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

Reconstructing continuous surfaces from 3D point clouds is a fundamentaloperation in 3D geometry processing. Several recent state-of-the-art methodsaddress this problem using neural networks to learn signed distance functions(SDFs). In this paper, we introduce \textit{Neural-Pull}, a new approach thatis simple and leads to high quality SDFs. Specifically, we train a neuralnetwork to pull query 3D locations to their closest points on the surface usingthe predicted signed distance values and the gradient at the query locations,both of which are computed by the network itself. The pulling operation moveseach query location with a stride given by the distance predicted by thenetwork. Based on the sign of the distance, this may move the query locationalong or against the direction of the gradient of the SDF. This is adifferentiable operation that allows us to update the signed distance value andthe gradient simultaneously during training. Our outperforming results underwidely used benchmarks demonstrate that we can learn SDFs more accurately andflexibly for surface reconstruction and single image reconstruction than thestate-of-the-art methods.

Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfaces