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

Large-scale radiance fields are promising mapping tools for smarttransportation applications like autonomous driving or drone delivery. But forlarge-scale scenes, compact synchronized RGB-D cameras are not applicable dueto limited sensing range, and using separate RGB and depth sensors inevitablyleads to unsynchronized sequences. Inspired by the recent success ofself-calibrating radiance field training methods that do not require knownintrinsic or extrinsic parameters, we propose the first solution thatself-calibrates the mismatch between RGB and depth frames. We leverage theimportant domain-specific fact that RGB and depth frames are actually sampledfrom the same trajectory and develop a novel implicit network called thetime-pose function. Combining it with a large-scale radiance field leads to anarchitecture that cascades two implicit representation networks. To validateits effectiveness, we construct a diverse and photorealistic dataset thatcovers various RGB-D mismatch scenarios. Through a comprehensive benchmarkingon this dataset, we demonstrate the flexibility of our method in differentscenarios and superior performance over applicable prior counterparts. Codes,data, and models will be made publicly available.

AsyncNeRF: Learning Large-scale Radiance Fields from Asynchronous RGB-D Sequences with Time-Pose Function