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

We contribute a dense SLAM system that takes a live stream of depth images asinput and reconstructs non-rigid deforming scenes in real time, withouttemplates or prior models. In contrast to existing approaches, we do notmaintain any volumetric data structures, such as truncated signed distancefunction (TSDF) fields or deformation fields, which are performance and memoryintensive. Our system works with a flat point (surfel) based representation ofgeometry, which can be directly acquired from commodity depth sensors. Standardgraphics pipelines and general purpose GPU (GPGPU) computing are leveraged forall central operations: i.e., nearest neighbor maintenance, non-rigiddeformation field estimation and fusion of depth measurements. Our pipelineinherently avoids expensive volumetric operations such as marching cubes,volumetric fusion and dense deformation field update, leading to significantlyimproved performance. Furthermore, the explicit and flexible surfel basedgeometry representation enables efficient tackling of topology changes andtracking failures, which makes our reconstructions consistent with updateddepth observations. Our system allows robots to maintain a scene descriptionwith non-rigidly deformed objects that potentially enables interactions withdynamic working environments.

SurfelWarp: Efficient Non-Volumetric Single View Dynamic Reconstruction