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

Graphics Interchange Format (GIF) is a highly portable graphics format thatis ubiquitous on the Internet. Despite their small sizes, GIF images oftencontain undesirable visual artifacts such as flat color regions, falsecontours, color shift, and dotted patterns. In this paper, we proposeGIF2Video, the first learning-based method for enhancing the visual quality ofGIFs in the wild. We focus on the challenging task of GIF restoration byrecovering information lost in the three steps of GIF creation: frame sampling,color quantization, and color dithering. We first propose a novel CNNarchitecture for color dequantization. It is built upon a compositionalarchitecture for multi-step color correction, with a comprehensive lossfunction designed to handle large quantization errors. We then adapt theSuperSlomo network for temporal interpolation of GIF frames. We introduce twolarge datasets, namely GIF-Faces and GIF-Moments, for both training andevaluation. Experimental results show that our method can significantly improvethe visual quality of GIFs, and outperforms direct baseline andstate-of-the-art approaches.

GIF2Video: Color Dequantization and Temporal Interpolation of GIF images