |
|---|---|
| author | Zhou, Chenliang Zhong, Fangcheng Hanji, Param Guo, Zhilin Fogarty, Kyle Sztrajman, Alejandro Gao, Hongyun Oztireli, Cengiz |
| author_facet | Zhou, Chenliang Zhong, Fangcheng Hanji, Param Guo, Zhilin Fogarty, Kyle Sztrajman, Alejandro Gao, Hongyun Oztireli, Cengiz |
| contents | We propose FrePolad: frequency-rectified point latent diffusion, a point cloud generation pipeline integrating a variational autoencoder (VAE) with a denoising diffusion probabilistic model (DDPM) for the latent distribution. FrePolad simultaneously achieves high quality, diversity, and flexibility in point cloud cardinality for generation tasks while maintaining high computational efficiency. The improvement in generation quality and diversity is achieved through (1) a novel frequency rectification via spherical harmonics designed to retain high-frequency content while learning the point cloud distribution; and (2) a latent DDPM to learn the regularized yet complex latent distribution. In addition, FrePolad supports variable point cloud cardinality by formulating the sampling of points as conditional distributions over a latent shape distribution. Finally, the low-dimensional latent space encoded by the VAE contributes to FrePolad's fast and scalable sampling. Our quantitative and qualitative results demonstrate FrePolad's state-of-the-art performance in terms of quality, diversity, and computational efficiency. Project page: https://chenliang-zhou.github.io/FrePolad/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_12090 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | FrePolad: Frequency-Rectified Point Latent Diffusion for Point Cloud Generation Zhou, Chenliang Zhong, Fangcheng Hanji, Param Guo, Zhilin Fogarty, Kyle Sztrajman, Alejandro Gao, Hongyun Oztireli, Cengiz Computer Vision and Pattern Recognition We propose FrePolad: frequency-rectified point latent diffusion, a point cloud generation pipeline integrating a variational autoencoder (VAE) with a denoising diffusion probabilistic model (DDPM) for the latent distribution. FrePolad simultaneously achieves high quality, diversity, and flexibility in point cloud cardinality for generation tasks while maintaining high computational efficiency. The improvement in generation quality and diversity is achieved through (1) a novel frequency rectification via spherical harmonics designed to retain high-frequency content while learning the point cloud distribution; and (2) a latent DDPM to learn the regularized yet complex latent distribution. In addition, FrePolad supports variable point cloud cardinality by formulating the sampling of points as conditional distributions over a latent shape distribution. Finally, the low-dimensional latent space encoded by the VAE contributes to FrePolad's fast and scalable sampling. Our quantitative and qualitative results demonstrate FrePolad's state-of-the-art performance in terms of quality, diversity, and computational efficiency. Project page: https://chenliang-zhou.github.io/FrePolad/. |
| title | FrePolad: Frequency-Rectified Point Latent Diffusion for Point Cloud Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2311.12090 |