awesome 3D Generative Models

Similar to the 2D Generative Model (such as Stable Diffusion, Flux) that builds a bridge between text and images, the 3D Generative Model is a bridge between text/images and 3D data. But the pipeline of 3D creation is way more complex than 2D creation. 3D Generative models can be categorized into 3D objects and 3D scene generation (world model).

3D Animation Pipeline: Modeling (Re-Topology / UV Unwrapping / Artist Mesh) → Texture (PBR) → Motion (Rigging & Skinning / Animation / Rendering / Lighting / Simulation)

Contents

• Review
• Modeling - 3D Representation
• Modeling - VAE For Mesh Reconstruction
• Modeling / Texture - Flow-matching DiT For Mesh Generation & Texture Generation
• Modeling - Re-topology / Artist Mesh Generation
• Modeling - UV unwrapping
• Texture Generation
• Motion - Rigging / Articulation / Dynamics with Physical Property / Animation / Simulation
• Acceleration For Mesh Generation
• Post-train of 3D base models
• 3D Scene Generation (World Models)
  • Open source
  • Closed source
• Common Metrics
• Benchmark

Review

1. Feed-Forward-3D
2. Production-Ready 3D Survey
3. Awesome Feed-Forward 3D

Modeling - 3D Representation

1. VecSet (TOG 2023), Used by Hunyuan3D2.1, TripoSG, Step1X-3D)
2. (SLat) TRELLIS (Dec, 2024, CVPR'25)
3. Ghost on the Shell: An Expressive Representation of General 3D Shapes (ICLR 2024 Oral)
4. FastMesh: Efficient Artistic Mesh Generation via Component Decoupling
5. Geometry Distributions (ICCV 2025)
6. (VoxSet) LATTICE: Democratize High-Fidelity 3D Generation at Scale (Nov, 2025)
7. (O-Voxel) TRELLIS.2 (Dec, 2025 -> CVPR'26 Oral)
8. Faithful Contouring (Nov, 2025 -> CVPR'26 Oral)
9. FACE: A Face-based Autoregressive Representation for High-Fidelity and Efficient Mesh Generation (CVPR 2026)
10. Mesh BDF: Barycentric Dominance Field for 3D Native Mesh Generation (Jun, 2026)

Modeling - VAE For Mesh Reconstruction

1. Sparc3D (Jun, 2025)
2. TripoSF (Mar, 2025)
3. Dora (Feb, 2025, CVPR'25)

Modeling / Texture - Flow-matching DiT For Mesh Generation & Texture Generation

1. Ultra3D (Jul, 2025)
2. Hunyuan3D-2.1 (Jun, 2025)
3. Hunyuan3D-2 (Jan, 2025)
4. TripoSG (Mar, 2025)
5. Step1X-3D (May, 2025) with 🏋️training code & 🔥dataset!
6. Direct3D-S2 (May, 2025)
7. Hi3DGen (Apr, 2025 ICCV'25)
8. TRELLIS (Dec, 2024, CVPR'25)
9. UniLat3D (Sep, 2025)
10. UltraShape 1.0
11. Trelli2 (CVPR'26)
12. Pixal3D (SIGGRAPH'26)
13. LATO.2: Factorized 3D Mesh Generation with Vertex and Topology Flow (Jul, 2026, Meshy AI)
14. MeshGen: Generating PBR Textured Mesh with Render-Enhanced Auto-Encoder and Generative Data Augmentation (CVPR 2025 Highlight)
15. Nexus: Native Mesh Generation with Diffusion (SIGGRAPH 2026)
16. Cube: A Roblox View of 3D Intelligence (Mar, 2025; v0.5 Jul, 2025)
17. CubePart: An Open-Vocabulary Part-Controllable 3D Generator (SIGGRAPH 2026)
18. Arbor: Explicit Geometric Conditioning for Controllable 3D Asset Generation (Jun, 2026)
19. PartLLM: A Unified Multimodal Foundation for 3D Part Segmentation (SIGGRAPH Asia 2026, TOG)
20. SAM3D-Part: Interactive Part Selection and Generation from 3D Objects (SIGGRAPH Asia 2026)
21. GENA3D: Generative Amodal 3D Modeling by Bridging 2D Priors and 3D Coherence (ECCV 2026)

Modeling - Re-topology / Artist Mesh Generation

1. BPT (CVPR' 25)
2. DeepMesh (ICCV' 25)
3. MeshMosaic (CVPR' 26)
4. SATO (SIGGRAPH' 26)
5. TriFlow: Generating Artist-Like 3D Mesh Topology via Nearest-Vertex Vector Fields (ECCV 2026)
6. MeshOctave: Vertex Split-and-Rewire Cascades for Native Mesh Generation (2026)
7. TaoFlowForge: Progressive Native Mesh Generation via Cascaded Flow Matching (2026)

Modeling - UV unwrapping

1. Auto-Regressive Surface Cutting (Jun, 2025)
2. ArtUV: Artist-style UV Unwrapping (Sep, 2025)
3. SeamCrafter: Enhancing Mesh Seam Generation for Artist UV Unwrapping via Reinforcement Learning (Sep, 2025)
4. PartUV: Part-Based UV Unwrapping of 3D Meshes (SIGGRAPH Asia'24)
5. MeshTailor: Cutting Seams via Generative Mesh Traversal

