Saved in:
Bibliographic Details
Main Authors: Xiang, Jianfeng, Chen, Xiaoxue, Xu, Sicheng, Wang, Ruicheng, Lv, Zelong, Deng, Yu, Zhu, Hongyuan, Dong, Yue, Zhao, Hao, Yuan, Nicholas Jing, Yang, Jiaolong
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.14692
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911323317600256
author Xiang, Jianfeng
Chen, Xiaoxue
Xu, Sicheng
Wang, Ruicheng
Lv, Zelong
Deng, Yu
Zhu, Hongyuan
Dong, Yue
Zhao, Hao
Yuan, Nicholas Jing
Yang, Jiaolong
author_facet Xiang, Jianfeng
Chen, Xiaoxue
Xu, Sicheng
Wang, Ruicheng
Lv, Zelong
Deng, Yu
Zhu, Hongyuan
Dong, Yue
Zhao, Hao
Yuan, Nicholas Jing
Yang, Jiaolong
contents Recent advancements in 3D generative modeling have significantly improved the generation realism, yet the field is still hampered by existing representations, which struggle to capture assets with complex topologies and detailed appearance. This paper present an approach for learning a structured latent representation from native 3D data to address this challenge. At its core is a new sparse voxel structure called O-Voxel, an omni-voxel representation that encodes both geometry and appearance. O-Voxel can robustly model arbitrary topology, including open, non-manifold, and fully-enclosed surfaces, while capturing comprehensive surface attributes beyond texture color, such as physically-based rendering parameters. Based on O-Voxel, we design a Sparse Compression VAE which provides a high spatial compression rate and a compact latent space. We train large-scale flow-matching models comprising 4B parameters for 3D generation using diverse public 3D asset datasets. Despite their scale, inference remains highly efficient. Meanwhile, the geometry and material quality of our generated assets far exceed those of existing models. We believe our approach offers a significant advancement in 3D generative modeling.
format Preprint
id arxiv_https___arxiv_org_abs_2512_14692
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Native and Compact Structured Latents for 3D Generation
Xiang, Jianfeng
Chen, Xiaoxue
Xu, Sicheng
Wang, Ruicheng
Lv, Zelong
Deng, Yu
Zhu, Hongyuan
Dong, Yue
Zhao, Hao
Yuan, Nicholas Jing
Yang, Jiaolong
Computer Vision and Pattern Recognition
Artificial Intelligence
Recent advancements in 3D generative modeling have significantly improved the generation realism, yet the field is still hampered by existing representations, which struggle to capture assets with complex topologies and detailed appearance. This paper present an approach for learning a structured latent representation from native 3D data to address this challenge. At its core is a new sparse voxel structure called O-Voxel, an omni-voxel representation that encodes both geometry and appearance. O-Voxel can robustly model arbitrary topology, including open, non-manifold, and fully-enclosed surfaces, while capturing comprehensive surface attributes beyond texture color, such as physically-based rendering parameters. Based on O-Voxel, we design a Sparse Compression VAE which provides a high spatial compression rate and a compact latent space. We train large-scale flow-matching models comprising 4B parameters for 3D generation using diverse public 3D asset datasets. Despite their scale, inference remains highly efficient. Meanwhile, the geometry and material quality of our generated assets far exceed those of existing models. We believe our approach offers a significant advancement in 3D generative modeling.
title Native and Compact Structured Latents for 3D Generation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2512.14692