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

Scene Completion is the task of completing missing geometry from a partialscan of a scene. Most previous methods compute an implicit representation fromrange data using a Truncated Signed Distance Function (T-SDF) computed on a 3Dgrid as input to neural networks. The truncation decreases but does not removethe border errors introduced by the sign of SDF for open surfaces. As analternative, we present an Unsigned Distance Function (UDF) as an inputrepresentation to scene completion neural networks. The proposed UDF is simple,and efficient as a geometry representation, and can be computed on any pointcloud. In contrast to usual Signed Distance Functions, our UDF does not requirenormal computation. To obtain the explicit geometry, we present a method forextracting a point cloud from discretized UDF values on a sparse grid. Wecompare different SDFs and UDFs for the scene completion task on indoor andoutdoor point clouds collected using RGB-D and LiDAR sensors and show improvedcompletion using the proposed UDF function.

Unsigned Distance Field as an Accurate 3D Scene Representation for Neural Scene Completion