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

Event cameras are bio-inspired, motion-activated sensors that demonstratesubstantial potential in handling challenging situations, such as motion blurand high-dynamic range. In this paper, we proposed EVI-SAM to tackle theproblem of 6 DoF pose tracking and 3D reconstruction using monocular eventcamera. A novel event-based hybrid tracking framework is designed to estimatethe pose, leveraging the robustness of feature matching and the precision ofdirect alignment. Specifically, we develop an event-based 2D-2D alignment toconstruct the photometric constraint, and tightly integrate it with theevent-based reprojection constraint. The mapping module recovers the dense andcolorful depth of the scene through the image-guided event-based mappingmethod. Subsequently, the appearance, texture, and surface mesh of the 3D scenecan be reconstructed by fusing the dense depth map from multiple viewpointsusing truncated signed distance function (TSDF) fusion. To the best of ourknowledge, this is the first non-learning work to realize event-based densemapping. Numerical evaluations are performed on both publicly available andself-collected datasets, which qualitatively and quantitatively demonstrate thesuperior performance of our method. Our EVI-SAM effectively balances accuracyand robustness while maintaining computational efficiency, showcasing superiorpose tracking and dense mapping performance in challenging scenarios. VideoDemo: https://youtu.be/Nn40U4e5Si8.

EVI-SAM: Robust, Real-time, Tightly-coupled Event-Visual-Inertial State Estimation and 3D Dense Mapping