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

Homography estimation serves as a fundamental technique for image alignmentin a wide array of applications. The advent of convolutional neural networkshas introduced learning-based methodologies that have exhibited remarkableefficacy in this realm. Yet, the generalizability of these approaches acrossdistinct domains remains underexplored. Unlike other conventional tasks,CNN-driven homography estimation models show a distinctive immunity to domainshifts, enabling seamless deployment from one dataset to another without thenecessity of transfer learning. This study explores the resilience of a varietyof deep homography estimation models to domain shifts, revealing that thenetwork architecture itself is not a contributing factor to this remarkableadaptability. By closely examining the models' focal regions and subjectinginput images to a variety of modifications, we confirm that the models heavilyrely on local textures such as edges and corner points for homographyestimation. Moreover, our analysis underscores that the domain shift immunityitself is intricately tied to the utilization of these local textures.

Analyzing the Domain Shift Immunity of Deep Homography Estimation