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

The traditional homography estimation pipeline consists of four main steps:feature detection, feature matching, outlier removal and transformationestimation. Recent deep learning models intend to address the homographyestimation problem using a single convolutional network. While these models aretrained in an end-to-end fashion to simplify the homography estimation problem,they lack the feature matching step and/or the outlier removal step, which areimportant steps in the traditional homography estimation pipeline. In thispaper, we attempt to build a deep learning model that mimics all four steps inthe traditional homography estimation pipeline. In particular, the featurematching step is implemented using the cost volume technique. To removeoutliers in the cost volume, we treat this outlier removal problem as adenoising problem and propose a novel self-supervised loss to solve theproblem. Extensive experiments on synthetic and real datasets demonstrate thatthe proposed model outperforms existing deep learning models.

SSORN: Self-Supervised Outlier Removal Network for Robust Homography Estimation