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, learning multi-view neural surface reconstruction with thesupervision of point clouds or depth maps has been a promising way. However,due to the underutilization of prior information, current methods stillstruggle with the challenges of limited accuracy and excessive time complexity.In addition, prior data perturbation is also an important but rarely consideredissue. To address these challenges, we propose a novel point-guided methodnamed PG-NeuS, which achieves accurate and efficient reconstruction whilerobustly coping with point noise. Specifically, aleatoric uncertainty of thepoint cloud is modeled to capture the distribution of noise, leading to noiserobustness. Furthermore, a Neural Projection module connecting points andimages is proposed to add geometric constraints to implicit surface, achievingprecise point guidance. To better compensate for geometric bias between volumerendering and point modeling, high-fidelity points are filtered into a BiasNetwork to further improve details representation. Benefiting from theeffective point guidance, even with a lightweight network, the proposed PG-NeuSachieves fast convergence with an impressive 11x speedup compared to NeuS.Extensive experiments show that our method yields high-quality surfaces withhigh efficiency, especially for fine-grained details and smooth regions,outperforming the state-of-the-art methods. Moreover, it exhibits strongrobustness to noisy data and sparse data.

PG-NeuS: Robust and Efficient Point Guidance for Multi-View Neural Surface Reconstruction