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

Real-world dynamic scene deblurring has long been a challenging task sincepaired blurry-sharp training data is unavailable. Conventional Maximum APosteriori estimation and deep learning-based deblurring methods are restrictedby handcrafted priors and synthetic blurry-sharp training pairs respectively,thereby failing to generalize to real dynamic blurriness. To this end, wepropose a Neural Maximum A Posteriori (NeurMAP) estimation framework fortraining neural networks to recover blind motion information and sharp contentfrom unpaired data. The proposed NeruMAP consists of a motion estimationnetwork and a deblurring network which are trained jointly to model the(re)blurring process (i.e. likelihood function). Meanwhile, the motionestimation network is trained to explore the motion information in images byapplying implicit dynamic motion prior, and in return enforces the deblurringnetwork training (i.e. providing sharp image prior). The proposed NeurMAP is anorthogonal approach to existing deblurring neural networks, and is the firstframework that enables training image deblurring networks on unpaired datasets.Experiments demonstrate our superiority on both quantitative metrics and visualquality over state-of-the-art methods. Codes are available onhttps://github.com/yjzhang96/NeurMAP-deblur.

Neural Maximum A Posteriori Estimation on Unpaired Data for Motion Deblurring