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

Video snapshot compressive imaging (SCI) utilizes a 2D detector to capturesequential video frames and compresses them into a single measurement. Variousreconstruction methods have been developed to recover the high-speed videoframes from the snapshot measurement. However, most existing reconstructionmethods are incapable of capturing long-range spatial and temporaldependencies, which are critical for video processing. In this paper, wepropose a flexible and robust approach based on graph neural network (GNN) toefficiently model non-local interactions between pixels in space as well astime regardless of the distance. Specifically, we develop a motion-awaredynamic GNN for better video representation, i.e., represent each pixel as theaggregation of relative nodes under the guidance of frame-by-frame motions,which consists of motion-aware dynamic sampling, cross-scale node sampling andgraph aggregation. Extensive results on both simulation and real datademonstrate both the effectiveness and efficiency of the proposed approach, andthe visualization clearly illustrates the intrinsic dynamic sampling operationsof our proposed model for boosting the video SCI reconstruction results. Thecode and models will be released to the public.

Motion-aware Dynamic Graph Neural Network for Video Compressive Sensing