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

Event-based cameras can measure intensity changes (called `{\it events}')with microsecond accuracy under high-speed motion and challenging lightingconditions. With the active pixel sensor (APS), the event camera allowssimultaneous output of the intensity frames. However, the output images arecaptured at a relatively low frame-rate and often suffer from motion blur. Ablurry image can be regarded as the integral of a sequence of latent images,while the events indicate the changes between the latent images. Therefore, weare able to model the blur-generation process by associating event data to alatent image. In this paper, we propose a simple and effective approach, the\textbf{Event-based Double Integral (EDI)} model, to reconstruct a highframe-rate, sharp video from a single blurry frame and its event data. Thevideo generation is based on solving a simple non-convex optimization problemin a single scalar variable. Experimental results on both synthetic and realimages demonstrate the superiority of our EDI model and optimization method incomparison to the state-of-the-art.

Bringing a Blurry Frame Alive at High Frame-Rate with an Event Camera