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

Eliminating ghosting artifacts due to moving objects is a challenging problemin high dynamic range (HDR) imaging. In this letter, we present a hybrid modelconsisting of a convolutional encoder and a Transformer decoder to generateghost-free HDR images. In the encoder, a context aggregation network andnon-local attention block are adopted to optimize multi-scale features andcapture both global and local dependencies of multiple low dynamic range (LDR)images. The decoder based on Swin Transformer is utilized to improve thereconstruction capability of the proposed model. Motivated by the phenomenaldifference between the presence and absence of artifacts under the field ofstructure tensor (ST), we integrate the ST information of LDR images asauxiliary inputs of the network and use ST loss to further constrain artifacts.Different from previous approaches, our network is capable of processing anarbitrary number of input LDR images. Qualitative and quantitative experimentsdemonstrate the effectiveness of the proposed method by comparing it withexisting state-of-the-art HDR deghosting models. Codes are available athttps://github.com/pandayuanyu/HSTHdr.

Ghost-free High Dynamic Range Imaging via Hybrid CNN-Transformer and Structure Tensor