Hole-filling approach based on convolutional neural network for depth image-based rendering view synthesis

2020 ◽  
Vol 29 (01) ◽  
pp. 1
Author(s):  
Chengtao Cai ◽  
Bing Fan ◽  
Haiyang Meng ◽  
Qidan Zhu
Author(s):  
MICHAEL SCHMEING ◽  
XIAOYI JIANG

In this paper, we address the disocclusion problem that occurs during view synthesis in depth image-based rendering (DIBR). We propose a method that can recover faithful texture information for disoccluded areas. In contrast to common disocclusion filling methods, which usually work frame-by-frame, our algorithm can take information from temporally neighboring frames into account. This way, we are able to reconstruct a faithful filling for the disocclusion regions and not just an approximate or plausible one. Our method avoids artifacts that occur with common approaches and can additionally reduce compression artifacts at object boundaries.


2016 ◽  
Vol 9 (5) ◽  
pp. 145-164 ◽  
Author(s):  
Ran Liu ◽  
Zekun Deng ◽  
Lin Yi ◽  
Zhenwei Huang ◽  
Donghua Cao ◽  
...  

2017 ◽  
Vol 24 (3) ◽  
pp. 329-333 ◽  
Author(s):  
Jea-Hyung Cho ◽  
Wonseok Song ◽  
Hyuk Choi ◽  
Taejeong Kim

Sign in / Sign up

Export Citation Format

Share Document