Native and Compact Structured Latents for 3D Generation

Papers with Code Trending Papers

Summary

This paper introduces O-Voxel, a new sparse voxel representation for 3D generative modeling that efficiently handles complex topologies and appearance, and trains large-scale flow-matching models with 4B parameters to achieve state-of-the-art generation quality.

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.
Original Article
View Cached Full Text

Cached at: 07/25/26, 05:03 AM

Paper page - Native and Compact Structured Latents for 3D Generation

Source: https://huggingface.co/papers/2512.14692 Published on Dec 16, 2025

Authors:

,

,

,

,

,

,

,

,

,

Abstract

A new sparse voxel representation called O-Voxel enables high-quality 3D generative modeling with efficient inference and robust topology handling.

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 detailedappearance. This paper present an approach for learning a structured latent representation from native 3D data to address this challenge. At its core is a newsparse voxel structurecalledO-Voxel, anomni-voxel representationthat encodes bothgeometryandappearance.O-Voxelcan robustly model arbitrary topology, including open, non-manifold, and fully-enclosed surfaces, while capturing comprehensive surface attributes beyond texture color, such asphysically-based rendering parameters. Based onO-Voxel, we design aSparse Compression VAEwhich provides a high spatial compression rate and a compact latent space. We train large-scaleflow-matching modelscomprising 4B parameters for 3D generation using diverse public 3D asset datasets. Despite their scale, inference remains highly efficient. Meanwhile, thegeometryand material quality of our generated assets far exceed those of existing models. We believe our approach offers a significant advancement in 3D generative modeling.

View arXiv pageView PDFProject pageGitHub8.92kAdd to collection

Get this paper in your agent:

hf papers read 2512\.14692

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper37

#### microsoft/TRELLIS.2-4B Image-to-3D• UpdatedDec 27, 2025 • 1.56M • 1.01k #### mancub/TRELLIS.2-4B Image-to-3D• UpdatedDec 18, 2025 • 17 • 1 #### Jinstudio/TRELLIS.2-4B Image-to-3D• Updated29 days ago • 34 • 1 #### camenduru/TRELLIS.2-4B Image-to-3D• UpdatedDec 17, 2025 • 35.4k Browse 37 models citing this paper## Datasets citing this paper1

#### serpentine-b/t2 UpdatedDec 20, 2025 • 17

Spaces citing this paper164

Browse 164 spaces citing this paper## Collections including this paper2

Similar Articles

Structured 3D Latents for Scalable and Versatile 3D Generation

Papers with Code Trending

微软提出统一的结构化潜在表示(SLAT),结合 rectified flow transformers 实现高质量、多格式(Radiance Fields、3D Gaussians、网格)的 3D 资产生成,支持文本/图像条件及局部编辑,在 500K 3D 数据集上训练的 2B 参数模型显著超越现有方法。

Direct3D-V3: Latent-Free Diffusion Transformers in the Native Voxel Domain

Hugging Face Daily Papers

Direct3D-V3 proposes a latent-free diffusion transformer framework that discards the VAE and directly models raw SDF voxel grids in the native voxel domain, using implicit manifold regularization and camera-prediction auxiliary tasks to produce richer 3D mesh detail.

@zhiwen_fan_: paper from dust3r’s team

X AI KOLs Timeline

A paper from the DUSt3R team proposes sparse auto-regressive modeling for 3D scene generation from multi-view images, using a voxel-aligned 3D latent space and an occupancy-aware masked autoregressive transformer.