Learning Patterns of Latent Residual for Improving Video Compression

Yen-Chung Chen, Keng-Jui Chang, Yi-Hsuan Tsai, Wei-Chen Chiu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We tackle the problem of reducing compression artifacts. Specifically, we focus on transmitting the residual from the original video, i.e. difference between a compressed video and its corresponding original/uncompressed one, together with the compressed video during video transmission. Our video compression pipeline is capable of diminishing the overall cost of transmitting the residual and simultaneously achieving comparable video quality with respect to a state-of-the-art baseline. We provide experimental results on several datasets, including the one with great diversity, to substantiate the capacity of our pipeline in improving video compression.
Original languageEnglish
Title of host publicationThe IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops
Number of pages5
StatePublished - Jun 2019

Fingerprint Dive into the research topics of 'Learning Patterns of Latent Residual for Improving Video Compression'. Together they form a unique fingerprint.

Cite this