# Native and Compact Structured Latents for 3D Generation

arXiv: https://arxiv.org/abs/2512.14692 · HTML: https://mlsanity.com/paper/2512.14692/

## Key facts

- Cited by 175 papers in the map (data through 14 Oct 2026).
- Builds on 68 of its 81 references that are in the map.
- First posted on arXiv 16 Dec 2025.

## Builds on (most cited first, 30 of 68)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [Root Mean Square Layer Normalization](https://mlsanity.com/paper/1910.07467/) (2019)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis](https://mlsanity.com/paper/2310.00426/) (2023)
- [Objaverse-XL: A Universe of 10M+ 3D Objects](https://mlsanity.com/paper/2307.05663/) (2023)
- [Structured 3D Latents for Scalable and Versatile 3D Generation](https://mlsanity.com/paper/2412.01506/) (2024)
- [Diffusion Probabilistic Models for 3D Point Cloud Generation](https://mlsanity.com/paper/2103.01458/) (2021)
- [Point-E: A System for Generating 3D Point Clouds from Complex Prompts](https://mlsanity.com/paper/2212.08751/) (2022)
- [Mip-Splatting: Alias-free 3D Gaussian Splatting](https://mlsanity.com/paper/2311.16493/) (2023)
- [Perceiver IO: A General Architecture for Structured Inputs & Outputs](https://mlsanity.com/paper/2107.14795/) (2021)
- [LION: Latent Point Diffusion Models for 3D Shape Generation](https://mlsanity.com/paper/2210.06978/) (2022)
- [3D Shape Generation and Completion through Point-Voxel Diffusion](https://mlsanity.com/paper/2104.03670/) (2021)
- [3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models](https://mlsanity.com/paper/2301.11445/) (2023)
- [CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets](https://mlsanity.com/paper/2406.13897/) (2024)
- [Shap-E: Generating Conditional 3D Implicit Functions](https://mlsanity.com/paper/2305.02463/) (2023)
- [ABO: Dataset and Benchmarks for Real-World 3D Object Understanding](https://mlsanity.com/paper/2110.06199/) (2021)
- [Extracting Triangular 3D Models, Materials, and Lighting From Images](https://mlsanity.com/paper/2111.12503/) (2021)
- [3D-FUTURE: 3D Furniture shape with TextURE](https://mlsanity.com/paper/2009.09633/) (2020)
- [PolyGen: An Autoregressive Generative Model of 3D Meshes](https://mlsanity.com/paper/2002.10880/) (2020)

## Built on by (most cited first, 30 of 175)

- [SceneSmith: Agentic Generation of Simulation-Ready Indoor Scenes](https://mlsanity.com/paper/2602.09153/) (2026)
- [UltraShape 1.0: High-Fidelity 3D Shape Generation via Scalable Geometric Refinement](https://mlsanity.com/paper/2512.21185/) (2025)
- [PhysX-Omni: Unified Simulation-Ready Physical 3D Generation for Rigid, Deformable, and Articulated Objects](https://mlsanity.com/paper/2605.21572/) (2026)
- [LATO: 3D Mesh Flow Matching with Structured TOpology Preserving LAtents](https://mlsanity.com/paper/2603.06357/) (2026)
- [SegviGen: Repurposing 3D Generative Model for Part Segmentation](https://mlsanity.com/paper/2603.16869/) (2026)
- [PAct: Part-Decomposed Single-View Articulated Object Generation](https://mlsanity.com/paper/2602.14965/) (2026)
- [MoGe-3: Fine-Detail Monocular Geometry Estimation with Self-Guided Sparse Volumetric Refinement](https://mlsanity.com/paper/2607.17967/) (2026)
- [Reconstruction by Generation: 3D Multi-Object Scene Reconstruction from Sparse Observations](https://mlsanity.com/paper/2604.27106/) (2026)
- [Stream3D: Sequential Multi-View 3D Generation via Evidential Memory](https://mlsanity.com/paper/2605.21472/) (2026)
- [One Video, One World: Turning Monocular Video into Physical 4D Scenes](https://mlsanity.com/paper/2606.31388/) (2026)
- [EmbodiedGen V2: An Agentic, Simulation-Ready 3D World Engine for Embodied AI](https://mlsanity.com/paper/2607.07459/) (2026)
- [LATO.2: Factorized 3D Mesh Generation with Vertex and Topology Flow](https://mlsanity.com/paper/2607.10623/) (2026)
- [Optimization and Generation in Aerodynamics Inverse Design](https://mlsanity.com/paper/2602.03582/) (2026)
- [PEGAsus: 3D Personalization of Geometry and Appearance](https://mlsanity.com/paper/2602.08198/) (2026)
- [GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation](https://mlsanity.com/paper/2603.26661/) (2026)
- [LottieGPT: Tokenizing Vector Animation for Autoregressive Generation](https://mlsanity.com/paper/2604.11792/) (2026)
- [DexWorldModel: Causal Latent World Modeling towards Automated Learning of Embodied Tasks](https://mlsanity.com/paper/2604.16484/) (2026)
- [GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction](https://mlsanity.com/paper/2605.23888/) (2026)
- [World Tracing: Generative Pixel-Aligned Geometry Beyond the Visible](https://mlsanity.com/paper/2606.13652/) (2026)
- [Mix3R: Mixing Feed-forward Reconstruction and Generative 3D Priors for Joint Multi-view Aligned 3D Reconstruction and Pose Estimation](https://mlsanity.com/paper/2605.03359/) (2026)
- [Seed3D 2.0: Advancing High-Fidelity Simulation-Ready 3D Content Generation](https://mlsanity.com/paper/2605.13862/) (2026)
- [Generative 3D Gaussians with Learned Density Control](https://mlsanity.com/paper/2605.16355/) (2026)
- [Instruct-Particulate: Scaling Feed-Forward 3D Object Articulation with Kinematic Control](https://mlsanity.com/paper/2606.14699/) (2026)
- [Meshy T2: Fast Native Mesh Generation with Flow Matching](https://mlsanity.com/paper/2607.28675/) (2026)
- [Procedura: Agentic 3D Modeling with Procedural Control](https://mlsanity.com/paper/2608.26238/) (2026)
- [Research on World Models Is Not Merely Injecting World Knowledge into Specific Tasks](https://mlsanity.com/paper/2602.01630/) (2026)
- [Fast-SAM3D: 3Dfy Anything in Images but Faster](https://mlsanity.com/paper/2602.05293/) (2026)
- [Interact3D: Compositional 3D Generation of Interactive Objects](https://mlsanity.com/paper/2603.16085/) (2026)
- [VideoMatGen: PBR Materials through Joint Generative Modeling](https://mlsanity.com/paper/2603.16566/) (2026)
- [Omni123: Exploring 3D Native Foundation Models with Limited 3D Data by Unifying Text to 2D and 3D Generation](https://mlsanity.com/paper/2604.02289/) (2026)

## Abstract (arXiv)

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.