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, methods for neural surface representation and rendering, forexample NeuS, have shown that learning neural implicit surfaces through volumerendering is becoming increasingly popular and making good progress. However,these methods still face some challenges. Existing methods lack a directrepresentation of depth information, which makes object reconstructionunrestricted by geometric features, resulting in poor reconstruction of objectswith texture and color features. This is because existing methods only usesurface normals to represent implicit surfaces without using depth information.Therefore, these methods cannot model the detailed surface features of objectswell. To address this problem, we propose a neural implicit surface learningmethod called Depth-NeuS based on depth information optimization for multi-viewreconstruction. In this paper, we introduce depth loss to explicitly constrainSDF regression and introduce geometric consistency loss to optimize forlow-texture areas. Specific experiments show that Depth-NeuS outperformsexisting technologies in multiple scenarios and achieves high-quality surfacereconstruction in multiple scenarios.

Depth-NeuS: Neural Implicit Surfaces Learning for Multi-view Reconstruction Based on Depth Information Optimization