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 conventional methods for estimating camera poses and scene structuresfrom severely blurry or low resolution images often result in failure. Theoff-the-shelf deblurring or super-resolution methods may show visually pleasingresults. However, applying each technique independently before matching isgenerally unprofitable because this naive series of procedures ignores theconsistency between images. In this paper, we propose a pioneering unifiedframework that solves four problems simultaneously, namely, dense depthreconstruction, camera pose estimation, super-resolution, and deblurring. Byreflecting a physical imaging process, we formulate a cost minimization problemand solve it using an alternating optimization technique. The experimentalresults on both synthetic and real videos show high-quality depth maps derivedfrom severely degraded images that contrast the failures of naive multi-viewstereo methods. Our proposed method also produces outstanding deblurred andsuper-resolved images unlike the independent application or combination ofconventional video deblurring, super-resolution methods.

Joint Estimation of Camera Pose, Depth, Deblurring, and Super-Resolution from a Blurred Image Sequence