mlsanityData to 14 Oct 2026

Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details

arXiv 2506.16504 ↗First posted 19 Jun 2025cs.CV cs.AIcited by 125

On the map: Diffusion models → 3D, point cloud and scene generation

Abstract (arXiv)

In this report, we present Hunyuan3D 2.5, a robust suite of 3D diffusion models aimed at generating high-fidelity and detailed textured 3D assets. Hunyuan3D 2.5 follows two-stages pipeline of its previous version Hunyuan3D 2.0, while demonstrating substantial advancements in both shape and texture generation. In terms of shape generation, we introduce a new shape foundation model -- LATTICE, which is trained with scaled high-quality datasets, model-size, and compute. Our largest model reaches 10B parameters and generates sharp and detailed 3D shape with precise image-3D following while keeping mesh surface clean and smooth, significantly closing the gap between generated and handcrafted 3D shapes. In terms of texture generation, it is upgraded with phyiscal-based rendering (PBR) via a novel multi-view architecture extended from Hunyuan3D 2.0 Paint model. Our extensive evaluation shows that Hunyuan3D 2.5 significantly outperforms previous methods in both shape and end-to-end texture generation.

Key facts. Cited by 125 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 63 of its 67 references that are in the map. First posted on arXiv 19 Jun 2025.

Builds on

63 of 67 references.

Closest ancestors · 33

Same direction, newest first

  1. 2025RomanTex: Decoupling 3D-aware Rotary Positional Embedded Multi-Attention Network for Texture Synthesis24 Mar
  2. 2025Unleashing Vecset Diffusion Model for Fast Shape Generation20 Mar
  3. 2025TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models10 Feb
  4. 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation21 Jan
  5. 2024Material Anything: Generating Materials for Any 3D Object via Diffusion22 Nov
  6. 2024TEXGen: a Generative Diffusion Model for Mesh Textures22 Nov
  7. 2024Hunyuan3D 1.0: A Unified Framework for Text-to-3D and Image-to-3D Generation4 Nov
  8. 2024Jointly Generating Multi-view Consistent PBR Textures using Collaborative Control9 Oct
  9. 2024VCD-Texture: Variance Alignment based 3D-2D Co-Denoising for Text-Guided Texturing5 Jul
  10. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets30 May
  11. 2024DreamMat: High-quality PBR Material Generation with Geometry- and Light-aware Diffusion Models27 May
  12. 2024Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer23 May
21 more
  1. 2024TexPainter: Generative Mesh Texturing with Multi-view Consistency17 May
  2. 2024RGBleftrightarrowX: Image decomposition and synthesis using material- and lighting-aware diffusion models1 May
  3. 2024MaPa: Text-driven Photorealistic Material Painting for 3D Shapes26 Apr
  4. 2024MatFusion: A Generative Diffusion Model for SVBRDF Capture24 Apr
  5. 2024IntrinsicAnything: Learning Diffusion Priors for Inverse Rendering Under Unknown Illumination17 Apr
  6. 2024GenesisTex: Adapting Image Denoising Diffusion to Texture Space26 Mar
  7. 2024MVDiffusion++: A Dense High-resolution Multi-view Diffusion Model for Single or Sparse-view 3D Object Reconstruction20 Feb
  8. 2023Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models21 Dec
  9. 2023UniDream: Unifying Diffusion Priors for Relightable Text-to-3D Generation14 Dec
  10. 2023ImageDream: Image-Prompt Multi-view Diffusion for 3D Generation2 Dec
  11. 2023Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model23 Oct
  12. 2023Wonder3D: Single Image to 3D using Cross-Domain Diffusion23 Oct
  13. 2023MVDream: Multi-view Diffusion for 3D Generation31 Aug
  14. 2023MatFuse: Controllable Material Generation with Diffusion Models22 Aug
  15. 2023MATLABER: Material-Aware Text-to-3D via LAtent BRDF auto-EncodeR18 Aug
  16. 2023Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation24 Mar
  17. 2023Text2Tex: Text-driven Texture Synthesis via Diffusion Models20 Mar
  18. 2023Zero-1-to-3: Zero-shot One Image to 3D Object20 Mar
  19. 2023TEXTure: Text-Guided Texturing of 3D Shapes3 Feb
  20. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models26 Jan
  21. 2022DreamFusion: Text-to-3D using 2D Diffusion29 Sep

