Image-based Material Editing for Making Reflective Objects Fluorescent

Daichi Hidaka, Takahiro Okabe

2020

Abstract

Fluorescent materials give us a unique sense of quality such as self-luminous ones, because they absorb light with certain wavelengths and then emit light with longer wavelengths. The existing methods for image-based material editing make objects in an image specular, translucent, and transparent, but they do not address fluorescent materials. In this paper, we propose a method for making reflective objects in a single input image fluorescent by adding photorealistic fluorescent components to the objects of interest. Specifically, we show that photometrically consistent fluorescent components can approximately be represented by using the 3-band (RGB) spectral irradiance on the surface of a reflective object, and then compute the fluorescent components on the basis of intrinsic image decomposition without explicitly estimating the object’s shape and the light sources illuminating it from the input image. We conducted a number of experiments using both synthetic and real images, and confirmed that our proposed method is effective for making reflective objects fluorescent.

Paper Citation

in Harvard Style

Hidaka D. and Okabe T. (2020). Image-based Material Editing for Making Reflective Objects Fluorescent. In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 1: GRAPP; ISBN 978-989-758-402-2, SciTePress, pages 355-360. DOI: 10.5220/0009146103550360

in Bibtex Style

@conference{grapp20,
author={Daichi Hidaka and Takahiro Okabe},
title={Image-based Material Editing for Making Reflective Objects Fluorescent},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 1: GRAPP},
year={2020},
pages={355-360},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009146103550360},
isbn={978-989-758-402-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 1: GRAPP
TI - Image-based Material Editing for Making Reflective Objects Fluorescent
SN - 978-989-758-402-2
AU - Hidaka D.
AU - Okabe T.
PY - 2020
SP - 355
EP - 360
DO - 10.5220/0009146103550360
PB - SciTePress