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

Depth estimation in surgical video plays a crucial role in many image-guidedsurgery procedures. However, it is difficult and time consuming to create depthmap ground truth datasets in surgical videos due in part to inconsistentbrightness and noise in the surgical scene. Therefore, building an accurate androbust self-supervised depth and camera ego-motion estimation system is gainingmore attention from the computer vision community. Although severalself-supervision methods alleviate the need for ground truth depth maps andposes, they still need known camera intrinsic parameters, which are oftenmissing or not recorded. Moreover, the camera intrinsic prediction methods inexisting works depend heavily on the quality of datasets. In this work, weaimed to build a self-supervised depth and ego-motion estimation system whichcan predict not only accurate depth maps and camera pose, but also cameraintrinsic parameters. We proposed a cost-volume-based supervision manner togive the system auxiliary supervision for camera parameters prediction. Theexperimental results showed that the proposed method improved the accuracy ofestimated camera parameters, ego-motion, and depth estimation.

WS-SfMLearner: Self-supervised Monocular Depth and Ego-motion Estimation on Surgical Videos with Unknown Camera Parameters