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

Dual-lens super-resolution (SR) is a practical scenario for reference (Ref)based SR by utilizing the telephoto image (Ref) to assist the super-resolutionof the low-resolution wide-angle image (LR input). Different from generalRefSR, the Ref in dual-lens SR only covers the overlapped field of view (FoV)area. However, current dual-lens SR methods rarely utilize these specificcharacteristics and directly perform dense matching between the LR input andRef. Due to the resolution gap between LR and Ref, the matching may miss thebest-matched candidate and destroy the consistent structures in the overlappedFoV area. Different from them, we propose to first align the Ref with thecenter region (namely the overlapped FoV area) of the LR input by combiningglobal warping and local warping to make the aligned Ref be sharp andconsistent. Then, we formulate the aligned Ref and LR center as value-keypairs, and the corner region of the LR is formulated as queries. In this way,we propose a kernel-free matching strategy by matching between the LR-corner(query) and LR-center (key) regions, and the corresponding aligned Ref (value)can be warped to the corner region of the target. Our kernel-free matchingstrategy avoids the resolution gap between LR and Ref, which makes our networkhave better generalization ability. In addition, we construct a DuSR-Realdataset with (LR, Ref, HR) triples, where the LR and HR are well aligned.Experiments on three datasets demonstrate that our method outperforms thesecond-best method by a large margin. Our code and dataset are available athttps://github.com/ZifanCui/KeDuSR.

KeDuSR: Real-World Dual-Lens Super-Resolution via Kernel-Free Matching