mlsanityData to 14 Oct 2026

MaterialMVP: Illumination-Invariant Material Generation via Multi-view PBR Diffusion

arXiv 2503.10289 ↗First posted 13 Mar 2025cs.CVcited by 28

Not on the map. Why?

Abstract (arXiv)

Physically-based rendering (PBR) has become a cornerstone in modern computer graphics, enabling realistic material representation and lighting interactions in 3D scenes. In this paper, we present MaterialMVP, a novel end-to-end model for generating PBR textures from 3D meshes and image prompts, addressing key challenges in multi-view material synthesis. Our approach leverages Reference Attention to extract and encode informative latent from the input reference images, enabling intuitive and controllable texture generation. We also introduce a Consistency-Regularized Training strategy to enforce stability across varying viewpoints and illumination conditions, ensuring illumination-invariant and geometrically consistent results. Additionally, we propose Dual-Channel Material Generation, which separately optimizes albedo and metallic-roughness (MR) textures while maintaining precise spatial alignment with the input images through Multi-Channel Aligned Attention. Learnable material embeddings are further integrated to capture the distinct properties of albedo and MR. Experimental results demonstrate that our model generates PBR textures with realistic behavior across diverse lighting scenarios, outperforming existing methods in both consistency and quality for scalable 3D asset creation.

Key facts. Cited by 28 papers in the map (data through 14 Oct 2026). Builds on 70 of its 77 references that are in the map. First posted on arXiv 13 Mar 2025.

Builds on

70 of 77 references.

References · 70

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2020Denoising Diffusion Implicit Modelscited by 9,781
  4. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  5. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
  6. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
  7. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,540
  8. 2023IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Modelscited by 1,464
  9. 2023MVDream: Multi-view Diffusion for 3D Generationcited by 938
  10. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 774
  11. 2023Wonder3D: Single Image to 3D using Cross-Domain Diffusioncited by 689
  12. 2023Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creationcited by 687
38 more
  1. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Imagecited by 645
  2. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 560
  3. 2023Zero123++: a Single Image to Consistent Multi-view Diffusion Base Modelcited by 521
  4. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assetscited by 455
  5. 2023Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Modelcited by 378
  6. 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generationcited by 356
  7. 2023Common Diffusion Noise Schedules and Sample Steps are Flawedcited by 310
  8. 2023TEXTure: Text-Guided Texturing of 3D Shapescited by 304
  9. 2024Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understandingcited by 298
  10. 2023One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusioncited by 283
  11. 2023ImageDream: Image-Prompt Multi-view Diffusion for 3D Generationcited by 257
  12. 2023Text2Tex: Text-driven Texture Synthesis via Diffusion Modelscited by 235
  13. 2024RGBleftrightarrowX: Image decomposition and synthesis using material- and lighting-aware diffusion modelscited by 161
  14. 2024Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Imagecited by 135
  15. 2023Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Modelscited by 123
  16. 2024Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attentioncited by 100
  17. 2024MVDiffusion++: A Dense High-resolution Multi-view Diffusion Model for Single or Sparse-view 3D Object Reconstructioncited by 95
  18. 2023TexFusion: Synthesizing 3D Textures with Text-Guided Image Diffusion Modelscited by 87
  19. 2023Text-Guided Texturing by Synchronized Multi-View Diffusioncited by 86
  20. 2023Paint-it: Text-to-Texture Synthesis via Deep Convolutional Texture Map Optimization and Physically-Based Renderingcited by 84
  21. 2024Hunyuan3D 1.0: A Unified Framework for Text-to-3D and Image-to-3D Generationcited by 82
  22. 2023EpiDiff: Enhancing Multi-View Synthesis via Localized Epipolar-Constrained Diffusioncited by 72
  23. 2024IntrinsicAnything: Learning Diffusion Priors for Inverse Rendering Under Unknown Illuminationcited by 67
  24. 2023ConsistNet: Enforcing 3D Consistency for Multi-view Images Diffusioncited by 65
  25. 2023Texture Generation on 3D Meshes with Point-UV Diffusioncited by 63
  26. 2024SPAD : Spatially Aware Multiview Diffuserscited by 62
  27. 2024ViewDiff: 3D-Consistent Image Generation with Text-to-Image Modelscited by 57
  28. 2024FlashTex: Fast Relightable Mesh Texturing with LightControlNetcited by 56
  29. 2024TextureDreamer: Image-guided Texture Synthesis through Geometry-aware Diffusioncited by 52
  30. 2024Meta 3D TextureGen: Fast and Consistent Texture Generation for 3D Objectscited by 52
  31. 2023Direct2.5: Diverse Text-to-3D Generation via Multi-view 2.5D Diffusioncited by 50
  32. 2024DreamMat: High-quality PBR Material Generation with Geometry- and Light-aware Diffusion Modelscited by 50
  33. 2023UniDream: Unifying Diffusion Priors for Relightable Text-to-3D Generationcited by 47
  34. 2024TEXGen: a Generative Diffusion Model for Mesh Texturescited by 46
  35. 2023SceneTex: High-Quality Texture Synthesis for Indoor Scenes via Diffusion Priorscited by 43
  36. 2023MatFuse: Controllable Material Generation with Diffusion Modelscited by 39
  37. 2024MVD-Fusion: Single-view 3D via Depth-consistent Multi-view Generationcited by 35
  38. 2023Cascade-Zero123: One Image to Highly Consistent 3D with Self-Prompted Nearby Viewscited by 33

