mlsanityData to 7 Oct 2026

Deep Polarization Cues for Single-shot Shape and Subsurface Scattering Estimation

arXiv 2407.08149 ↗First posted 11 Jul 2024cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

In this work, we propose a novel learning-based method to jointly estimate the shape and subsurface scattering (SSS) parameters of translucent objects by utilizing polarization cues. Although polarization cues have been used in various applications, such as shape from polarization (SfP), BRDF estimation, and reflection removal, their application in SSS estimation has not yet been explored. Our observations indicate that the SSS affects not only the light intensity but also the polarization signal. Hence, the polarization signal can provide additional cues for SSS estimation. We also introduce the first large-scale synthetic dataset of polarized translucent objects for training our model. Our method outperforms several baselines from the SfP and inverse rendering realms on both synthetic and real data, as demonstrated by qualitative and quantitative results.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 33 of its 79 references that are in the map. First posted on arXiv 11 Jul 2024.

Builds on

33 of 79 references.

References · 33

  1. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  2. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  3. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 721
  4. 2019Inverse Rendering for Complex Indoor Scenes: Shape, Spatially-Varying Lighting and SVBRDF from a Single Imagecited by 202
  5. 2017Learning to Predict Indoor Illumination from a Single Imagecited by 160
  6. 2018Single-Image SVBRDF Capture with a Rendering-Aware Deep Networkcited by 116
  7. 2019Neural Inverse Rendering of an Indoor Scene from a Single Imagecited by 101
  8. 2021Learning Indoor Inverse Rendering with 3D Spatially-Varying Lightingcited by 82
  9. 2020Polarized Reflection Removal with Perfect Alignment in the Wildcited by 69
  10. 2018Materials for Masses: SVBRDF Acquisition with a Single Mobile Phone Imagecited by 66
  11. 2022IRISformer: Dense Vision Transformers for Single-Image Inverse Rendering in Indoor Scenescited by 62
  12. 2020Two-shot Spatially-varying BRDF and Shape Estimationcited by 59
21 more
  1. 2021Deep Polarization Imaging for 3D shape and SVBRDF Acquisitioncited by 56
  2. 2021Shape from Polarization for Complex Scenes in the Wildcited by 53
  3. 2022PANDORA: Polarization-Aided Neural Decomposition Of Radiancecited by 52
  4. 2018Modeling Surface Appearance from a Single Photograph using Self-augmented Convolutional Neural Networkscited by 51
  5. 2018Deep attention-based classification network for robust depth predictioncited by 36
  6. 2021Shape and Material Capture at Homecited by 36
  7. 2018LIME: Live Intrinsic Material Estimationcited by 33
  8. 2019Depth from a polarisation + RGB stereo paircited by 29
  9. 2020Polarimetric Multi-View Inverse Renderingcited by 28
  10. 20203D Human Shape Reconstruction from a Polarization Imagecited by 28
  11. 2021De-rendering the World's Revolutionary Artefactscited by 28
  12. 2023NeISF: Neural Incident Stokes Field for Geometry and Material Estimationcited by 25
  13. 2021Polarimetric Pose Predictioncited by 16
  14. 2022Transparent Shape from a Single View Polarization Imagecited by 16
  15. 2021Human Pose and Shape Estimation from Single Polarization Imagescited by 13
  16. 2021Neural Relightable Participating Media Renderingcited by 12
  17. 2021All-photon Polarimetric Time-of-Flight Imagingcited by 12
  18. 2022Perspective Phase Angle Model for Polarimetric 3D Reconstructioncited by 11
  19. 2016What Is Around The Camera?cited by 10
  20. 2022Simultaneous Acquisition of High Quality RGB Image and Polarization Information using a Sparse Polarization Sensorcited by 9
  21. 2023Inverse Rendering of Translucent Objects using Physical and Neural Rendererscited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 3.

6 papers.

  1. 2024NeISF++: Neural Incident Stokes Field for Polarized Inverse Rendering of Conductors and Dielectricscited by 9
  2. 2025PolGS: Polarimetric Gaussian Splatting for Fast Reflective Surface Reconstructioncited by 8
  3. 2025TensoIS: A Step Towards Feed-Forward Tensorial Inverse Subsurface Scattering for Perlin Distributed Heterogeneous Mediacited by 0
  4. 2026Revisiting Shape from Polarization in the Era of Vision Foundation Modelscited by 0
  5. 2026PolGS++: Physically-Guided Polarimetric Gaussian Splatting for Fast Reflective Surface Reconstructioncited by 0
  6. 2026Structure-Aware Consistency Priors for Shape from Polarization in Complex Mediacited by 0