mlsanityData to 7 Oct 2026

Flexible SVBRDF Capture with a Multi-Image Deep Network

arXiv 1906.11557 ↗First posted 27 Jun 2019cs.GRcited by 50

Not on the map. Why?

Abstract (arXiv)

Empowered by deep learning, recent methods for material capture can estimate a spatially-varying reflectance from a single photograph. Such lightweight capture is in stark contrast with the tens or hundreds of pictures required by traditional optimization-based approaches. However, a single image is often simply not enough to observe the rich appearance of real-world materials. We present a deep-learning method capable of estimating material appearance from a variable number of uncalibrated and unordered pictures captured with a handheld camera and flash. Thanks to an order-independent fusing layer, this architecture extracts the most useful information from each picture, while benefiting from strong priors learned from data. The method can handle both view and light direction variation without calibration. We show how our method improves its prediction with the number of input pictures, and reaches high quality reconstructions with as little as 1 to 10 images -- a sweet spot between existing single-image and complex multi-image approaches.

Key facts. Cited by 50 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 12; 2023: 6; 2024: 10; 2025: 10; 2026: 3.

50 papers.

Sort:

By area:

  1. 2021ABO: Dataset and Benchmarks for Real-World 3D Object Understandingcited by 360
  2. 2021Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decompositioncited by 204
  3. 2022SAMURAI: Shape And Material from Unconstrained Real-world Arbitrary Image collectionscited by 89
  4. 2021Unified Shape and SVBRDF Recovery using Differentiable Monte Carlo Renderingcited by 71
  5. 2021Deep Polarization Imaging for 3D shape and SVBRDF Acquisitioncited by 56
  6. 2023ControlMat: A Controlled Generative Approach to Material Capturecited by 50
  7. 2024MatSynth: A Modern PBR Materials Datasetcited by 42
  8. 2023MatFuse: Controllable Material Generation with Diffusion Modelscited by 39
  9. 2021A Survey on Intrinsic Images: Delving Deep Into Lambert and Beyondcited by 37
  10. 2021Generative Modelling of BRDF Textures from Flash Imagescited by 35
  11. 2024MatFusion: A Generative Diffusion Model for SVBRDF Capturecited by 31
  12. 2022TileGen: Tileable, Controllable Material Generation and Capturecited by 27
38 more
  1. 2023Materialistic: Selecting Similar Materials in Imagescited by 26
  2. 2021SurfaceNet: Adversarial SVBRDF Estimation from a Single Imagecited by 25
  3. 2024ZeST: Zero-Shot Material Transfer from a Single Imagecited by 24
  4. 2022Multi-view Inverse Rendering for Large-scale Real-world Indoor Scenescited by 23
  5. 2022PhotoScene: Photorealistic Material and Lighting Transfer for Indoor Scenescited by 22
  6. 2022SeamlessGAN: Self-Supervised Synthesis of Tileable Texture Mapscited by 19
  7. 2023PhotoMat: A Material Generator Learned from Single Flash Photoscited by 18
  8. 2024SHINOBI: Shape and Illumination using Neural Object Decomposition via BRDF Optimization In-the-wildcited by 18
  9. 2024MaterialPicker: Multi-Modal DiT-Based Material Generationcited by 10
  10. 2024SAMa: Material-aware 3D Selection and Segmentationcited by 9
  11. 2025MARBLE: Material Recomposition and Blending in CLIP-Spacecited by 9
  12. 2023VQ-NeRF: Neural Reflectance Decomposition and Editing with Vector Quantizationcited by 8
  13. 2025SViM3D: Stable Video Material Diffusion for Single Image 3D Generationcited by 7
  14. 2021Neural Photometry-guided Visual Attribute Transfercited by 6
  15. 2021SVBRDF Recovery From a Single Image With Highlights using a Pretrained Generative Adversarial Networkcited by 4
  16. 2022KiloNeuS: A Versatile Neural Implicit Surface Representation for Real-Time Renderingcited by 4
  17. 2023JoIN: Joint GANs Inversion for Intrinsic Image Decompositioncited by 4
  18. 2024StableMaterials: Enhancing Diversity in Material Generation via Semi-Supervised Learningcited by 4
  19. 2024Uncertainty for SVBRDF Acquisition using Frequency Analysiscited by 4
  20. 2022Efficient Reflectance Capture with a Deep Gated Mixture-of-Expertscited by 3
  21. 2022Estimating Neural Reflectance Field from Radiance Field using Tree Structurescited by 2
  22. 2024DreamPBR: Text-driven Generation of High-resolution SVBRDF with Multi-modal Guidancecited by 2
  23. 2025RETRO: REthinking Tactile Representation Learning with Material PriOrscited by 1
  24. 2025DualMat: PBR Material Estimation via Coherent Dual-Path Diffusioncited by 1
  25. 2025RealMat: Realistic Materials with Diffusion and Reinforcement Learningcited by 1
  26. 2025Yesnt: Are Diffusion Relighting Models Ready for Capture Stage Compositing? A Hybrid Alternative to Bridge the Gapcited by 1
  27. 2022Diffuse Map Guiding Unsupervised Generative Adversarial Network for SVBRDF Estimationcited by 0
  28. 2022Deep Uncalibrated Photometric Stereo via Inter-Intra Image Feature Fusioncited by 0
  29. 2022NeIF: Representing General Reflectance as Neural Intrinsics Fields for Uncalibrated Photometric Stereocited by 0
  30. 2022Deep scene-scale material estimation from multi-view indoor capturescited by 0
  31. 2024Deep image-based Adaptive BRDF Measurecited by 0
  32. 2025HiMat: DiT-based Ultra-High Resolution SVBRDF Generationcited by 0
  33. 2025SpecGen: Neural Spectral BRDF Generation via Spectral-Spatial Tri-plane Aggregationcited by 0
  34. 2025Phieat: Physically Grounded Material Feature Representationcited by 0
  35. 2025An evaluation of SVBRDF Prediction from Generative Image Models for Appearance Modeling of 3D Scenescited by 0
  36. 2026Rendering-Aware Sparse Sampling for BRDF Acquisitioncited by 0
  37. 2026Feature-Guided Diffusion for Non-Differentiable Inverse Renderingcited by 0
  38. 2026MatLoom: Layered Text-to-Material Generation in a Compact Program Spacecited by 0