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

Surface reconstruction for point clouds is an important task in 3D computervision. Most of the latest methods resolve this problem by learning signeddistance functions (SDF) from point clouds, which are limited to reconstructingshapes or scenes with closed surfaces. Some other methods tried to representshapes or scenes with open surfaces using unsigned distance functions (UDF)which are learned from large scale ground truth unsigned distances. However,the learned UDF is hard to provide smooth distance fields near the surface dueto the noncontinuous character of point clouds. In this paper, we propose anovel method to learn consistency-aware unsigned distance functions directlyfrom raw point clouds. We achieve this by learning to move 3D queries to reachthe surface with a field consistency constraint, where we also enable toprogressively estimate a more accurate surface. Specifically, we train a neuralnetwork to gradually infer the relationship between 3D queries and theapproximated surface by searching for the moving target of queries in a dynamicway, which results in a consistent field around the surface. Meanwhile, weintroduce a polygonization algorithm to extract surfaces directly from thegradient field of the learned UDF. The experimental results in surfacereconstruction for synthetic and real scan data show significant improvementsover the state-of-the-art under the widely used benchmarks.

Learning Consistency-Aware Unsigned Distance Functions Progressively from Raw Point Clouds