期刊
JOURNAL OF COMPUTATIONAL DESIGN AND ENGINEERING
卷 8, 期 4, 页码 995-1012出版社
OXFORD UNIV PRESS
DOI: 10.1093/jcde/qwab025
关键词
computer vision; photometric stereo; deep learning; convolutional neural network; image superresolution
资金
- National Research Foundation of Korea (NRF) - Korea government (MSIT) [2020R1A2B5B03002005]
- Ministry of Science and ICT
- National IT Industry Promotion Agency
- National Research Foundation of Korea [2020R1A2B5B03002005] Funding Source: Korea Institute of Science & Technology Information (KISTI), National Science & Technology Information Service (NTIS)
This paper presents a novel deep-learning-based photometric stereo method that uses superresolution images to enhance original image information. By optimizing the input-output of the network, better results were achieved compared to existing methods.
This paper introduces a novel deep-learning-based photometric stereo method that uses superresolution (SR) images: SR photometric stereo. Recent deep-learning-based SR algorithms have yielded great results in terms of enlarging images without mosaic effects. Supposing that the SR algorithms successfully enhance the feature and colour information of original images, implementing SR images using the photometric stereo method facilitates the use of considerably more information on the object than existing photometric stereo methods. We built a novel deep-learning-based network for the photometric stereo technique to optimize the input-output of SR image inputs and normal map outputs. We tested our network using the most widely used benchmark dataset and obtained better results than existing photometric stereo methods.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据