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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Deep learning techniques hold promise to develop dense topographyreconstruction and pose estimation methods for endoscopic videos. However,currently available datasets do not support effective quantitativebenchmarking. In this paper, we introduce a comprehensive endoscopic SLAMdataset consisting of 3D point cloud data for six porcine organs, capsule andstandard endoscopy recordings as well as synthetically generated data. A Pandarobotic arm, two commercially available capsule endoscopes, two conventionalendoscopes with different camera properties, and two high precision 3D scannerswere employed to collect data from 8 ex-vivo porcine gastrointestinal(GI)-tract organs. In total, 35 sub-datasets are provided with 6D pose groundtruth for the ex-vivo part: 18 sub-dataset for colon, 12 sub-datasets forstomach and 5 sub-datasets for small intestine, while four of these containpolyp-mimicking elevations carried out by an expert gastroenterologist.Synthetic capsule endoscopy frames from GI-tract with both depth and poseannotations are included to facilitate the study of simulation-to-real transferlearning algorithms. Additionally, we propound Endo-SfMLearner, an unsupervisedmonocular depth and pose estimation method that combines residual networks withspatial attention module in order to dictate the network to focus ondistinguishable and highly textured tissue regions. The proposed approach makesuse of a brightness-aware photometric loss to improve the robustness under fastframe-to-frame illumination changes. To exemplify the use-case of the EndoSLAMdataset, the performance of Endo-SfMLearner is extensively compared with thestate-of-the-art. The codes and the link for the dataset are publicly availableat https://github.com/CapsuleEndoscope/EndoSLAM. A video demonstrating theexperimental setup and procedure is accessible throughhttps://www.youtube.com/watch?v=G_LCe0aWWdQ.

EndoSLAM Dataset and An Unsupervised Monocular Visual Odometry and Depth Estimation Approach for Endoscopic Videos: Endo-SfMLearner