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

We present a novel method to reconstruct 3D scenes from images by leveragingdeep dense monocular SLAM and fast uncertainty propagation. The proposedapproach is able to 3D reconstruct scenes densely, accurately, and in real-timewhile being robust to extremely noisy depth estimates coming from densemonocular SLAM. Differently from previous approaches, that either use ad-hocdepth filters, or that estimate the depth uncertainty from RGB-D cameras'sensor models, our probabilistic depth uncertainty derives directly from theinformation matrix of the underlying bundle adjustment problem in SLAM. We showthat the resulting depth uncertainty provides an excellent signal to weight thedepth-maps for volumetric fusion. Without our depth uncertainty, the resultingmesh is noisy and with artifacts, while our approach generates an accurate 3Dmesh with significantly fewer artifacts. We provide results on the challengingEuroc dataset, and show that our approach achieves 92% better accuracy thandirectly fusing depths from monocular SLAM, and up to 90% improvements comparedto the best competing approach.

Probabilistic Volumetric Fusion for Dense Monocular SLAM