# Shape from Polarization of Thermal Emission and Reflection

arXiv: https://arxiv.org/abs/2506.18217 · HTML: https://mlsanity.com/paper/2506.18217/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 44 references that are in the map.
- First posted on arXiv 23 Jun 2025.

## Builds on (most cited first, 9 of 9)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation](https://mlsanity.com/paper/2102.04306/) (2021)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning](https://mlsanity.com/paper/1702.03118/) (2017)
- [Transformer-Based Attention Networks for Continuous Pixel-Wise Prediction](https://mlsanity.com/paper/2103.12091/) (2021)
- [Shape from Polarization for Complex Scenes in the Wild](https://mlsanity.com/paper/2112.11377/) (2021)
- [Transparent Shape from a Single View Polarization Image](https://mlsanity.com/paper/2204.06331/) (2022)

## Built on by (most cited first, 2 of 2)

- [Dual Band Thermal Videography: Separating Time-Varying Reflection and Emission Near Ambient Conditions](https://mlsanity.com/paper/2509.11334/) (2025)
- [A Theory of Shape Reconstruction from Heat Conduction and Shading](https://mlsanity.com/paper/2610.04052/) (2026)

## Abstract (arXiv)

Shape estimation for transparent objects is challenging due to their complex light transport. To circumvent these difficulties, we leverage the Shape from Polarization (SfP) technique in the Long-Wave Infrared (LWIR) spectrum, where most materials are opaque and emissive. While a few prior studies have explored LWIR SfP, these attempts suffered from significant errors due to inadequate polarimetric modeling, particularly the neglect of reflection. Addressing this gap, we formulated a polarization model that explicitly accounts for the combined effects of emission and reflection. Based on this model, we estimated surface normals using not only a direct model-based method but also a learning-based approach employing a neural network trained on a physically-grounded synthetic dataset. Furthermore, we modeled the LWIR polarimetric imaging process, accounting for inherent systematic errors to ensure accurate polarimetry. We implemented a prototype system and created ThermoPol, the first real-world benchmark dataset for LWIR SfP. Through comprehensive experiments, we demonstrated the high accuracy and broad applicability of our method across various materials, including those transparent in the visible spectrum.