publications

2026

1. CVPR

   

   Ground Reaction Inertial Poser: Physics-based Human Motion Capture from Sparse IMUs and Insole Pressure Sensors

   Ryosuke Hori, Jyun-Ting Song, Zhengyi Luo, Jinkun Cao, Soyong Shin, Hideo Saito, and Kris Kitani

   In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

   Website
2. IEEE VR W

   

   Real-Time Dynamic Digital Twin Generation Using Multiple First-Person Views

   Hiroki Yazaki, Shinnosuke Hirokawa, Ryosuke Hori, Hideo Saito, Azusa Sawada, and Manabu Nakanoya

   In IEEE Conference on Virtual Reality and 3D User Interfaces (VR) Workshop (WSR), 2026

2025

1. IEEE Access

   

   Gait Inertial Poser (GIP): Gait-aware Human Motion Capture using Shoe-embedded IMUs

   Ryosuke Hori, Hiroyuki Deguchi, Tsubasa Maruyama, Mitsunori Tada, and Hideo Saito

   IEEE Access, 2025

   DOI
2. CVPR W

   

   Human Mesh Reconstruction of Sports Players with Multiple Dynamic Cameras

   Yamato Hokari, Ryosuke Hori, and Hideo Saito

   In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshop, 2025
3. CHI W

   

   Realtime Smart Gait Poser for foot augmentation

   Hiroyuki Deguchi, Ryosuke Hori, Tsubasa Maruyama, Mitsunori Tada, and Hideo Saito

   In ACM Conference on Human Factors in Computing Systems (CHI) Workshop, 2025

2024

1. TVCG

   

   EventPointMesh: Human Mesh Recovery Solely From Event Point Clouds

   Ryosuke Hori, Mariko Isogawa, Dan Mikami, and Hideo Saito

   IEEE Transactions on Visualization and Computer Graphics (TVCG) / IEEE Conference on Virtual Reality and 3D User Interfaces (VR), 2024

   DOI Website
2. MMSports

   

   Occlusion Free Multi-Object Tracking Extention using Multi-Camera for Sport

   Momoe Yamane, Akimasa Kondo, Masashi Hatano, Ryosuke Hori, and Hideo Saito

   In Proceedings of the 7th ACM International Workshop on Multimedia Content Analysis in Sports (MMSports), Melbourne VIC, Australia, 2024

   Abs DOI

   As data analysis becomes increasingly significant, streamlining data collection is essential, particularly in sports. Among various aspects, player performance analysis is crucial for both professional and amateur levels. In computer vision, Multi-Object Tracking (MOT) and Multi-Camera Multi-Object Tracking (MCMOT) enable the analysis of people’s trajectories captured in videos. However, many existing methods do not account for crowded scenarios, such as sports matches, and require complex preprocessing of datasets, making them impractical for real-world applications. To address these challenges, we introduce a simple yet novel extension of MOT methods by utilizing the Gaussian distribution to associate tracking information obtained from multiple cameras. By integrating tracking data from all cameras, our methodology effectively mitigates identity switches and expands the tracking range. Experimental results demonstrate our tracking system’s effectiveness, showing a reduction in ID switches and false negatives compared to results achieved with a standard multi-object tracker.

3. MIRU

   

   Realtime Smart Gait Poser: Real-time Estimation of Walking Posture Using Smart Shoes (in Japanese)

   Hiroyuki Deguchi, Ryosuke Hori, Mitsunori Tada, and Hideo Saito

   In Meeting on Image Recognition and Understanding (MIRU), 2024
4. MIRU

   

   Estimation of First-Person View Videos from a Second-Person Perspective Camera Utilizing Pre-scanned 3D Environments (in Japanese)

   Hiroki Yazaki, Ryosuke Hori, Tomoya Matsubara, and Hideo Saito

   In Meeting on Image Recognition and Understanding (MIRU), 2024
5. MIRU

   

   3D Human Pose Estimation Using Wearable Insole-type Pressure Sensors (in Japanese)

   Ryotaro Numata, Ryosuke Hori, Fukuhara Yoshihiro, and Mariko Isogawa

   In Meeting on Image Recognition and Understanding (MIRU), 2024

2023

1. J. Imaging

   

