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

Most existing deep-learning-based single image dynamic scene blind deblurring(SIDSBD) methods usually design deep networks to directly remove thespatially-variant motion blurs from one inputted motion blurred image, withoutblur kernels estimation. In this paper, inspired by the Projective Motion PathBlur (PMPB) model and deformable convolution, we propose a novel constraineddeformable convolutional network (CDCN) for efficient single image dynamicscene blind deblurring, which simultaneously achieves accuratespatially-variant motion blur kernels estimation and the high-quality imagerestoration from only one observed motion blurred image. In our proposed CDCN,we first construct a novel multi-scale multi-level multi-input multi-output(MSML-MIMO) encoder-decoder architecture for more powerful features extractionability. Second, different from the DLVBD methods that use multiple consecutiveframes, a novel constrained deformable convolution reblurring (CDCR) strategyis proposed, in which the deformable convolution is first applied to blurredfeatures of the inputted single motion blurred image for learning the samplingpoints of motion blur kernel of each pixel, which is similar to the estimationof the motion density function of the camera shake in the PMPB model, and thena novel PMPB-based reblurring loss function is proposed to constrain thelearned sampling points convergence, which can make the learned sampling pointsmatch with the relative motion trajectory of each pixel better and promote theaccuracy of the spatially-variant motion blur kernels estimation.

A Constrained Deformable Convolutional Network for Efficient Single  Image Dynamic Scene Blind Deblurring with Spatially-Variant Motion Blur  Kernels Estimation