Masashi Hatano

This paper proposes EventEgoHands++, a framework for event-based 3D hand mesh reconstruction from an egocentric viewpoint that incorporates a Hand Detector that estimates instance-level bounding boxes and masks for both the left and right hands and introduces Adaptive Attention, which dynamically gates the attention based on these detection results to accurately learn the spatial relationship and mutual interactions between the hands.

Estimating visibility for each hand joint independently can dramatically enhance the accuracy of 3D hand pose estimation in real-world applications.