mlsanityData to 14 Oct 2026

Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material

arXiv 2506.15442 ↗First posted 18 Jun 2025cs.CV cs.AIcited by 165

Not on the map. Why?

Cited by 21 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

3D AI-generated content (AIGC) is a passionate field that has significantly accelerated the creation of 3D models in gaming, film, and design. Despite the development of several groundbreaking models that have revolutionized 3D generation, the field remains largely accessible only to researchers, developers, and designers due to the complexities involved in collecting, processing, and training 3D models. To address these challenges, we introduce Hunyuan3D 2.1 as a case study in this tutorial. This tutorial offers a comprehensive, step-by-step guide on processing 3D data, training a 3D generative model, and evaluating its performance using Hunyuan3D 2.1, an advanced system for producing high-resolution, textured 3D assets. The system comprises two core components: the Hunyuan3D-DiT for shape generation and the Hunyuan3D-Paint for texture synthesis. We will explore the entire workflow, including data preparation, model architecture, training strategies, evaluation metrics, and deployment. By the conclusion of this tutorial, you will have the knowledge to finetune or develop a robust 3D generative model suitable for applications in gaming, virtual reality, and industrial design.

Key facts. Cited by 165 papers in the map (data through 14 Oct 2026). Builds on 40 of its 45 references that are in the map. First posted on arXiv 18 Jun 2025.

Builds on

40 of 45 references.

References · 40

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  5. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  6. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  7. 2022Flow Matching for Generative Modelingcited by 5,702
  8. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  9. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  10. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,540
  11. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,489
  12. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 849
28 more
  1. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 774
  2. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 770
  3. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Imagecited by 645
  4. 2023Zero123++: a Single Image to Consistent Multi-view Diffusion Base Modelcited by 521
  5. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 458
  6. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assetscited by 455
  7. 2024InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Modelscited by 433
  8. 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generationcited by 356
  9. 2023Common Diffusion Noise Schedules and Sample Steps are Flawedcited by 310
  10. 2024Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understandingcited by 298
  11. 2022ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understandingcited by 267
  12. 2023Uni3D: Exploring Unified 3D Representation at Scalecited by 237
  13. 2023Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representationcited by 228
  14. 2025TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Modelscited by 213
  15. 2016Thingi10K: A Dataset of 10,000 3D-Printing Modelscited by 183
  16. 2024CraftsMan3D: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry Refinercited by 123
  17. 2025Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attentioncited by 110
  18. 20243DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusioncited by 101
  19. 2024Dora: Sampling and Benchmarking for 3D Shape Variational Auto-Encoderscited by 98
  20. 2025Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assetscited by 87
  21. 2023Text-Guided Texturing by Synchronized Multi-View Diffusioncited by 86
  22. 2023Consistent123: Improve Consistency for One Image to 3D Object Synthesiscited by 84
  23. 2024Hunyuan3D 1.0: A Unified Framework for Text-to-3D and Image-to-3D Generationcited by 82
  24. 2024Scaling Mesh Generation via Compressive Tokenizationcited by 73
  25. 2024TEXGen: a Generative Diffusion Model for Mesh Texturescited by 46
  26. 2025RomanTex: Decoupling 3D-aware Rotary Positional Embedded Multi-Attention Network for Texture Synthesiscited by 20
  27. 2024ViewFusion: Towards Multi-View Consistency via Interpolated Denoisingcited by 14
  28. 2024FlexiTex: Enhancing Texture Generation via Visual Guidancecited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 44; 2026: 121.

165 papers.

Sort:

By area:

  1. 2025SAM 3D: 3Dfy Anything in Imagescited by 247
  2. 2025Native and Compact Structured Latents for 3D Generationcited by 175
  3. 2025Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Detailscited by 125
  4. 2025SceneGen: Single-Image 3D Scene Generation in One Feedforward Passcited by 54
  5. 2025Ultra3D: Efficient and High-Fidelity 3D Generation with Part Attentioncited by 44
  6. 2025LATTICE: Democratize High-Fidelity 3D Generation at Scalecited by 44
  7. 2025NANO3D: A Training-Free Approach for Efficient 3D Editing Without Maskscited by 31
  8. 2025Particulate: Feed-Forward 3D Object Articulationcited by 23
  9. 2025Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assetscited by 22
  10. 2025UniLat3D: Geometry-Appearance Unified Latents for Single-Stage 3D Generationcited by 20
  11. 2025Seed3D 1.0: From Images to High-Fidelity Simulation-Ready 3D Assetscited by 20
  12. 2025WorldGen: From Text to Traversable and Interactive 3D Worldscited by 19
38 more
  1. 2025UltraShape 1.0: High-Fidelity 3D Shape Generation via Scalable Geometric Refinementcited by 16
  2. 2025HOLODECK 2.0: Vision-Language-Guided 3D World Generation with Editingcited by 15
  3. 2025Rethinking Driving World Model as Synthetic Data Generator for Perception Taskscited by 14
  4. 2026Pixal3D: Pixel-Aligned 3D Generation from Imagescited by 14
  5. 2025Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generationcited by 13
  6. 2026Mesh4D: 4D Mesh Reconstruction and Tracking from Monocular Videocited by 12
  7. 2026HY3D-Bench: Generation of 3D Assetscited by 11
  8. 2025AnchorFlow: Training-Free 3D Editing via Latent Anchor-Aligned Flowscited by 9
  9. 2026WorldClaw: Agentic 3D Open-World Generation at Scalecited by 8
  10. 2025Sat2RealCity: Geometry-Aware and Appearance-Controllable 3D Urban Generation from Satellite Imagerycited by 7
  11. 2025Part-X-MLLM: Part-aware 3D Multimodal Large Language Modelcited by 7
  12. 2025NaTex: Seamless Texture Generation as Latent Color Diffusioncited by 7
  13. 2026MeshFlow: Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion Transformercited by 7
  14. 2025XSpecMesh: Quality-Preserving Auto-Regressive Mesh Generation Acceleration via Multi-Head Speculative Decodingcited by 6
  15. 2025PhysGen: Physically Grounded 3D Shape Generation for Industrial Designcited by 6
  16. 2025Topology Sculptor, Shape Refiner: Discrete Diffusion Model for High-Fidelity 3D Meshes Generationcited by 5
  17. 2025MoCA: Mixture-of-Components Attention for Scalable Compositional 3D Generationcited by 5
  18. 2026Optimization and Generation in Aerodynamics Inverse Designcited by 5
  19. 2026CubePart: An Open-Vocabulary Part-Controllable 3D Generatorcited by 5
  20. 2026A Definition and Roadmap for World Modelscited by 5
  21. 2025Native 3D Editing with Full Attentioncited by 4
  22. 2026Syn4D: A Multiview Synthetic 4D Datasetcited by 4
  23. 2026Generative 3D Gaussians with Learned Density Controlcited by 4
  24. 2026Procedura: Agentic 3D Modeling with Procedural Controlcited by 4
  25. 2025PoseMaster: A Unified 3D Native Framework for Stylized Pose Generationcited by 3
  26. 2025SAT-SKYLINES: 3D Building Generation from Satellite Imagery and Coarse Geometric Priorscited by 3
  27. 2025UrbanWorld2.0: A Multimodal Agentic Framework for Reality-Aligned 3D World Generation at City-Scalecited by 3
  28. 2025CaliTex: Geometry-Calibrated Attention for View-Coherent 3D Texture Generationcited by 3
  29. 2025Self-Evolving 3D Scene Generation from a Single Imagecited by 3
  30. 2026CG-MLLM: Captioning and Generating 3D content via Multi-modal Large Language Modelscited by 3
  31. 2026Fast-SAM3D: 3Dfy Anything in Images but Fastercited by 3
  32. 2026Omni123: Exploring 3D Native Foundation Models with Limited 3D Data by Unifying Text to 2D and 3D Generationcited by 3
  33. 2026OpenWorldLib: A Unified Codebase and Definition of Advanced World Modelscited by 3
  34. 2026ReplicateAnyScene: Zero-Shot Video-to-3D Composition via Textual-Visual-Spatial Alignmentcited by 3
  35. 2026Sculpt4D: Generating 4D Shapes via Sparse-Attention Diffusion Transformerscited by 3
  36. 2026The Many Senses of Visual Similarity: A Text-Prompted Image Perceptual Metriccited by 3
  37. 2026Axolotl3D: a Unified Framework for Faithful 3D Shape Completioncited by 3
  38. 2025RealMirror: A Comprehensive, Open-Source Vision-Language-Action Platform for Embodied AIcited by 2

50 most cited of 165 All 165 (JSON)