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

We present DiffBIR, which leverages pretrained text-to-image diffusion modelsfor blind image restoration problem. Our framework adopts a two-stage pipeline.In the first stage, we pretrain a restoration module across diversifieddegradations to improve generalization capability in real-world scenarios. Thesecond stage leverages the generative ability of latent diffusion models, toachieve realistic image restoration. Specifically, we introduce an injectivemodulation sub-network -- LAControlNet for finetuning, while the pre-trainedStable Diffusion is to maintain its generative ability. Finally, we introduce acontrollable module that allows users to balance quality and fidelity byintroducing the latent image guidance in the denoising process duringinference. Extensive experiments have demonstrated its superiority overstate-of-the-art approaches for both blind image super-resolution and blindface restoration tasks on synthetic and real-world datasets. The code isavailable at https://github.com/XPixelGroup/DiffBIR.

DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior