Shadow Detection and Removal From Photo-Realistic Synthetic Urban Image Using Deep Learning
作者机构:Department of Computer ScienceKyonggi UniversityGyeonggi-do16227Korea
出 版 物:《Computers, Materials & Continua》 (计算机、材料和连续体(英文))
年 卷 期:2020年第62卷第1期
页 面:459-472页
核心收录:
学科分类:0831[工学-生物医学工程(可授工学、理学、医学学位)] 0808[工学-电气工程] 0809[工学-电子科学与技术(可授工学、理学学位)] 08[工学] 0805[工学-材料科学与工程(可授工学、理学学位)] 0701[理学-数学] 0801[工学-力学(可授工学、理学学位)] 0812[工学-计算机科学与技术(可授工学、理学学位)]
主 题:Deep-learning shadow detection shadow removal synthetic data
摘 要:Recently,virtual reality technology that can interact with various data is used for urban design and ***,one of the most important elements in virtual reality technology,means visual expression so that a person can experience three-dimensional space like *** obtain this realism,real-world data are used in the various *** example,in order to increase the realism of 3D modeled building textures real aerial images are utilized in 3D ***,the aerial image captured during the day can be shadowed by the sun and it can cause the distortion or deterioration of *** resolve this problem,researches on detecting and removing shadows have been conducted,but the detecting and removing shadow is still considered as a challenging *** this paper,we propose a novel method for detecting and removing shadows using deep *** this work,we first a build a new dataset of photo-realistic synthetic urban data based on the virtual environment using 3D spatial information provided by *** detecting and removing shadow from the dataset,firstly,the 1-channel shadow mask image is inferred from the 3-channel shadow image through the ***,to generate a shadow-free image,a 3-channel shadow image and a detected 1-channel shadow mask into the GAN is *** the experiments,we can prove that the proposed method outperforms the existing methods in detecting and removing shadow.