Ryosuke Hori
Hi, I am Ryosuke Hori (堀 涼介).
I am a researcher at the Digital Human Research Team, part of the Artificial Intelligence Research Center at the National Institute of Advanced Industrial Science and Technology (AIST). I received my PhD from Keio University under the supervision of Prof. Hideo Saito. During my PhD, I was a visiting researcher at the Kris Kitani Lab in the Robotics Institute (RI) at Carnegie Mellon University and a Research Fellow of the JSPS Research Fellowships for Young Scientists (DC1).
Email / CV / Google Scholar / Github / Linkedin
News
| Feb 20, 2026 | Our paper conducted during my visit at CMU has been accepted to CVPR 2026. |
|---|---|
| Mar 11, 2025 | Gave a TVCG invited presentation at IEEE VR 2025. |
| Oct 21, 2024 | Gave an invited talk at IW-P3HSE Workshop, IEEE ISMAR. |
| Sep 15, 2024 | One paper accepted to IEEE Transactions on Visualization and Computer Graphics (TVCG). |
| Apr 01, 2024 | Started a visiting researcher position at Carnegie Mellon University. |
Selected Publications
- ICIP
Map-Mono-Ego: Map-Grounded Global Human Pose Estimation from Monocular Egocentric VideoIn IEEE International Conference on Image Processing (ICIP), 2026 - CVPR
Ground Reaction Inertial Poser: Physics-based Human Motion Capture from Sparse IMUs and Insole Pressure SensorsIn IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026 - IEEE VR W
Real-Time Dynamic Digital Twin Generation Using Multiple First-Person ViewsIn 2026 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), 2026 - IEEE Access
Gait Inertial Poser (GIP): Gait-aware Human Motion Capture using Shoe-embedded IMUsIEEE Access, 2025 - CVPR W
Human Mesh Reconstruction of Sports Players with Multiple Dynamic CamerasIn 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2025 - ICIP
Silhouette-Based Synthetic Data Generation For 3D Human Pose Estimation With A Single Wrist-Mounted 360° CameraIn 2021 IEEE International Conference on Image Processing (ICIP), 2021