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

Existing dehazing approaches struggle to process real-world hazy images owingto the lack of paired real data and robust priors. In this work, we present anew paradigm for real image dehazing from the perspectives of synthesizing morerealistic hazy data and introducing more robust priors into the network.Specifically, (1) instead of adopting the de facto physical scattering model,we rethink the degradation of real hazy images and propose a phenomenologicalpipeline considering diverse degradation types. (2) We propose a Real ImageDehazing network via high-quality Codebook Priors (RIDCP). Firstly, a VQGAN ispre-trained on a large-scale high-quality dataset to obtain the discretecodebook, encapsulating high-quality priors (HQPs). After replacing thenegative effects brought by haze with HQPs, the decoder equipped with a novelnormalized feature alignment module can effectively utilize high-qualityfeatures and produce clean results. However, although our degradation pipelinedrastically mitigates the domain gap between synthetic and real data, it isstill intractable to avoid it, which challenges HQPs matching in the wild.Thus, we re-calculate the distance when matching the features to the HQPs by acontrollable matching operation, which facilitates finding better counterparts.We provide a recommendation to control the matching based on an explainablesolution. Users can also flexibly adjust the enhancement degree as per theirpreference. Extensive experiments verify the effectiveness of our datasynthesis pipeline and the superior performance of RIDCP in real imagedehazing.

RIDCP: Revitalizing Real Image Dehazing via High-Quality Codebook Priors