Learning Projection Patterns for Direct-Global Separation

Takaoki Ueda, Ryo Kawahara, Takahiro Okabe

2024

Abstract

Separating the direct component such as diffuse reflection and specular reflection and the global component such as inter-reflection and subsurface scattering is important for various computer vision and computer graphics applications. Conventionally, high-frequency patterns designed by physics-based model or signal processing theory are projected from a projector to a scene, but their assumptions do not necessarily hold for real images due to the shallow depth of field of a projector and the limited spatial resolution of a camera. Accordingly, in this paper, we propose a data-driven approach for direct-global separation. Specifically, our proposed method learns not only the separation module but also the imaging module, i.e. the projection patterns at the same time in an end-to-end manner. We conduct a number of experiments using real images captured with a projector-camera system, and confirm the effectiveness of our method.

Paper Citation

in Harvard Style

Ueda T., Kawahara R. and Okabe T. (2024). Learning Projection Patterns for Direct-Global Separation. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP; ISBN 978-989-758-679-8, SciTePress, pages 599-606. DOI: 10.5220/0012418900003660

in Bibtex Style

@conference{visapp24,
author={Takaoki Ueda and Ryo Kawahara and Takahiro Okabe},
title={Learning Projection Patterns for Direct-Global Separation},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP},
year={2024},
pages={599-606},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012418900003660},
isbn={978-989-758-679-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP
TI - Learning Projection Patterns for Direct-Global Separation
SN - 978-989-758-679-8
AU - Ueda T.
AU - Kawahara R.
AU - Okabe T.
PY - 2024
SP - 599
EP - 606
DO - 10.5220/0012418900003660
PB - SciTePress