50 most cited of 70 All 70 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 14; 2026: 14.

28 papers.

Sort:

By area:

  1. 2025Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Detailscited by 125
  2. 2025Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assetscited by 22
  3. 2025Seed3D 1.0: From Images to High-Fidelity Simulation-Ready 3D Assetscited by 20
  4. 2025Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generationcited by 13
  5. 2025Video Perception Models for 3D Scene Synthesiscited by 7
  6. 2025NaTex: Seamless Texture Generation as Latent Color Diffusioncited by 7
  7. 2025ZeroScene: A Zero-Shot Framework for 3D Scene Generation from a Single Image and Controllable Texture Editingcited by 5
  8. 2025LaFiTe: A Generative Latent Field for 3D Native Texturingcited by 4
  9. 2025MatPedia: A Universal Generative Foundation for High-Fidelity Material Synthesiscited by 3
  10. 2026VideoMatGen: PBR Materials through Joint Generative Modelingcited by 3
  11. 2026ROAR-3D: Routing Arbitrary Views for High-Fidelity 3D Generationcited by 3
  12. 2025NI-Tex: Non-isometric Image-based Garment Texture Generationcited by 2
16 more
  1. 2025MatMart: Material Reconstruction of 3D Objects via Diffusioncited by 2
  2. 2025LumiTex: Towards High-Fidelity PBR Texture Generation with Illumination Contextcited by 2
  3. 2025Photo3D: Advancing Photorealistic 3D Generation through Structure-Aligned Detail Enhancementcited by 2
  4. 2026Hitem3D 2.0: Multi-View Guided Native 3D Texture Generationcited by 2
  5. 2026Does Native 3D Texture Generation Necessarily Require 3D Assets for Training?cited by 2
  6. 2025MatLat: Material Latent Space for PBR Texture Generationcited by 1
  7. 2026MV2UV: Generating High-quality UV Texture Maps with Multiview Promptscited by 1
  8. 2026Towards Realistic 3D Emission Materials: Dataset, Baseline, and Evaluation for Emission Texture Generationcited by 0
  9. 2026Advances in Neural 3D Mesh Texturing: A Surveycited by 0
  10. 2026Property-Informed Diffusion-Based Text-to-Microstructure Generationcited by 0
  11. 2026HAFMat: Hybrid Priors Guided Adaptive Fusion for Single-Image Human Material Estimationcited by 0
  12. 2026RealSkin: Spatio-Spectral Partial Neural Adjoint Maps for Image-to-3D Attribute Transfercited by 0
  13. 2026GLOSS: Geometric Local Self-Similarity Learning for Faithful Reference-Guided Texture Fillcited by 0
  14. 2026Learning 3D Editing without Paired Supervision via Generative Prior Distillationcited by 0
  15. 2026TaoTex: Boosting Texture Detail Fidelity for Native 3D Material Generationcited by 0
  16. 2026Texture Space Material Diffusioncited by 0