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

In most of computer vision applications, motion blur is regarded as anundesirable artifact. However, it has been shown that motion blur in an imagemay have practical interests in fundamental computer vision problems. In thiswork, we propose a novel framework to estimate optical flow from a singlemotion-blurred image in an end-to-end manner. We design our network withtransformer networks to learn globally and locally varying motions from encodedfeatures of a motion-blurred input, and decode left and right frame featureswithout explicit frame supervision. A flow estimator network is then used toestimate optical flow from the decoded features in a coarse-to-fine manner. Wequalitatively and quantitatively evaluate our model through a large set ofexperiments on synthetic and real motion-blur datasets. We also providein-depth analysis of our model in connection with related approaches tohighlight the effectiveness and favorability of our approach. Furthermore, weshowcase the applicability of the flow estimated by our method on deblurringand moving object segmentation tasks.

Optical Flow Estimation from a Single Motion-blurred Image