EventEgoHands: Event-based Egocentric 3D Hand Mesh Reconstruction
This addresses challenges in human-computer interaction and AR/VR applications by enabling robust hand tracking in dynamic environments, though it is incremental as it builds on event camera technology.
The paper tackled the problem of 3D hand mesh reconstruction in low-light or motion-blur conditions by proposing EventEgoHands, an event-based method that improved MPJPE by approximately 4.5 cm (43%) on the N-HOT3D dataset.
Reconstructing 3D hand mesh is challenging but an important task for human-computer interaction and AR/VR applications. In particular, RGB and/or depth cameras have been widely used in this task. However, methods using these conventional cameras face challenges in low-light environments and during motion blur. Thus, to address these limitations, event cameras have been attracting attention in recent years for their high dynamic range and high temporal resolution. Despite their advantages, event cameras are sensitive to background noise or camera motion, which has limited existing studies to static backgrounds and fixed cameras. In this study, we propose EventEgoHands, a novel method for event-based 3D hand mesh reconstruction in an egocentric view. Our approach introduces a Hand Segmentation Module that extracts hand regions, effectively mitigating the influence of dynamic background events. We evaluated our approach and demonstrated its effectiveness on the N-HOT3D dataset, improving MPJPE by approximately more than 4.5 cm (43%).