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

Merging multi-exposure images is a common approach for obtaining high dynamicrange (HDR) images, with the primary challenge being the avoidance of ghostingartifacts in dynamic scenes. Recent methods have proposed using deep neuralnetworks for deghosting. However, the methods typically rely on sufficient datawith HDR ground-truths, which are difficult and costly to collect. In thiswork, to eliminate the need for labeled data, we propose SelfHDR, aself-supervised HDR reconstruction method that only requires dynamicmulti-exposure images during training. Specifically, SelfHDR learns areconstruction network under the supervision of two complementary components,which can be constructed from multi-exposure images and focus on HDR color aswell as structure, respectively. The color component is estimated from alignedmulti-exposure images, while the structure one is generated through astructure-focused network that is supervised by the color component and aninput reference (\eg, medium-exposure) image. During testing, the learnedreconstruction network is directly deployed to predict an HDR image.Experiments on real-world images demonstrate our SelfHDR achieves superiorresults against the state-of-the-art self-supervised methods, and comparableperformance to supervised ones. Codes are available athttps://github.com/cszhilu1998/SelfHDR

Self-Supervised High Dynamic Range Imaging with Multi-Exposure Images in Dynamic Scenes