Abstract
There are holes for images generated by Depth-Image-Based Rendering (DIBR) method due to occlusion of foreground. An algorithm to fill holes based on convolutional neural networks is presented. PSNR of the image after filling holes is 32.65dB.
© 2018 The Author(s)
PDF ArticleMore Like This
Chun-Yen Chuang, Li-Chun Liu, Chia-Chien Wei, Jun-Jie Liu, Lindor Henrickson, Wan-Jou Huang, Chih-Lin Wang, Young-Kai Chen, and Jyehong Chen
W2A.43 Optical Fiber Communication Conference (OFC) 2018
Tianjiao Zeng, Zhenbo Ren, and Edmund Y. Lam
CW5B.3 Computational Optical Sensing and Imaging (COSI) 2018
Andrew P. Norton, Noah Toyonaga, Bruce Macintosh, and Steven Chu
OTh3E.4 Adaptive Optics: Analysis, Methods & Systems (AO) 2018