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

For the success of video deblurring, it is essential to utilize informationfrom neighboring frames. Most state-of-the-art video deblurring methods adoptmotion compensation between video frames to aggregate information from multipleframes that can help deblur a target frame. However, the motion compensationmethods adopted by previous deblurring methods are not blur-invariant, andconsequently, their accuracy is limited for blurry frames with different bluramounts. To alleviate this problem, we propose two novel approaches to deblurvideos by effectively aggregating information from multiple video frames.First, we present blur-invariant motion estimation learning to improve motionestimation accuracy between blurry frames. Second, for motion compensation,instead of aligning frames by warping with estimated motions, we use a pixelvolume that contains candidate sharp pixels to resolve motion estimationerrors. We combine these two processes to propose an effective recurrent videodeblurring network that fully exploits deblurred previous frames. Experimentsshow that our method achieves the state-of-the-art performance bothquantitatively and qualitatively compared to recent methods that use deeplearning.

Recurrent Video Deblurring with Blur-Invariant Motion Estimation and Pixel Volumes