Quality-Blind Compressed Color Image Enhancement with Convolutional Neural Networks

Lossy compressed images and videos suffer from visible compression artifacts, especially when the bit-rate is low. To improve the quality of the compressed image while keeping the same bit-rate, decoder-side compression artifacts reduction (CAR) becomes important. Recently, convolutional neural netw...

Full description

Saved in:
Bibliographic Details
Main Authors: Cui, Kai, Koyuncu, Ahmet Burakhan, Boev, Atanas, Alshina, Elena, Steinbach, Eckehard
Format: Conference Proceeding
Language:English
Subjects:
Analytical models
Automobiles
Codecs
compression artifacts reduction
Convolutional neural networks
Image coding
post-filtering
quality-blind enhancement
Task analysis
Training
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Lossy compressed images and videos suffer from visible compression artifacts, especially when the bit-rate is low. To improve the quality of the compressed image while keeping the same bit-rate, decoder-side compression artifacts reduction (CAR) becomes important. Recently, convolutional neural networks are adopted for CAR tasks and achieve the state-of-the-art performance. However, most CAR algorithms only focus on the reconstruction of the luminance channel. Also, a separate model usually needs to be trained for each quality factor (QF), which makes these approaches not practical in existing codecs. In this paper, we analyze a quality-blind training strategy and compare it with training separate models for each QF. The testing results with three representative CAR algorithms show the superiority of the quality-blind training compared to separate training. The results for pseudo and real quality-blind CAR tests further prove the generalizability of the quality-blind training for practical CAR tasks.
ISSN:2158-1525
2158-1525
DOI:10.1109/ISCAS51556.2021.9401182