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

Real-time, high-quality, 3D scanning of large-scale scenes is key to mixedreality and robotic applications. However, scalability brings challenges ofdrift in pose estimation, introducing significant errors in the accumulatedmodel. Approaches often require hours of offline processing to globally correctmodel errors. Recent online methods demonstrate compelling results, but sufferfrom: (1) needing minutes to perform online correction preventing truereal-time use; (2) brittle frame-to-frame (or frame-to-model) pose estimationresulting in many tracking failures; or (3) supporting only unstructuredpoint-based representations, which limit scan quality and applicability. Wesystematically address these issues with a novel, real-time, end-to-endreconstruction framework. At its core is a robust pose estimation strategy,optimizing per frame for a global set of camera poses by considering thecomplete history of RGB-D input with an efficient hierarchical approach. Weremove the heavy reliance on temporal tracking, and continually localize to theglobally optimized frames instead. We contribute a parallelizable optimizationframework, which employs correspondences based on sparse features and densegeometric and photometric matching. Our approach estimates globally optimized(i.e., bundle adjusted) poses in real-time, supports robust tracking withrecovery from gross tracking failures (i.e., relocalization), and re-estimatesthe 3D model in real-time to ensure global consistency; all within a singleframework. Our approach outperforms state-of-the-art online systems withquality on par to offline methods, but with unprecedented speed and scancompleteness. Our framework leads to a comprehensive online scanning solutionfor large indoor environments, enabling ease of use and high-quality results.

BundleFusion: Real-time Globally Consistent 3D Reconstruction using On-the-fly Surface Re-integration