Neural Field Multi-view Shape-from-polarisation
Loading...
Date
2025
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association and John Wiley & Sons Ltd.
Abstract
We tackle the problem of multi-view shape-from-polarisation using a neural implicit surface representation and volume rendering of a polarised neural radiance field (P-NeRF). The P-NeRF predicts the parameters of a mixed diffuse/specular polarisation model. This directly relates polarisation behaviour to the surface normal without explicitly modelling illumination or BRDF. Via the implicit surface representation, this allows polarisation to directly inform the estimated geometry. This improves shape estimation and also allows separation of diffuse and specular radiance. For polarimetric images from division-of-focal-plane sensors, we fit directly to the raw data without first demosaicing. This avoids fitting to demosaicing artefacts and we propose losses and saturation masking specifically to handle HDR measurements. Our method achieves state-of-the-art performance on the PANDORA benchmark. We apply our method in a lightstage setting, providing single-shot face capture.
Description
CCS Concepts: Computing methodologies → Reconstruction
@article{10.1111:cgf.70177,
journal = {Computer Graphics Forum},
title = {{Neural Field Multi-view Shape-from-polarisation}},
author = {Wanaset, Rapee and Guarnera, Giuseppe Claudio and Smith, William A. P.},
year = {2025},
publisher = {The Eurographics Association and John Wiley & Sons Ltd.},
ISSN = {1467-8659},
DOI = {10.1111/cgf.70177}
}