Guardado en:
Detalles Bibliográficos
Autores principales: Huang, Yuhang, Zou, SHilong, Liu, Xinwang, Xu, Kai
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2405.00998
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916716217368576
author Huang, Yuhang
Zou, SHilong
Liu, Xinwang
Xu, Kai
author_facet Huang, Yuhang
Zou, SHilong
Liu, Xinwang
Xu, Kai
contents This paper presents a novel latent 3D diffusion model for the generation of neural voxel fields, aiming to achieve accurate part-aware structures. Compared to existing methods, there are two key designs to ensure high-quality and accurate part-aware generation. On one hand, we introduce a latent 3D diffusion process for neural voxel fields, enabling generation at significantly higher resolutions that can accurately capture rich textural and geometric details. On the other hand, a part-aware shape decoder is introduced to integrate the part codes into the neural voxel fields, guiding the accurate part decomposition and producing high-quality rendering results. Through extensive experimentation and comparisons with state-of-the-art methods, we evaluate our approach across four different classes of data. The results demonstrate the superior generative capabilities of our proposed method in part-aware shape generation, outperforming existing state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2405_00998
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Part-aware Shape Generation with Latent 3D Diffusion of Neural Voxel Fields
Huang, Yuhang
Zou, SHilong
Liu, Xinwang
Xu, Kai
Computer Vision and Pattern Recognition
This paper presents a novel latent 3D diffusion model for the generation of neural voxel fields, aiming to achieve accurate part-aware structures. Compared to existing methods, there are two key designs to ensure high-quality and accurate part-aware generation. On one hand, we introduce a latent 3D diffusion process for neural voxel fields, enabling generation at significantly higher resolutions that can accurately capture rich textural and geometric details. On the other hand, a part-aware shape decoder is introduced to integrate the part codes into the neural voxel fields, guiding the accurate part decomposition and producing high-quality rendering results. Through extensive experimentation and comparisons with state-of-the-art methods, we evaluate our approach across four different classes of data. The results demonstrate the superior generative capabilities of our proposed method in part-aware shape generation, outperforming existing state-of-the-art methods.
title Part-aware Shape Generation with Latent 3D Diffusion of Neural Voxel Fields
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.00998