mlsanityData to 14 Oct 2026

Single-image Reflectance and Transmittance Estimation from Any Flatbed Scanner

arXiv 2502.14462 ↗First posted 20 Feb 2025cs.GR cs.AI cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Flatbed scanners have emerged as promising devices for high-resolution, single-image material capture. However, existing approaches assume very specific conditions, such as uniform diffuse illumination, which are only available in certain high-end devices, hindering their scalability and cost. In contrast, in this work, we introduce a method inspired by intrinsic image decomposition, which accurately removes both shading and specularity, effectively allowing captures with any flatbed scanner. Further, we extend previous work on single-image material reflectance capture with the estimation of opacity and transmittance, critical components of full material appearance (SVBSDF), improving the results for any material captured with a flatbed scanner, at a very high resolution and accuracy

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 34 of its 70 references that are in the map. First posted on arXiv 20 Feb 2025.

Builds on

34 of 70 references.

References · 34

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  3. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  4. 2017Mixed Precision Trainingcited by 1,156
  5. 2015A Neural Algorithm of Artistic Stylecited by 483
  6. 2019Kornia: an Open Source Differentiable Computer Vision Library for PyTorchcited by 232
  7. 2022Dual Diffusion Implicit Bridges for Image-to-Image Translationcited by 213
  8. 2020Focal Frequency Loss for Image Reconstruction and Synthesiscited by 206
  9. 2017Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removalcited by 161
  10. 2018Single-Image SVBRDF Capture with a Rendering-Aware Deep Networkcited by 116
  11. 2021Auto-Exposure Fusion for Single-Image Shadow Removalcited by 79
  12. 2022Learning to Relight Portrait Images via a Virtual Light Stage and Synthetic-to-Real Adaptationcited by 67
22 more
  1. 2022Unifying Diffusion Models' Latent Space, with Applications to CycleDiffusion and Guidancecited by 67
  2. 2018Materials for Masses: SVBRDF Acquisition with a Single Mobile Phone Imagecited by 66
  3. 2017CycleGAN, a Master of Steganographycited by 65
  4. 2018VisemeNet: Audio-Driven Animator-Centric Speech Animationcited by 63
  5. 2023ControlMat: A Controlled Generative Approach to Material Capturecited by 50
  6. 2019CycleGAN-VC2: Improved CycleGAN-based Non-parallel Voice Conversioncited by 46
  7. 2023MatFuse: Controllable Material Generation with Diffusion Modelscited by 39
  8. 2021A Survey on Intrinsic Images: Delving Deep Into Lambert and Beyondcited by 37
  9. 2021Generative Modelling of BRDF Textures from Flash Imagescited by 35
  10. 2022Geometry-aware Single-image Full-body Human Relightingcited by 34
  11. 2022De-rendering 3D Objects in the Wildcited by 31
  12. 2024MatFusion: A Generative Diffusion Model for SVBRDF Capturecited by 31
  13. 2021Single-image Full-body Human Relightingcited by 30
  14. 2022TileGen: Tileable, Controllable Material Generation and Capturecited by 27
  15. 2021SurfaceNet: Adversarial SVBRDF Estimation from a Single Imagecited by 25
  16. 2021An Inverse Procedural Modeling Pipeline for SVBRDF Mapscited by 24
  17. 2022SeamlessGAN: Self-Supervised Synthesis of Tileable Texture Mapscited by 19
  18. 2019A Bayesian Inference Framework for Procedural Material Parameter Estimationcited by 11
  19. 2023UMat: Uncertainty-Aware Single Image High Resolution Material Capturecited by 11
  20. 2021Neural Photometry-guided Visual Attribute Transfercited by 6
  21. 2023NeuBTF: Neural fields for BTF encoding and transfercited by 5
  22. 2021SVBRDF Recovery From a Single Image With Highlights using a Pretrained Generative Adversarial Networkcited by 4

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025ePBR: Extended PBR Materials in Image Synthesiscited by 3