Deep Non-Local Kalman Network for Video Compression Artifact Reduction

• Published in: IEEE transactions on image processing Vol. 29; pp. 1725 - 1737
• Main Authors: Lu, Guo, Zhang, Xiaoyun, Ouyang, Wanli, Xu, Dong, Chen, Li, Gao, Zhiyong
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.01.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Artificial neural networks; Corresponding states; deep neural network; Frames; Image coding; Image restoration; Kalman filters; Kalman model; Neural networks; Optical imaging; recursive filtering; Recursive methods; Reduction; Restoration; Task analysis; Video compression; Video compression artifact reduction; Video data; video restoration

Video compression algorithms are widely used to reduce the huge size of video data, but they also introduce unpleasant visual artifacts due to the lossy compression. In order to improve the quality of the compressed videos, we proposed a deep non-local Kalman network for compression artifact reducti...