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

Although many recent works have made advancements in the image restoration(IR) field, they often suffer from an excessive number of parameters. Anotherissue is that most Transformer-based IR methods focus only on either local orglobal features, leading to limited receptive fields or deficient parameterissues. To address these problems, we propose a lightweight IR network,Reciprocal Attention Mixing Transformer (RAMiT). It employs our proposeddimensional reciprocal attention mixing Transformer (D-RAMiT) blocks, whichcompute bi-dimensional (spatial and channel) self-attentions in parallel withdifferent numbers of multi-heads. The bi-dimensional attentions help each otherto complement their counterpart's drawbacks and are then mixed. Additionally,we introduce a hierarchical reciprocal attention mixing (H-RAMi) layer thatcompensates for pixel-level information losses and utilizes semanticinformation while maintaining an efficient hierarchical structure. Furthermore,we revisit and modify MobileNet V1 and V2 to attach efficient convolutions toour proposed components. The experimental results demonstrate that RAMiTachieves state-of-the-art performance on multiple lightweight IR tasks,including super-resolution, color denoising, grayscale denoising, low-lightenhancement, and deraining. Codes are available athttps://github.com/rami0205/RAMiT.

RAMiT: Reciprocal Attention Mixing Transformer for Lightweight Image Restoration