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/

Zendy Plus

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

Zendy Tools

Zendy Open

Under stereo settings, the performance of image JPEG artifacts removal can befurther improved by exploiting the additional information provided by a secondview. However, incorporating this information for stereo image JPEG artifactsremoval is a huge challenge, since the existing compression artifacts makepixel-level view alignment difficult. In this paper, we propose a novelparallax transformer network (PTNet) to integrate the information from stereoimage pairs for stereo image JPEG artifacts removal. Specifically, awell-designed symmetric bi-directional parallax transformer module is proposedto match features with similar textures between different views instead ofpixel-level view alignment. Due to the issues of occlusions and boundaries, aconfidence-based cross-view fusion module is proposed to achieve better featurefusion for both views, where the cross-view features are weighted withconfidence maps. Especially, we adopt a coarse-to-fine design for thecross-view interaction, leading to better performance. Comprehensiveexperimental results demonstrate that our PTNet can effectively removecompression artifacts and achieves superior performance than other testingstate-of-the-art methods.

Learning Parallax Transformer Network for Stereo Image JPEG Artifacts Removal