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

State-of-the-art image denoisers exploit various types of deep neuralnetworks via deterministic training. Alternatively, very recent works utilizedeep reinforcement learning for restoring images with diverse or unknowncorruptions. Though deep reinforcement learning can generate effective policynetworks for operator selection or architecture search in image restoration,how it is connected to the classic deterministic training in solving inverseproblems remains unclear. In this work, we propose a novel image denoisingscheme via Residual Recovery using Reinforcement Learning, dubbed R3L. We showthat R3L is equivalent to a deep recurrent neural network that is trained usinga stochastic reward, in contrast to many popular denoisers using supervisedlearning with deterministic losses. To benchmark the effectiveness ofreinforcement learning in R3L, we train a recurrent neural network with thesame architecture for residual recovery using the deterministic loss, thus toanalyze how the two different training strategies affect the denoisingperformance. With such a unified benchmarking system, we demonstrate that theproposed R3L has better generalizability and robustness in image denoising whenthe estimated noise level varies, comparing to its counterparts usingdeterministic training, as well as various state-of-the-art image denoisingalgorithms.

R3L: Connecting Deep Reinforcement Learning to Recurrent Neural Networks for Image Denoising via Residual Recovery