Texture Generation

1. SyncMVD (SIGGRAPH Asia'24)
2. TEXGen (SIGGRAPH Asia'24)
3. ARM(CVPR'25)
4. MaterialAnything (CVPR'25)
5. MaterialMVP (ICCV'25)
6. RomanTex (ICCV'25)
7. NaTex: Meet Native Texture Generation (Nov 25)
8. SeqTex: Generate Mesh Textures in Video Sequence (SIGGRAPH Asia'25)
9. Chord: Chain of Rendering Decomposition for PBR Material Estimation from Generated Texture images (SIGGRAPH Asia'25)
10. LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windows
11. VideoNeuMat: Neural Material Extraction from Generative Video Models (SIGGRAPH 2026)
12. HKTex: Generating UV-Free Textures for 3D Meshes with Multiscale Heat Kernels (ECCV 2026 best🥇, Long Oral)
13. UltraTex: Unleashing 2K Multi-View Diffusion for 3D Texturing (SIGGRAPH Asia 2026)
14. SceneHI: High-Resolution 3D-Consistent Scene Texturing with Controllable Illumination (ECCV 2026)

Motion - Rigging / Articulation / Dynamics with Physical Property / Animation / Simulation

1. Unirig (SIGGRAPH'25)
2. AnimateAnyMesh(ICCV'25)
3. FreeArt3D: Training-Free Articulated Object Generation using 3D Diffusion(SIGGRAPH AISA'25)
4. Pixie: Physics from Pixels(Aug 2025)
5. SAFT: Shape and Appearance of Fabrics from Template via Differentiable Physical Simulations from Monocular Video (ICCV 2025)
6. BrickGPT: Generating Physically Stable and Buildable Brick Structures from Text (ICCV 2025 Best Paper)
7. PhysX-3D: Physical-Grounded 3D Asset Generation (NIPS 2025 Spotlight)
8. PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Image
9. PGC: Physics-Based Gaussian Cloth from a Single Pose (CVPR 2025 Highlight)
10. PhysAvatar: Learning the Physics of Dressed 3D Avatars from Visual Observations (ECCV 2024)
11. DSO: Aligning 3D Generators with Simulation Feedback for Physical Soundness (ICCV 2025)
12. ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation (SIGGRAPH 2026)

13. [AniGen: Unified S^3 Fields for Animatable 3D Asset Generation](https://yihua7.github.io/AniGen_web/) (SIGGRAPH 2026) 14. [R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow](https://github.com/Tencent-Hunyuan/R-DMesh) (SIGGRAPH 2026)

Acceleration For Mesh Generation (lightning vecset decoder)

1. FlashVDM (ICCV' 25)

Post-train of 3D base models

1. DeepMesh: Auto-Regressive Artist-Mesh Creation With Reinforcement Learning (ICCV 2025)
2. Nabla-R2D3 : Effective and Efficient 3D Diffusion Alignment with 2D Rewards (NIPS 2025)
3. DreamDPO: Aligning Text-to-3D Generation with Human Preferences via Direct Preference Optimization (ICML 2025)

3D Scene Generation (World Models)

Open source

1. https://github.com/Tencent-Hunyuan/HY-World-2.0
2. https://inspatio.github.io/worldfm/
3. https://research.nvidia.com/labs/sil/projects/lyra2/
4. https://world-grow.github.io/
5. https://fantasy-amap.github.io/fantasy-world/
6. https://worldgen.github.io
7. https://github.com/quan-meng/seen2scene
8. https://github.com/nicolasvonluetzow/gaussiangpt
9. Code World Model: Coding Agent as World Brain (Aug, 2026)
10. Code-as-World: Agentic Discovery of Executable World Representations for Physical Reasoning (Aug, 2026)
11. Dream-Cubed: Controllable Generative Modeling in Minecraft (Apr, 2026)

Closed source

1. https://marble.worldlabs.ai/
2. https://spaitial.ai/
3. https://deepmind.google/models/genie/
4. https://odyssey.ml/
5. https://runwayml.com/
6. https://moonlakeai.com/

Common Metrics

For mesh

1. ULIP-T(⬆), ULIP-I(⬆), ULIP
2. Uni3D-T(⬆), Uni3D-I(⬆), Uni3D
   • code for ULIP/Uni3D: https://github.com/Tencent-Hunyuan/FlashVDM/blob/main/evaluation/app_metric.py
3. Chamfer Distance (CD⬇) and Normal Consistency (NC⬆) quantify the geometric similarity between reconstructed/generated and ground-truth meshes.

For texture

1. CLIP-FiD(⬇)
2. CMMD(⬇)
3. CLIP-I(⬆)
4. LPIPS(⬇)

Benchmark

1. HY3D-Bench
2. Meshy-Bench
3. Taxon3D
   • live arena: https://taxon3d.org — blind pairwise human evaluation of generated 3D organisms (plants, fungi, animals) against CC-licensed reference photographs of the real species. Bradley–Terry with bootstrap CIs; a model without enough comparisons is reported unranked rather than given a point estimate.