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

Scene text removal aims to remove the text and fill the regions withperceptually plausible background information in natural images. It hasattracted increasing attention due to its various applications in privacyprotection, scene text retrieval, and text editing. With the development ofdeep learning, the previous methods have achieved significant improvements.However, most of the existing methods seem to ignore the large perceptivefields and global information. The pioneer method can get significantimprovements by only changing training data from the cropped image to the fullimage. In this paper, we present a single-stage multi-scale network MSLKANetfor scene text removal in full images. For obtaining large perceptive fieldsand global information, we propose multi-scale large kernel attention (MSLKA)to obtain long-range dependencies between the text regions and the backgroundsat various granularity levels. Furthermore, we combine the large kerneldecomposition mechanism and atrous spatial pyramid pooling to build a largekernel spatial pyramid pooling (LKSPP), which can perceive more valid pixels inthe spatial dimension while maintaining large receptive fields and low cost ofcomputation. Extensive experimental results indicate that the proposed methodachieves state-of-the-art performance on both synthetic and real-world datasetsand the effectiveness of the proposed components MSLKA and LKSPP.

MSLKANet: A Multi-Scale Large Kernel Attention Network for Scene Text Removal