Hiroyuki Deguchi

face.jpeg

Hi, I am Hiroyuki Deguchi (出口 裕之).

I am pursuing my first year as a PhD candidate at Keio University under the guidance of Prof. Hideo Saito, and also a research assistant at the Digital Human Research Team, part of the Artificial Intelligence Research Center at the National Institute of Advanced Industrial Science and Technology (AIST).

My research focuses on computer vision, especially egocentric vision, human motion capture, and 3D human reconstruction using multimodal sensors. More broadly, I am interested in human-centered visual understanding and in building robust vision systems that connect perception in the real world with digital human modeling, with a long-term interest in humanoid applications.

News

May 11, 2026. One paper accepted to IEEE International Conference on Image Processing.

June 7, 2024. One paper accepted to IEEE International Conference on Image Processing.

Jul 28, 2023. Received the “Demo Presentation Award” and the “Student Encouragement Award” at MIRU 2023.

Publications

Map-Mono-Ego preview
H. Deguchi, Ryosuke Hori, Kotaro Amaya, Tsubasa Maruyama, Mitsunori Tada, and Hideo Saito
Map-Mono-Ego: Map-Grounded Global Human Pose Estimation from Monocular Egocentric Video
In Proceedings of the 2026 IEEE International Conference on Image Processing (ICIP).
Gait Inertial Poser preview
R. Hori, H. Deguchi, T. Maruyama, M. Tada, and H. Saito
Gait Inertial Poser (GIP): Gait-Aware Human Motion Capture Using Shoe-Embedded IMUs
IEEE Access, vol. 13, pp. 183262-183282, 2025.
Realtime Smart Gait Poser preview
H. Deguchi*, R. Hori*, T. Maruyama, M. Tada, and H. Saito
Realtime Smart Gait Poser for Foot Augmentation
CHI 2025 Workshop, 2025.
E2GS preview
H. Deguchi*, M. Masuda*, T. Nakabayashi, and H. Saito
E2GS: Event Enhanced Gaussian Splatting
In Proceedings of the 2024 IEEE International Conference on Image Processing (ICIP), pp. 1676-1682, 2024.