BRDF-based Irradiance Image Estimation to Remove Radiometric Differences for Stereo Matching

Kebin Peng, John Quarles, Kevin Desai

2022

Abstract

Existing stereo matching methods assume that the corresponding pixels between left and right views have similar intensity. However, in real situations, image intensity tends to be dissimilar because of the radiometric differences obtained due to change in light reflected. In this paper, we propose a novel approach for removing these radiometric differences to perform stereo matching effectively. The approach estimates irradiance images based on the Bidirectional Reflectance Distribution Function (BRDF) which describes the ratio of radiance to irradiance for a given image. We demonstrate that to compute an irradiance image we only need to estimate the light source direction and the object’s roughness. We consider an approximation that the dot product of the unknown light direction parameters follows a Gaussian distribution and we use that to estimate the light source direction. The object’s roughness is estimated by calculating the pixel intensity variance using a local window strategy. By applying the above steps independently on the original stereo images, we obtain the illumination invariant irradiance images that can be used as input to stereo matching methods. Experiments conducted on well-known stereo estimation datasets demonstrate that our proposed approach significantly reduces the error rate of stereo matching methods.

Download


Paper Citation


in Harvard Style

Peng K., Quarles J. and Desai K. (2022). BRDF-based Irradiance Image Estimation to Remove Radiometric Differences for Stereo Matching. In Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 5: VISAPP; ISBN 978-989-758-555-5, SciTePress, pages 734-744. DOI: 10.5220/0010879800003124


in Bibtex Style

@conference{visapp22,
author={Kebin Peng and John Quarles and Kevin Desai},
title={BRDF-based Irradiance Image Estimation to Remove Radiometric Differences for Stereo Matching},
booktitle={Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 5: VISAPP},
year={2022},
pages={734-744},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010879800003124},
isbn={978-989-758-555-5},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 5: VISAPP
TI - BRDF-based Irradiance Image Estimation to Remove Radiometric Differences for Stereo Matching
SN - 978-989-758-555-5
AU - Peng K.
AU - Quarles J.
AU - Desai K.
PY - 2022
SP - 734
EP - 744
DO - 10.5220/0010879800003124
PB - SciTePress