Attached Shadow Constrained Shape from Polarization

Momoka Yoshida, Ryo Kawahara, Takahiro Okabe

2025

Abstract

This paper tackles a long-standing challenge in computer vision: single-shot, per-pixel surface normal recovery. Although polarization provides a crucial clue to solving this problem, it leaves ambiguity in the normal estimation even when the refractive index is known. Therefore, previous studies require additional clues or assumptions. In this paper, we propose a novel approach to resolve this ambiguity and the unknown refractive index simultaneously. Our key idea is to leverage attached shadows to resolve normal ambiguity while measuring the refractive index based on wavelength characteristics in a single-shot scenario. We achieve this by separating the contributions of three appropriately placed narrow-band light sources in the RGB channel. We further introduce disambiguation uncertainty to address cast shadows and achieve more accurate normal recovery. Our experimental evaluations with synthetic and real images confirm the effectiveness of our method both qualitatively and quantitatively.

Paper Citation

in Harvard Style

Yoshida M., Kawahara R. and Okabe T. (2025). Attached Shadow Constrained Shape from Polarization. In Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP; ISBN 978-989-758-728-3, SciTePress, pages 640-647. DOI: 10.5220/0013248700003912

in Bibtex Style

@conference{visapp25,
author={Momoka Yoshida and Ryo Kawahara and Takahiro Okabe},
title={Attached Shadow Constrained Shape from Polarization},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP},
year={2025},
pages={640-647},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013248700003912},
isbn={978-989-758-728-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP
TI - Attached Shadow Constrained Shape from Polarization
SN - 978-989-758-728-3
AU - Yoshida M.
AU - Kawahara R.
AU - Okabe T.
PY - 2025
SP - 640
EP - 647
DO - 10.5220/0013248700003912
PB - SciTePress