English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In video compression, most of the existing deep learning approachesconcentrate on the visual quality of a single frame, while ignoring the usefulpriors as well as the temporal information of adjacent frames. In this paper,we propose a multi-frame guided attention network (MGANet) to enhance thequality of compressed videos. Our network is composed of a temporal encoderthat discovers inter-frame relations, a guided encoder-decoder subnet thatencodes and enhances the visual patterns of target frame, and amulti-supervised reconstruction component that aggregates information topredict details. We design a bidirectional residual convolutional LSTM unit toimplicitly discover frames variations over time with respect to the targetframe. Meanwhile, the guided map is proposed to guide our network toconcentrate more on the block boundary. Our approach takes advantage ofintra-frame prior information and inter-frame information to improve thequality of compressed video. Experimental results show the robustness andsuperior performance of the proposed method.Code is available athttps://github.com/mengab/MGANet

MGANet: A Robust Model for Quality Enhancement of Compressed Video