Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

A multi‐illuminant synthetic image test set

A multi‐illuminant synthetic image test set A new multi‐illuminant synthetic image test set called MIST is described and made publicly available. MIST is intended primarily for evaluating illumination estimation and color constancy methods, but additional data are provided to make it useful for other computer vision applications as well. MIST addresses the problem found in most existing real‐image datasets, which is that the groundtruth illumination is only measured at a very limited number of locations, despite the fact that illumination tends to vary significantly in almost all scenes. In contrast, MIST provides for each pixel: (a) the percent surface spectral reflectance, (b) the spectrum of the incident illumination, (c) the separate specular and diffuse components of the reflected light, and (d) the depth (ie, camera‐to‐surface distance). The dataset contains 900 stereo pairs, each of the 1800 images being a 30‐band multispectral image covering the visible spectrum from 400 to 695 nm at a 5 nm interval. Standard sRGB versions of the multispectral images are also provided. The images are synthesized by extending the Blender Cycles ray‐tracing renderer. The rendering is done in a way that ensures the images are not only photorealistic, but physically accurate as well. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Color Research & Application Wiley

A multi‐illuminant synthetic image test set

Hao, Xiangpeng; Funt, Brian
Color Research & Application , Volume 45 (6) – Dec 1, 2020
Download PDF
12 pages

Loading next page...
 
/lp/wiley/a-multi-illuminant-synthetic-image-test-set-c003i5d9Wp

References (34)

Publisher
Wiley
Copyright
© 2020 Wiley Periodicals LLC
ISSN
0361-2317
eISSN
1520-6378
DOI
10.1002/col.22535
Publisher site
See Article on Publisher Site

Abstract

A new multi‐illuminant synthetic image test set called MIST is described and made publicly available. MIST is intended primarily for evaluating illumination estimation and color constancy methods, but additional data are provided to make it useful for other computer vision applications as well. MIST addresses the problem found in most existing real‐image datasets, which is that the groundtruth illumination is only measured at a very limited number of locations, despite the fact that illumination tends to vary significantly in almost all scenes. In contrast, MIST provides for each pixel: (a) the percent surface spectral reflectance, (b) the spectrum of the incident illumination, (c) the separate specular and diffuse components of the reflected light, and (d) the depth (ie, camera‐to‐surface distance). The dataset contains 900 stereo pairs, each of the 1800 images being a 30‐band multispectral image covering the visible spectrum from 400 to 695 nm at a 5 nm interval. Standard sRGB versions of the multispectral images are also provided. The images are synthesized by extending the Blender Cycles ray‐tracing renderer. The rendering is done in a way that ensures the images are not only photorealistic, but physically accurate as well.

Journal

Color Research & Application – Wiley

Published: Dec 1, 2020

Keywords: ; ; ;

There are no references for this article.