Innovative hole-filling method for depth-image-based rendering (DIBR) based on context learning

Chao Li; Xinzhu Sang; Duo Chen; Di Zhang

doi:10.1117/12.2500779

6 November 2018 Innovative hole-filling method for depth-image-based rendering (DIBR) based on context learning

Chao Li, Xinzhu Sang, Duo Chen, Di Zhang

Proceedings Volume 10817, Optoelectronic Imaging and Multimedia Technology V; 1081706 (2018) https://doi.org/10.1117/12.2500779
Event: SPIE/COS Photonics Asia, 2018, Beijing, China

Abstract

A new convolutional neural network is proposed for hole filling in the synthesized virtual view generated by depth image-based rendering (DIBR). A context encoder in the network is trained to make predictions of the hole region based on the rendered virtual view, with an adversarial discriminator reducing the errors and producing sharper and more precise result. A texture network in the end of the framework extracts the style of the image and achieves a natural output which is closer to reality. The experiment results demonstrate both subjectively and objectively that the proposed method obtain better 3D video quality compared to previous methods. The average peak signal-to-noise ratio (PSNR) increases by 0.36 dB.

Citation Download Citation

Chao Li, Xinzhu Sang, Duo Chen, and Di Zhang "Innovative hole-filling method for depth-image-based rendering (DIBR) based on context learning", Proc. SPIE 10817, Optoelectronic Imaging and Multimedia Technology V, 1081706 (6 November 2018); https://doi.org/10.1117/12.2500779

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available