Other references · 30

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
  4. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,323
  5. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 849
  6. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 770
  7. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 739
  8. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  9. 2023UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Modelscited by 450
  10. 2022ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understandingcited by 267
  11. 2023MeshGPT: Generating Triangle Meshes with Decoder-Only Transformerscited by 259
  12. 2021CLIP-Forge: Towards Zero-Shot Text-to-Shape Generationcited by 254
18 more
  1. 2023Uni3D: Exploring Unified 3D Representation at Scalecited by 237
  2. 2023Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representationcited by 228
  3. 2023MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusioncited by 212
  4. 2025Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Materialcited by 165
  5. 2024MV-Adapter: Multi-view Consistent Image Generation Made Easycited by 112
  6. 2022ShapeFormer: Transformer-based Shape Completion via Sparse Representationcited by 106
  7. 2024Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attentioncited by 100
  8. 2024Meshtron: High-Fidelity, Artist-Like 3D Mesh Generation at Scalecited by 89
  9. 2023Text-Guided Texturing by Synchronized Multi-View Diffusioncited by 86
  10. 2023Paint-it: Text-to-Texture Synthesis via Deep Convolutional Texture Map Optimization and Physically-Based Renderingcited by 84
  11. 2024Scaling Mesh Generation via Compressive Tokenizationcited by 73
  12. 2024TextureDreamer: Image-guided Texture Synthesis through Geometry-aware Diffusioncited by 52
  13. 2023ShapeGPT: 3D Shape Generation with A Unified Multi-modal Language Modelcited by 39
  14. 2025MaterialMVP: Illumination-Invariant Material Generation via Multi-view PBR Diffusioncited by 28
  15. 2024Collaborative Control for Geometry-Conditioned PBR Image Generationcited by 22
  16. 2023HyperDreamer: Hyper-Realistic 3D Content Generation and Editing from a Single Imagecited by 17
  17. 2024MatAtlas: Text-driven Consistent Geometry Texturing and Material Assignmentcited by 14
  18. 2024TexRO: Generating Delicate Textures of 3D Models by Recursive Optimizationcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 31; 2026: 94.

125 papers.

Sort:

By area:

