mlsanityData to 14 Oct 2026

Depth from a polarisation + RGB stereo pair

arXiv 1903.12061 ↗First posted 28 Mar 2019cs.CVcited by 29

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a hybrid depth imaging system in which a polarisation camera is augmented by a second image from a standard digital camera. For this modest increase in equipment complexity over conventional shape-from-polarisation, we obtain a number of benefits that enable us to overcome longstanding problems with the polarisation shape cue. The stereo cue provides a depth map which, although coarse, is metrically accurate. This is used as a guide surface for disambiguation of the polarisation surface normal estimates using a higher order graphical model. In turn, these are used to estimate diffuse albedo. By extending a previous shape-from-polarisation method to the perspective case, we show how to compute dense, detailed maps of absolute depth, while retaining a linear formulation. We show that our hybrid method is able to recover dense 3D geometry that is superior to state-of-the-art shape-from-polarisation or two view stereo alone.

Key facts. Cited by 29 papers in the map (data through 14 Oct 2026). First posted on arXiv 28 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 4; 2022: 8; 2023: 7; 2024: 7; 2025: 1; 2026: 2.

29 papers.

Sort:

  1. 2021Shape from Polarization for Complex Scenes in the Wildcited by 53
  2. 2023On the Importance of Accurate Geometry Data for Dense 3D Vision Taskscited by 26
  3. 2022Is my Depth Ground-Truth Good Enough? HAMMER -- Highly Accurate Multi-Modal Dataset for DEnse 3D Scene Regressioncited by 19
  4. 2021Polarimetric Pose Predictioncited by 16
  5. 2023Event-based Shape from Polarizationcited by 16
  6. 2023Multi-View Azimuth Stereo via Tangent Space Consistencycited by 16
  7. 2021Polarization Guided Specular Reflection Separationcited by 10
  8. 2022CroMo: Cross-Modal Learning for Monocular Depth Estimationcited by 10
  9. 2022Simultaneous Acquisition of High Quality RGB Image and Polarization Information using a Sparse Polarization Sensorcited by 9
  10. 2021Polarimetric Monocular Dense Mapping Using Relative Deep Depth Priorcited by 8
  11. 2022Sparse Ellipsometry: Portable Acquisition of Polarimetric SVBRDF and Shape with Unstructured Flash Photographycited by 7
  12. 2024Polarization Wavefront Lidar: Learning Large Scene Reconstruction from Polarized Wavefrontscited by 7
17 more
  1. 2022Fresnel Microfacet BRDF: Unification of Polari-Radiometric Surface-Body Reflectioncited by 6
  2. 2024Robust Depth Enhancement via Polarization Prompt Fusion Tuningcited by 6
  3. 2024Deep Polarization Cues for Single-shot Shape and Subsurface Scattering Estimationcited by 6
  4. 2024Learning to Remove Wrinkled Transparent Film with Polarized Priorcited by 4
  5. 2024SS-SfP:Neural Inverse Rendering for Self Supervised Shape from (Mixed) Polarizationcited by 3
  6. 2024Polarimetric BSSRDF Acquisition of Dynamic Facescited by 3
  7. 2025Benchmarking Burst Super-Resolution for Polarization Images: Noise Dataset and Analysiscited by 3
  8. 2023S2P3: Self-Supervised Polarimetric Pose Predictioncited by 2
  9. 2022Physically-admissible polarimetric data augmentation for road-scene analysiscited by 1
  10. 2022Polarized Color Image Denoising using Pocoformercited by 1
  11. 2023Pola4All: survey of polarimetric applications and an open-source toolkit to analyze polarizationcited by 1
  12. 2023Event-based Shape from Polarization with Spiking Neural Networkscited by 1
  13. 2024High Resolution Surface Reconstruction of Cultural Heritage Objects Using Shape from Polarization Methodcited by 1
  14. 2022Polarimetric Multi-View Inverse Renderingcited by 0
  15. 2023Polarimetric Information for Multi-Modal 6D Pose Estimation of Photometrically Challenging Objects with Limited Datacited by 0
  16. 2026Segmentation-Driven Monocular Shape from Polarization based on Physical Modelcited by 0
  17. 2026CDPR: Cross-modal Diffusion with Polarization for Reliable Monocular Depth Estimationcited by 0