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

Deep neural networks (DNN) have achieved great success in image restoration.However, most DNN methods are designed as a black box, lacking transparency andinterpretability. Although some methods are proposed to combine traditionaloptimization algorithms with DNN, they usually demand pre-defined degradationprocesses or handcrafted assumptions, making it difficult to deal with complexand real-world applications. In this paper, we propose a Deep GeneralizedUnfolding Network (DGUNet) for image restoration. Concretely, without loss ofinterpretability, we integrate a gradient estimation strategy into the gradientdescent step of the Proximal Gradient Descent (PGD) algorithm, driving it todeal with complex and real-world image degradation. In addition, we designinter-stage information pathways across proximal mapping in different PGDiterations to rectify the intrinsic information loss in most deep unfoldingnetworks (DUN) through a multi-scale and spatial-adaptive way. By integratingthe flexible gradient descent and informative proximal mapping, we unfold theiterative PGD algorithm into a trainable DNN. Extensive experiments on variousimage restoration tasks demonstrate the superiority of our method in terms ofstate-of-the-art performance, interpretability, and generalizability. Thesource code is available athttps://github.com/MC-E/Deep-Generalized-Unfolding-Networks-for-Image-Restoration.

Deep Generalized Unfolding Networks for Image Restoration