  1. 2025TexVerse: A Universe of 3D Objects with High-Resolution Texturescited by 45
  2. 2025X-Part: high fidelity and structure coherent shape decompositioncited by 44
  3. 2025NANO3D: A Training-Free Approach for Efficient 3D Editing Without Maskscited by 31
  4. 2026LLM-as-a-Verifier: A General-Purpose Verification Frameworkcited by 30
  5. 2025Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assetscited by 22
  6. 2025UniLat3D: Geometry-Appearance Unified Latents for Single-Stage 3D Generationcited by 20
  7. 2025PartSAM: A Scalable Promptable Part Segmentation Model Trained on Native 3D Datacited by 16
  8. 2026ActionMesh: Animated 3D Mesh Generation with Temporal 3D Diffusioncited by 16
  9. 2025HOLODECK 2.0: Vision-Language-Guided 3D World Generation with Editingcited by 15
  10. 2026Motion 3-to-4: 3D Motion Reconstruction for 4D Synthesiscited by 15
  11. 2025Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generationcited by 13
  12. 2025QuadGPT: Native Quadrilateral Mesh Generation with Autoregressive Modelscited by 12
38 more
  1. 2026GeoPT: Scaling Physics Simulation via Lifted Geometric Pre-Trainingcited by 10
  2. 2025Yo'City: Personalized and Boundless 3D Realistic City Scene Generation via Self-Critic Expansioncited by 9
  3. 2025MeshMosaic: Scaling Artist Mesh Generation via Local-to-Global Assemblycited by 8
  4. 2026Elastic Diffusion Transformercited by 8
  5. 2026PAct: Part-Decomposed Single-View Articulated Object Generationcited by 8
  6. 2026ArtLLM: Generating Articulated Assets via 3D LLMcited by 8
  7. 2026WorldClaw: Agentic 3D Open-World Generation at Scalecited by 8
  8. 2025Sat2RealCity: Geometry-Aware and Appearance-Controllable 3D Urban Generation from Satellite Imagerycited by 7
  9. 2025Part-X-MLLM: Part-aware 3D Multimodal Large Language Modelcited by 7
  10. 2025NaTex: Seamless Texture Generation as Latent Color Diffusioncited by 7
  11. 2025MajutsuCity: Language-driven Aesthetic-adaptive City Generation with Controllable 3D Assets and Layoutscited by 6
  12. 2025PhysGen: Physically Grounded 3D Shape Generation for Industrial Designcited by 6
  13. 2026EmbodiedGen V2: An Agentic, Simulation-Ready 3D World Engine for Embodied AIcited by 6
  14. 2025ZeroScene: A Zero-Shot Framework for 3D Scene Generation from a Single Image and Controllable Texture Editingcited by 5
  15. 2025Topology Sculptor, Shape Refiner: Discrete Diffusion Model for High-Fidelity 3D Meshes Generationcited by 5
  16. 2026MonoArt: Progressive Structural Reasoning for Monocular Articulated 3D Reconstructioncited by 5
  17. 2026SIMART: Decomposing Monolithic Meshes into Sim-ready Articulated Assets via MLLMcited by 5
  18. 2025VaseVQA-3D: Benchmarking 3D VLMs on Ancient Greek Potterycited by 4
  19. 2026MorphAny3D: Unleashing the Power of Structured Latent in 3D Morphingcited by 4
  20. 2026PrevizWhiz: Combining Rough 3D Scenes and 2D Video to Guide Generative Video Previsualizationcited by 4
  21. 2026AGILE: Hand-Object Interaction Reconstruction from Video via Agentic Generationcited by 4
  22. 2026ArtHOI: Taming Foundation Models for Monocular 4D Reconstruction of Hand-Articulated-Object Interactionscited by 4
  23. 2026Mix3R: Mixing Feed-forward Reconstruction and Generative 3D Priors for Joint Multi-view Aligned 3D Reconstruction and Pose Estimationcited by 4
  24. 2026PhysOmni: Physics-Grounded Multi-Object Scene Generation from a Single Image with Real-Time Interactioncited by 4
  25. 2026Instruct-Particulate: Scaling Feed-Forward 3D Object Articulation with Kinematic Controlcited by 4
  26. 2025PoseMaster: A Unified 3D Native Framework for Stylized Pose Generationcited by 3
  27. 2025Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validitycited by 3
  28. 2025SAT-SKYLINES: 3D Building Generation from Satellite Imagery and Coarse Geometric Priorscited by 3
  29. 2025CraftMesh: High-Fidelity Generative Mesh Manipulation via Poisson Seamless Fusioncited by 3
  30. 2025CaliTex: Geometry-Calibrated Attention for View-Coherent 3D Texture Generationcited by 3
  31. 2025TabletopGen: Tabletop Scene Generation and Interactive Simulation for Robotic Manipulationcited by 3
  32. 2026Mesh-Pro: Asynchronous Advantage-guided Ranking Preference Optimization for Artist-style Quadrilateral Mesh Generationcited by 3
  33. 2026Omni123: Exploring 3D Native Foundation Models with Limited 3D Data by Unifying Text to 2D and 3D Generationcited by 3
  34. 2026StoryBlender: Inter-Shot Consistent and Editable 3D Storyboard with Spatial-temporal Dynamicscited by 3
  35. 2026Grasp in Gaussians: Fast Monocular Reconstruction of Dynamic Hand-Object Interactionscited by 3
  36. 2026ROAR-3D: Routing Arbitrary Views for High-Fidelity 3D Generationcited by 3
  37. 2026Direct 3D-Aware Object Insertion via Decomposed Visual Proxiescited by 3
  38. 2026φ-Scene: Physically Grounded Image-to-3D Scene Reconstructioncited by 3

50 most cited of 125 All 125 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets
  2. 20243DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion
  3. 2025Kiss3DGen: Repurposing Image Diffusion Models for 3D Asset Generation
  4. 2025MVPainter: Accurate and Detailed 3D Texture Generation via Multi-View Diffusion with Geometric Control
  5. 2023DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior
  6. 2026Home3D 1.0: A High-Fidelity Image-to-3D Asset Generation System for Interior Design
  7. 2025MeshGen: Generating PBR Textured Mesh with Render-Enhanced Auto-Encoder and Generative Data Augmentation
  8. 2023One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion