TY - GEN
T1 - EVENTEGOHANDS
T2 - 32nd IEEE International Conference on Image Processing, ICIP 2025
AU - Hara, Ryosei
AU - Ikeda, Wataru
AU - Hatano, Masashi
AU - Isogawa, Mariko
N1 - Publisher Copyright:
©2025 IEEE.
PY - 2025
Y1 - 2025
N2 - 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%).
AB - 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%).
KW - 3D hand mesh reconstruction
KW - 3d hand pose estimation
KW - egocentric vision
KW - event-based vision
UR - https://www.scopus.com/pages/publications/105028598923
UR - https://www.scopus.com/pages/publications/105028598923#tab=citedBy
U2 - 10.1109/ICIP55913.2025.11084751
DO - 10.1109/ICIP55913.2025.11084751
M3 - Conference contribution
AN - SCOPUS:105028598923
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 1199
EP - 1204
BT - 2025 IEEE International Conference on Image Processing, ICIP 2025 - Proceedings
PB - IEEE Computer Society
Y2 - 14 September 2025 through 17 September 2025
ER -