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

Image matching that finding robust and accurate correspondences across imagesis a challenging task under extreme conditions. Capturing local and globalfeatures simultaneously is an important way to mitigate such an issue butrecent transformer-based decoders were still stuck in the issues that CNN-basedencoders only extract local features and the transformers lack locality.Inspired by the locality and implicit positional encoding of convolutions, anovel convolutional transformer is proposed to capture both local contexts andglobal structures more sufficiently for detector-free matching. Firstly, auniversal FPN-like framework captures global structures in self-encoder as wellas cross-decoder by transformers and compensates local contexts as well asimplicit positional encoding by convolutions. Secondly, a novel convolutionaltransformer module explores multi-scale long range dependencies by a novelmulti-scale attention and further aggregates local information insidedependencies for enhancing locality. Finally, a novel regression-basedsub-pixel refinement module exploits the whole fine-grained window features forfine-level positional deviation regression. The proposed method achievessuperior performances on a wide range of benchmarks. The code will be availableon https://github.com/zwh0527/LGFCTR.

LGFCTR: Local and Global Feature Convolutional Transformer for Image Matching