   Future Prediction of Shuttlecock Trajectory in Badminton Using Player’s Information

   Yuka Nokihara, Ryo Hachiuma, Ryosuke Hori, and Hideo Saito

   Journal of Imaging, 2023

   Abs DOI

   Video analysis has become an essential aspect of net sports, such as badminton. Accurately predicting the future trajectory of balls and shuttlecocks can significantly benefit players by enhancing their performance and enabling them to devise effective game strategies. This paper aims to analyze data to provide players with an advantage in the fast-paced rallies of badminton matches. The paper delves into the innovative task of predicting future shuttlecock trajectories in badminton match videos and presents a method that takes into account both the shuttlecock position and the positions and postures of the players. In the experiments, players were extracted from the match video, their postures were analyzed, and a time-series model was trained. The results indicate that the proposed method improved accuracy by 13% compared to methods that solely used shuttlecock position information as input, and by 8.4% compared to methods that employed both shuttlecock and player position information as input.

2. VISIGRAPP

   

   Prediction of Shuttle Trajectory in Badminton Using Player’s Position.

   Yuka Nokihara, Ryosuke Hori, Ryo Hachiuma, and Hideo Saito

   In International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP), 2023
3. MIRU

   

   3D Human Pose and Shape Estimation Using an Event Camera (in Japanese)

   Ryosuke Hori, Mariko Isogawa, Dan Mikami, and Hideo Saito

   In Meeting on Image Recognition and Understanding (MIRU), 2023

   Awarded

   MIRU Student Encouragement Award

4. VRSJ

   

   3D Human Pose and Shape Estimation Using an Event Camera (in Japanese)

   Ryosuke Hori, Mariko Isogawa, Dan Mikami, and Hideo Saito

   In Annual Conference of the Virtual Reality Society of Japan (VRSJ), 2023

   Awarded

   VRSJ Academic Encouragement Award

5. MIRU

   

   Event Point Mesh in Realtime: Real-Time 3D Human Pose and Shape Estimation from Event Data (in Japanese)

   Hiroyuki Deguchi, Ikeda Wataru, Ryosuke Hori, Mariko Isogawa, and Hideo Saito

   In Meeting on Image Recognition and Understanding (MIRU), 2023

   Awarded

   MIRU Demo Presentation Award

2022

1. IEEE Access

   

   Silhouette-Based 3D Human Pose Estimation Using a Single Wrist-Mounted 360° Camera

   Ryosuke Hori, Ryo Hachiuma, Mariko Isogawa, Dan Mikami, and Hideo Saito

   IEEE Access, 2022

   DOI Website
2. CVIM

   

   3D Human Pose and Shape Estimation Using an Event Camera (in Japanese)

   Ryosuke Hori, Mariko Isogawa, Dan Mikami, and Hideo Saito

   In IPSJ SIG-CVIM Conference, 2022

   Awarded

   Honorable Mention Award from IPSJ SIG-CVIM, Excellent Research Presentation Award from IPSJ SIG-CGVI, Student Presentation Award from IPSJ SIG-CGVI

3. CCC

   

   Foot Pressure-Aware Human Mesh Recovery in 3D Scenes (in Japanese)

   Ryosuke Hori and Ryotaro Numata

   In cvpaper.challenge Conference Summer (CCC), 2022

   Awarded

   Best Paper Honorable Mention Award

2021

1. ICIP

   

   Silhouette-Based Synthetic Data Generation For 3D Human Pose Estimation With A Single Wrist-Mounted 360° Camera

   Ryosuke Hori, Ryo Hachiuma, Hideo Saito, Mariko Isogawa, and Dan Mikami

   In 2021 IEEE International Conference on Image Processing (ICIP), 2021

   DOI
2. MIRU

   

   Silhouette-Based Synthetic Data Generation For 3D Human Pose Estimation With A Single Wrist-Mounted 360° Camera (in Japanese)

   Ryosuke Hori, Ryo Hachiuma, Hideo Saito, Mariko Isogawa, and Dan Mikami

   In Meeting on Image Recognition and Understanding (MIRU), 2021