mlsanityData to 14 Oct 2026

Generative Modelling of BRDF Textures from Flash Images

arXiv 2102.11861 ↗First posted 23 Feb 2021cs.GR cs.CV cs.LGcited by 35

Not on the map. Why?

Abstract (arXiv)

We learn a latent space for easy capture, consistent interpolation, and efficient reproduction of visual material appearance. When users provide a photo of a stationary natural material captured under flashlight illumination, first it is converted into a latent material code. Then, in the second step, conditioned on the material code, our method produces an infinite and diverse spatial field of BRDF model parameters (diffuse albedo, normals, roughness, specular albedo) that subsequently allows rendering in complex scenes and illuminations, matching the appearance of the input photograph. Technically, we jointly embed all flash images into a latent space using a convolutional encoder, and -- conditioned on these latent codes -- convert random spatial fields into fields of BRDF parameters using a convolutional neural network (CNN). We condition these BRDF parameters to match the visual characteristics (statistics and spectra of visual features) of the input under matching light. A user study compares our approach favorably to previous work, even those with access to BRDF supervision.

Key facts. Cited by 35 papers in the map (data through 14 Oct 2026). Builds on 27 of its 68 references that are in the map. First posted on arXiv 23 Feb 2021.

Builds on

27 of 68 references.

References · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  5. 2013Auto-Encoding Variational Bayescited by 4,053
  6. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  7. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 2,010
  8. 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
  9. 2017Improved Texture Networks: Maximizing Quality and Diversity in Feed-forward Stylization and Texture Synthesiscited by 215
  10. 2016Texture Networks: Feed-forward Synthesis of Textures and Stylized Imagescited by 174
  11. 2018Single-Image SVBRDF Capture with a Rendering-Aware Deep Networkcited by 116
  12. 2018Non-Stationary Texture Synthesis by Adversarial Expansioncited by 67
15 more
  1. 2018Materials for Masses: SVBRDF Acquisition with a Single Mobile Phone Imagecited by 66
  2. 2020Two-shot Spatially-varying BRDF and Shape Estimationcited by 59
  3. 2017Learning Texture Manifolds with the Periodic Spatial GANcited by 53
  4. 2019Learning a Neural 3D Texture Space from 2D Exemplarscited by 53
  5. 2018Modeling Surface Appearance from a Single Photograph using Self-augmented Convolutional Neural Networkscited by 51
  6. 2019Flexible SVBRDF Capture with a Multi-Image Deep Networkcited by 50
  7. 2020MaterialGAN: Reflectance Capture using a Generative SVBRDF Modelcited by 33
  8. 2020Guided Fine-Tuning for Large-Scale Material Transfercited by 27
  9. 2017Material Editing Using a Physically Based Rendering Networkcited by 17
  10. 2019Synthesizing 3D Shapes from Silhouette Image Collections using Multi-projection Generative Adversarial Networkscited by 14
  11. 2015Deep Reflectance Mapscited by 13
  12. 2019A Bayesian Inference Framework for Procedural Material Parameter Estimationcited by 11
  13. 2018An intuitive control space for material appearancecited by 10
  14. 2016Texture Synthesis Through Convolutional Neural Networks and Spectrum Constraintscited by 8
  15. 2018Gaussian Material Synthesiscited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 2; 2022: 8; 2023: 6; 2024: 11; 2025: 7; 2026: 1.

35 papers.

Sort:

By area:

  1. 2021Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decompositioncited by 205
  2. 2022SAMURAI: Shape And Material from Unconstrained Real-world Arbitrary Image collectionscited by 89
  3. 2023ControlMat: A Controlled Generative Approach to Material Capturecited by 50
  4. 2024MatSynth: A Modern PBR Materials Datasetcited by 42
  5. 2024MatFusion: A Generative Diffusion Model for SVBRDF Capturecited by 31
  6. 2022TileGen: Tileable, Controllable Material Generation and Capturecited by 27
  7. 2023Materialistic: Selecting Similar Materials in Imagescited by 26
  8. 2022PhotoScene: Photorealistic Material and Lighting Transfer for Indoor Scenescited by 22
  9. 2024BlenderAlchemy: Editing 3D Graphics with Vision-Language Modelscited by 22
  10. 2022SeamlessGAN: Self-Supervised Synthesis of Tileable Texture Mapscited by 19
  11. 2023PhotoMat: A Material Generator Learned from Single Flash Photoscited by 18
  12. 2024Objects With Lighting: A Real-World Dataset for Evaluating Reconstruction and Rendering for Object Relightingcited by 18
23 more
  1. 2024SHINOBI: Shape and Illumination using Neural Object Decomposition via BRDF Optimization In-the-wildcited by 18
  2. 2023UMat: Uncertainty-Aware Single Image High Resolution Material Capturecited by 11
  3. 2022Learning to Learn and Sample BRDFscited by 9
  4. 2025VLMaterial: Procedural Material Generation with Large Vision-Language Modelscited by 9
  5. 2025SViM3D: Stable Video Material Diffusion for Single Image 3D Generationcited by 7
  6. 2025Chord: Chain of Rendering Decomposition for PBR Material Estimation from Generated Texture Imagescited by 5
  7. 2021SVBRDF Recovery From a Single Image With Highlights using a Pretrained Generative Adversarial Networkcited by 4
  8. 2024Uncertainty for SVBRDF Acquisition using Frequency Analysiscited by 4
  9. 2022Efficient Reflectance Capture with a Deep Gated Mixture-of-Expertscited by 3
  10. 2023Retargeting Visual Data with Deformation Fieldscited by 3
  11. 2024FROST-BRDF: A Fast and Robust Optimal Sampling Technique for BRDF Acquisitioncited by 3
  12. 2022Real-time Virtual-Try-On from a Single Example Image through Deep Inverse Graphics and Learned Differentiable Rendererscited by 2
  13. 2023Tree-Structured Shading Decompositioncited by 2
  14. 2024DreamPBR: Text-driven Generation of High-resolution SVBRDF with Multi-modal Guidancecited by 2
  15. 2024Content-aware Tile Generation using Exterior Boundary Inpaintingcited by 2
  16. 2025On Neural BRDFs: A Thorough Comparison of State-of-the-Art Approachescited by 2
  17. 2024FabricDiffusion: High-Fidelity Texture Transfer for 3D Garments Generation from In-The-Wild Clothing Imagescited by 1
  18. 2024Neural Differential Appearance Equationscited by 1
  19. 2025Single-image Reflectance and Transmittance Estimation from Any Flatbed Scannercited by 1
  20. 2025DualMat: PBR Material Estimation via Coherent Dual-Path Diffusioncited by 1
  21. 2025RealMat: Realistic Materials with Diffusion and Reinforcement Learningcited by 1
  22. 2022Deep scene-scale material estimation from multi-view indoor capturescited by 0
  23. 2026DealMaTe: Multi-Dimensional Material Transfer via Diffusion Transformercited by 0