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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Image denoising is a fundamental and challenging task in the field ofcomputer vision. Most supervised denoising methods learn to reconstruct cleanimages from noisy inputs, which have intrinsic spectral bias and tend toproduce over-smoothed and blurry images. Recently, researchers have exploreddiffusion models to generate high-frequency details in image restoration tasks,but these models do not guarantee that the generated texture aligns with realimages, leading to undesirable artifacts. To address the trade-off betweenvisual appeal and fidelity of high-frequency details in denoising tasks, wepropose a novel approach called the Reconstruct-and-Generate Diffusion Model(RnG). Our method leverages a reconstructive denoising network to recover themajority of the underlying clean signal, which serves as the initial estimationfor subsequent steps to maintain fidelity. Additionally, it employs a diffusionalgorithm to generate residual high-frequency details, thereby enhancing visualquality. We further introduce a two-stage training scheme to ensure effectivecollaboration between the reconstructive and generative modules of RnG. Toreduce undesirable texture introduced by the diffusion model, we also proposean adaptive step controller that regulates the number of inverse steps appliedby the diffusion model, allowing control over the level of high-frequencydetails added to each patch as well as saving the inference computational cost.Through our proposed RnG, we achieve a better balance between perception anddistortion. We conducted extensive experiments on both synthetic and realdenoising datasets, validating the superiority of the proposed approach.

Reconstruct-and-Generate Diffusion Model for Detail-Preserving Image Denoising