mlsanityData to 7 Oct 2026

An evaluation of SVBRDF Prediction from Generative Image Models for Appearance Modeling of 3D Scenes

arXiv 2512.13950 ↗First posted 15 Dec 2025cs.CV cs.GRcited by 0

Not on the map. Why?

Abstract (arXiv)

Digital content creation is experiencing a profound change with the advent of deep generative models. For texturing, conditional image generators now allow the synthesis of realistic RGB images of a 3D scene that align with the geometry of that scene. For appearance modeling, SVBRDF prediction networks recover material parameters from RGB images. Combining these technologies allows us to quickly generate SVBRDF maps for multiple views of a 3D scene, which can be merged to form a SVBRDF texture atlas of that scene. In this paper, we analyze the challenges and opportunities for SVBRDF prediction in the context of such a fast appearance modeling pipeline. On the one hand, single-view SVBRDF predictions might suffer from multiview incoherence and yield inconsistent texture atlases. On the other hand, generated RGB images, and the different modalities on which they are conditioned, can provide additional information for SVBRDF estimation compared to photographs. We compare neural architectures and conditions to identify designs that achieve high accuracy and coherence. We find that, surprisingly, a standard UNet is competitive with more complex designs. Project page: http://repo-sam.inria.fr/nerphys/svbrdf-evaluation

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 65 of its 79 references that are in the map. First posted on arXiv 15 Dec 2025.

Builds on

65 of 79 references.

References · 65

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2020Denoising Diffusion Implicit Modelscited by 9,655
  5. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  6. 2022Scalable Diffusion Models with Transformerscited by 5,931
  7. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  8. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
  9. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  10. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,483
  11. 2023IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Modelscited by 1,439
  12. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,285
38 more
  1. 2021Blended Diffusion for Text-driven Editing of Natural Imagescited by 924
  2. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 834
  3. 2021Label-Efficient Semantic Segmentation with Diffusion Modelscited by 495
  4. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assetscited by 444
  5. 2023TEXTure: Text-Guided Texturing of 3D Shapescited by 303
  6. 2023Unleashing Text-to-Image Diffusion Models for Visual Perceptioncited by 266
  7. 2021DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effortcited by 264
  8. 2023Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Modelscited by 245
  9. 2023Text2Tex: Text-driven Texture Synthesis via Diffusion Modelscited by 234
  10. 2023Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifoldcited by 218
  11. 2023Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondencecited by 211
  12. 2023MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusioncited by 210
  13. 2019Inverse Rendering for Complex Indoor Scenes: Shape, Spatially-Varying Lighting and SVBRDF from a Single Imagecited by 202
  14. 2024RGBleftrightarrowX: Image decomposition and synthesis using material- and lighting-aware diffusion modelscited by 159
  15. 2024MeshLRM: Large Reconstruction Model for High-Quality Meshescited by 138
  16. 2023State of the Art on Diffusion Models for Visual Computingcited by 126
  17. 2023Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Modelscited by 122
  18. 2023Unsupervised Semantic Correspondence Using Stable Diffusioncited by 120
  19. 2018Single-Image SVBRDF Capture with a Rendering-Aware Deep Networkcited by 116
  20. 2024StopThePop: Sorted Gaussian Splatting for View-Consistent Real-time Renderingcited by 107
  21. 2023Text-Guided Texturing by Synchronized Multi-View Diffusioncited by 86
  22. 2023Paint-it: Text-to-Texture Synthesis via Deep Convolutional Texture Map Optimization and Physically-Based Renderingcited by 84
  23. 2022Learning-based Inverse Rendering of Complex Indoor Scenes with Differentiable Monte Carlo Raytracingcited by 78
  24. 2024What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?cited by 74
  25. 2023Intrinsic Image Diffusion for Indoor Single-view Material Estimationcited by 73
  26. 2019Inverse Path Tracing for Joint Material and Lighting Estimationcited by 62
  27. 2021Deep Polarization Imaging for 3D shape and SVBRDF Acquisitioncited by 56
  28. 2024FlashTex: Fast Relightable Mesh Texturing with LightControlNetcited by 56
  29. 2025DiffusionRenderer: Neural Inverse and Forward Rendering with Video Diffusion Modelscited by 55
  30. 2023Readout Guidance: Learning Control from Diffusion Featurescited by 52
  31. 2024TextureDreamer: Image-guided Texture Synthesis through Geometry-aware Diffusioncited by 51
  32. 2019Flexible SVBRDF Capture with a Multi-Image Deep Networkcited by 50
  33. 2023ControlMat: A Controlled Generative Approach to Material Capturecited by 50
  34. 2024DreamMat: High-quality PBR Material Generation with Geometry- and Light-aware Diffusion Modelscited by 50
  35. 2023StyleGAN knows Normal, Depth, Albedo, and Morecited by 44
  36. 2023SceneTex: High-Quality Texture Synthesis for Indoor Scenes via Diffusion Priorscited by 43
  37. 2024Material Anything: Generating Materials for Any 3D Object via Diffusioncited by 31
  38. 2023Beyond Surface Statistics: Scene Representations in a Latent Diffusion Modelcited by 29

50 most cited of 65 All 65 (JSON)

Built on by

Not cited yet.