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 camera shows great potential in 3D hand pose estimation, especiallyaddressing the challenges of fast motion and high dynamic range in a low-powerway. However, due to the asynchronous differential imaging mechanism, it ischallenging to design event representation to encode hand motion informationespecially when the hands are not moving (causing motion ambiguity), and it isinfeasible to fully annotate the temporally dense event stream. In this paper,we propose EvHandPose with novel hand flow representations in Event-to-Posemodule for accurate hand pose estimation and alleviating the motion ambiguityissue. To solve the problem under sparse annotation, we design contrastmaximization and hand-edge constraints in Pose-to-IWE (Image with WarpedEvents) module and formulate EvHandPose in a weakly-supervision framework. Wefurther build EvRealHands, the first large-scale real-world event-based handpose dataset on several challenging scenes to bridge the real-synthetic domaingap. Experiments on EvRealHands demonstrate that EvHandPose outperformsprevious event-based methods under all evaluation scenes, achieves accurate andstable hand pose estimation with high temporal resolution in fast motion andstrong light scenes compared with RGB-based methods, generalizes well tooutdoor scenes and another type of event camera, and shows the potential forthe hand gesture recognition task.

EvHandPose: Event-based 3D Hand Pose Estimation with Sparse Supervision