# Deep Shape from Polarization

arXiv: https://arxiv.org/abs/1903.10210 · HTML: https://mlsanity.com/paper/1903.10210/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Mar 2019.

## Built on by (most cited first, 4 of 4)

- [CroMo: Cross-Modal Learning for Monocular Depth Estimation](https://mlsanity.com/paper/2203.12485/) (2022)
- [Polarimetric Monocular Dense Mapping Using Relative Deep Depth Prior](https://mlsanity.com/paper/2102.05212/) (2021)
- [Spectral and Polarization Vision: Spectro-polarimetric Real-world Dataset](https://mlsanity.com/paper/2311.17396/) (2023)
- [Deep Demosaicing for Polarimetric Filter Array Cameras](https://mlsanity.com/paper/2211.13732/) (2022)

## Abstract (arXiv)

This paper makes a first attempt to bring the Shape from Polarization (SfP) problem to the realm of deep learning. The previous state-of-the-art methods for SfP have been purely physics-based. We see value in these principled models, and blend these physical models as priors into a neural network architecture. This proposed approach achieves results that exceed the previous state-of-the-art on a challenging dataset we introduce. This dataset consists of polarization images taken over a range of object textures, paints, and lighting conditions. We report that our proposed method achieves the lowest test error on each tested condition in our dataset, showing the value of blending data-driven and physics-driven approaches.