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

Existing text-guided image manipulation methods aim to modify the appearanceof the image or to edit a few objects in a virtual or simple scenario, which isfar from practical application. In this work, we study a novel task ontext-guided image manipulation on the entity level in the real world. The taskimposes three basic requirements, (1) to edit the entity consistent with thetext descriptions, (2) to preserve the text-irrelevant regions, and (3) tomerge the manipulated entity into the image naturally. To this end, we proposea new transformer-based framework based on the two-stage image synthesismethod, namely \textbf{ManiTrans}, which can not only edit the appearance ofentities but also generate new entities corresponding to the text guidance. Ourframework incorporates a semantic alignment module to locate the image regionsto be manipulated, and a semantic loss to help align the relationship betweenthe vision and language. We conduct extensive experiments on the real datasets,CUB, Oxford, and COCO datasets to verify that our method can distinguish therelevant and irrelevant regions and achieve more precise and flexiblemanipulation compared with baseline methods. The project homepage is\url{https://jawang19.github.io/manitrans}.

ManiTrans: Entity-Level Text-Guided Image Manipulation via Token-wise Semantic Alignment and Generation