Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2508.19713 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914009039503360 |
|---|---|
| author | Doorenbos, Lars Patty, C. H. Lucas Sznitman, Raphael Márquez-Neila, Pablo |
| author_facet | Doorenbos, Lars Patty, C. H. Lucas Sznitman, Raphael Márquez-Neila, Pablo |
| contents | Mueller matrices (MMs) encode information on geometry and material properties, but recovering both simultaneously is an ill-posed problem. We explore whether MMs contain sufficient information to infer surface geometry and material properties with machine learning. We use a dataset of spheres of various isotropic materials, with MMs captured over the full angular domain at five visible wavelengths (450-650 nm). We train machine learning models to predict material properties and surface normals using only these MMs as input. We demonstrate that, even when the material type is unknown, surface normals can be predicted and object geometry reconstructed. Moreover, MMs allow models to identify material types correctly. Further analyses show that diagonal elements are key for material characterization, and off-diagonal elements are decisive for normal estimation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_19713 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Inferring geometry and material properties from Mueller matrices with machine learning Doorenbos, Lars Patty, C. H. Lucas Sznitman, Raphael Márquez-Neila, Pablo Optics Machine Learning Mueller matrices (MMs) encode information on geometry and material properties, but recovering both simultaneously is an ill-posed problem. We explore whether MMs contain sufficient information to infer surface geometry and material properties with machine learning. We use a dataset of spheres of various isotropic materials, with MMs captured over the full angular domain at five visible wavelengths (450-650 nm). We train machine learning models to predict material properties and surface normals using only these MMs as input. We demonstrate that, even when the material type is unknown, surface normals can be predicted and object geometry reconstructed. Moreover, MMs allow models to identify material types correctly. Further analyses show that diagonal elements are key for material characterization, and off-diagonal elements are decisive for normal estimation. |
| title | Inferring geometry and material properties from Mueller matrices with machine learning |
| topic | Optics Machine Learning |
| url | https://arxiv.org/abs/2508.19713 |