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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

The vast majority of modern consumer-grade cameras employ a rolling shuttermechanism, leading to image distortions if the camera moves during imageacquisition. In this paper, we present a novel deep network to solve thegeneric rolling shutter correction problem with two consecutive frames. Ourpipeline is symmetrically designed to predict the global shutter imagecorresponding to the intermediate time of these two frames, which is difficultfor existing methods because it corresponds to a camera pose that differs mostfrom the two frames. First, two time-symmetric dense undistortion flows areestimated by using well-established principles: pyramidal construction,warping, and cost volume processing. Then, both rolling shutter images arewarped into a common global shutter one in the feature space, respectively.Finally, a symmetric consistency constraint is constructed in the image decoderto effectively aggregate the contextual cues of two rolling shutter images,thereby recovering the high-quality global shutter image. Extensive experimentswith both synthetic and real data from public benchmarks demonstrate thesuperiority of our proposed approach over the state-of-the-art methods.

SUNet: Symmetric Undistortion Network for Rolling Shutter Correction