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 Decomposer, a semi-supervised reconstruction model that decomposesdistorted image sequences into their fundamental building blocks - the originalimage and the applied augmentations, i.e., shadow, light, and occlusions. Tosolve this problem, we use the SIDAR dataset that provides a large number ofdistorted image sequences: each sequence contains images with shadows,lighting, and occlusions applied to an undistorted version. Each distortionchanges the original signal in different ways, e.g., additive or multiplicativenoise. We propose a transformer-based model to explicitly learn thisdecomposition. The sequential model uses 3D Swin-Transformers forspatio-temporal encoding and 3D U-Nets as prediction heads for individual partsof the decomposition. We demonstrate that by separately pre-training our modelon weakly supervised pseudo labels, we can steer our model to optimize for ourambiguous problem definition and learn to differentiate between the differentimage distortions.

Decomposer: Semi-supervised Learning of Image Restoration and Image Decomposition