# UniLat3D: Geometry-Appearance Unified Latents for Single-Stage 3D Generation

arXiv: https://arxiv.org/abs/2509.25079 · HTML: https://mlsanity.com/paper/2509.25079/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models.
- Builds on 89 of its 94 references that are in the map.
- First posted on arXiv 29 Sep 2025.

## Placed in

- Diffusion models / [3D, point cloud and scene generation](https://mlsanity.com/diffusion/3d-point-cloud-and-scene-generation/)

## Builds on (most cited first, 30 of 89)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [Zero-1-to-3: Zero-shot One Image to 3D Object](https://mlsanity.com/paper/2303.11328/) (2023)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation](https://mlsanity.com/paper/2305.16213/) (2023)
- [4D Gaussian Splatting for Real-Time Dynamic Scene Rendering](https://mlsanity.com/paper/2310.08528/) (2023)
- [MVDream: Multi-view Diffusion for 3D Generation](https://mlsanity.com/paper/2308.16512/) (2023)
- [LRM: Large Reconstruction Model for Single Image to 3D](https://mlsanity.com/paper/2311.04400/) (2023)
- [DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation](https://mlsanity.com/paper/2309.16653/) (2023)
- [Structured 3D Latents for Scalable and Versatile 3D Generation](https://mlsanity.com/paper/2412.01506/) (2024)
- [Point-E: A System for Generating 3D Point Clouds from Complex Prompts](https://mlsanity.com/paper/2212.08751/) (2022)
- [Wonder3D: Single Image to 3D using Cross-Domain Diffusion](https://mlsanity.com/paper/2310.15008/) (2023)
- [One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization](https://mlsanity.com/paper/2306.16928/) (2023)
- [LION: Latent Point Diffusion Models for 3D Shape Generation](https://mlsanity.com/paper/2210.06978/) (2022)
- [Continuous 3D Perception Model with Persistent State](https://mlsanity.com/paper/2501.12387/) (2025)
- [FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision](https://mlsanity.com/paper/2407.08608/) (2024)
- [Zero-Shot Text-Guided Object Generation with Dream Fields](https://mlsanity.com/paper/2112.01455/) (2021)

## Built on by (most cited first, 20 of 20)

- [WorldGrow: Generating Infinite 3D World](https://mlsanity.com/paper/2510.21682/) (2025)
- [Motion 3-to-4: 3D Motion Reconstruction for 4D Synthesis](https://mlsanity.com/paper/2601.14253/) (2026)
- [Feedforward 3D Editing via Text-Steerable Image-to-3D](https://mlsanity.com/paper/2512.13678/) (2025)
- [LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generation](https://mlsanity.com/paper/2604.11789/) (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)
- [Generative 3D Gaussians with Learned Density Control](https://mlsanity.com/paper/2605.16355/) (2026)
- [Grasp in Gaussians: Fast Monocular Reconstruction of Dynamic Hand-Object Interactions](https://mlsanity.com/paper/2604.12929/) (2026)
- [EVA01: Unified Native 3D Understanding and Generation via Mixture-of-Transformers](https://mlsanity.com/paper/2605.16745/) (2026)
- [Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models](https://mlsanity.com/paper/2608.25518/) (2026)
- [Text-Image Conditioned 3D Generation](https://mlsanity.com/paper/2603.21295/) (2026)
- [TopoMesh: High-Fidelity Mesh Autoencoding via Topological Unification](https://mlsanity.com/paper/2603.24278/) (2026)
- [WorldAct: Activating Monolithic 3D Worlds into Interactive-Ready Object-Centric Scenes](https://mlsanity.com/paper/2605.15843/) (2026)
- [FlowObject: Flow Steering for Bridging Generative Priors and Reconstruction Fidelity](https://mlsanity.com/paper/2606.19019/) (2026)
- [ATATA: One Algorithm to Align Them All](https://mlsanity.com/paper/2601.11194/) (2026)
- [Structured 3D Latents Are Surprisingly Powerful: Unleashing Generalizable Style with 2D Diffusion](https://mlsanity.com/paper/2605.04412/) (2026)
- [CAdam: Context-Adaptive Moment Estimation for 3D Gaussian Densification in Generative Distillation](https://mlsanity.com/paper/2605.20872/) (2026)
- [Beyond Global Latents: Chunk-Based Sparse Grid VAE for Scalable 3D Modeling](https://mlsanity.com/paper/2608.02016/) (2026)
- [SCULPT: Subtractive Composition for 3D Part Generation](https://mlsanity.com/paper/2608.13541/) (2026)
- [Learning 3D Editing without Paired Supervision via Generative Prior Distillation](https://mlsanity.com/paper/2609.04942/) (2026)
- [HI3D 3.0 (Twinkle3D): Object-specific 3D Asset Generation with High Resolution](https://mlsanity.com/paper/2610.11685/) (2026)

## Abstract (arXiv)

High-fidelity 3D asset generation is crucial for various industries. While recent 3D pretrained models show strong capability in producing realistic content, most are built upon diffusion models and follow a two-stage pipeline that first generates geometry and then synthesizes appearance. Such a decoupled design tends to produce geometry-texture misalignment and non-negligible cost. In this paper, we propose UniLat3D, a unified framework that encodes geometry and appearance in a single latent space, enabling direct single-stage generation. Our key contribution is a geometry-appearance Unified VAE, which compresses high-resolution sparse features into a compact latent representation -- UniLat. UniLat integrates structural and visual information into a dense low-resolution latent, which can be efficiently decoded into diverse 3D formats, e.g., 3D Gaussians and meshes. Based on this unified representation, we train a single flow-matching model to map Gaussian noise directly into UniLat, eliminating redundant stages. Trained solely on public datasets, UniLat3D produces high-quality 3D assets in seconds from a single image, achieving superior appearance fidelity and geometric quality. More demos & code are available at https://unilat3d.github.io/