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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Real-time 3D scene reconstruction from RGB-D sensor data, as well as theexploration of such data in VR/AR settings, has seen tremendous progress inrecent years. The combination of both these components into telepresencesystems, however, comes with significant technical challenges. All approachesproposed so far are extremely demanding on input and output devices, computeresources and transmission bandwidth, and they do not reach the level ofimmediacy required for applications such as remote collaboration. Here, weintroduce what we believe is the first practical client-server system forreal-time capture and many-user exploration of static 3D scenes. Our system isbased on the observation that interactive frame rates are sufficient forcapturing and reconstruction, and real-time performance is only required on theclient site to achieve lag-free view updates when rendering the 3D model.Starting from this insight, we extend previous voxel block hashing frameworksby overcoming internal dependencies and introducing, to the best of ourknowledge, the first thread-safe GPU hash map data structure that is robustunder massively concurrent retrieval, insertion and removal of entries on athread level. We further propose a novel transmission scheme for volume datathat is specifically targeted to Marching Cubes geometry reconstruction andenables a 90% reduction in bandwidth between server and exploration clients.The resulting system poses very moderate requirements on network bandwidth,latency and client-side computation, which enables it to rely entirely onconsumer-grade hardware, including mobile devices. We demonstrate that ourtechnique achieves state-of-the-art representation accuracy while providing,for any number of clients, an immersive and fluid lag-free viewing experienceeven during network outages.

SLAMCast: Large-Scale, Real-Time 3D Reconstruction and Streaming for Immersive Multi-Client Live Telepresence