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

Conventional SLAM techniques strongly rely on scene rigidity to solve dataassociation, ignoring dynamic parts of the scene. In this work we presentSemi-Direct DefSLAM (SD-DefSLAM), a novel monocular deformable SLAM method ableto map highly deforming environments, built on top of DefSLAM. To robustlysolve data association in challenging deforming scenes, SD-DefSLAM combinesdirect and indirect methods: an enhanced illumination-invariant Lucas-Kanadetracker for data association, geometric Bundle Adjustment for pose anddeformable map estimation, and bag-of-words based on feature descriptors forcamera relocation. Dynamic objects are detected and segmented-out using a CNNtrained for the specific application domain. We thoroughly evaluate our systemin two public datasets. The mandala dataset is a SLAM benchmark withincreasingly aggressive deformations. The Hamlyn dataset containsintracorporeal sequences that pose serious real-life challenges beyonddeformation like weak texture, specular reflections, surgical tools andocclusions. Our results show that SD-DefSLAM outperforms DefSLAM in pointtracking, reconstruction accuracy and scale drift thanks to the improvement inall the data association steps, being the first system able to robustly performSLAM inside the human body.

SD-DefSLAM: Semi-Direct Monocular SLAM for Deformable and Intracorporeal Scenes