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

Recently, several works have addressed modeling of 3D shapes using deepneural networks to learn implicit surface representations. Up to now, themajority of works have concentrated on reconstruction quality, paying little orno attention to model size or training time. This work proposes LightSAL, anovel deep convolutional architecture for learning 3D shapes; the proposed workconcentrates on efficiency both in network training time and resulting modelsize. We build on the recent concept of Sign Agnostic Learning for training theproposed network, relying on signed distance fields, with unsigned distance asground truth. In the experimental section of the paper, we demonstrate that theproposed architecture outperforms previous work in model size and number ofrequired training iterations, while achieving equivalent accuracy. Experimentsare based on the D-Faust dataset that contains 41k 3D scans of human shapes.The proposed model has been implemented in PyTorch.

LightSAL: Lightweight Sign Agnostic Learning for Implicit Surface Representation