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 this paper, we consider the problem in defocus image deblurring. Previousclassical methods follow two-steps approaches, i.e., first defocus mapestimation and then the non-blind deblurring. In the era of deep learning, someresearchers have tried to address these two problems by CNN. However, thesimple concatenation of defocus map, which represents the blur level, leads tosuboptimal performance. Considering the spatial variant property of the defocusblur and the blur level indicated in the defocus map, we employ the defocus mapas conditional guidance to adjust the features from the input blurring imagesinstead of simple concatenation. Then we propose a simple but effective networkwith spatial modulation based on the defocus map. To achieve this, we design anetwork consisting of three sub-networks, including the defocus map estimationnetwork, a condition network that encodes the defocus map into conditionfeatures, and the defocus deblurring network that performs spatially dynamicmodulation based on the condition features. Moreover, the spatially dynamicmodulation is based on an affine transform function to adjust the features fromthe input blurry images. Experimental results show that our method can achievebetter quantitative and qualitative evaluation performance than the existingstate-of-the-art methods on the commonly used public test datasets.

Single-image Defocus Deblurring by Integration of Defocus Map Prediction Tracing the Inverse Problem Computation