Guénolé Fiche
Research Subjects
Research Interests
Guénolé Fiche has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Fabien Baradel
Naver Labs Europe
2 shared publications - Philippe Weinzaepfel
Naver Labs Europe
2 shared publications - Renaud Seguier
CentraleSupélec, IETR (UMR CNRS 6164), France
2 shared publications - Romain Brégier
Naver Labs Europe
2 shared publications - Simon Leglaive
CentraleSupélec, IETR (UMR CNRS 6164), France
2 shared publications - Camila González Barral
SYSNAV, Vernon, France
1 shared publication
Latest Publications
- 11 September 2026
- Published by Springer Nature
- p. 281-299
Multi-HMR 2: Multi-person Camera-Centric Human Detection, Mesh Recovery and Tracking
- 11 September 2026
- Published by Springer Nature
- p. 281-299
Multi-HMR 2: Multi-person Camera-Centric Human Detection, Mesh Recovery and Tracking
- Open Access
- 15 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Motion-DVAE: Unsupervised learning for fast human motion denoising
- 15 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Open AccessMotion-DVAE: Unsupervised learning for fast human motion denoising
- Open Access
- 15 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-7
SwimXYZ: A large-scale dataset of synthetic swimming motions and videos
Technologies play an increasingly important role in sports and become a real competitive advantage for the athletes who benefit from it. Among them, the use of motion capture is developing in various sports to optimize sporting gestures. Unfortunately, traditional motion capture systems are expensive and constraining. Recently developed computer vision-based approaches also struggle in certain sports, like swimming, due to the aquatic environment. One of the reasons for the gap in performance is the lack of labeled datasets with swimming videos. In an attempt to address this issue, we introduce SwimXYZ, a synthetic dataset of swimming motions and videos. SwimXYZ contains 3.4 million frames annotated with ground truth 2D and 3D joints, as well as 240 sequences of swimming motions in the SMPL parameters format. In addition to making this dataset publicly available, we present use cases for SwimXYZ in swimming stroke clustering and 2D pose estimation.
- 15 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessSwimXYZ: A large-scale dataset of synthetic swimming motions and videos
Technologies play an increasingly important role in sports and become a real competitive advantage for the athletes who benefit from it. Among them, the use of motion capture is developing in various sports to optimize sporting gestures. Unfortunately, traditional motion capture systems are expensive and constraining. Recently developed computer vision-based approaches also struggle in certain sports, like swimming, due to the aquatic environment. One of the reasons for the gap in performance is the lack of labeled datasets with swimming videos. In an attempt to address this issue, we introduce SwimXYZ, a synthetic dataset of swimming motions and videos. SwimXYZ contains 3.4 million frames annotated with ground truth 2D and 3D joints, as well as 240 sequences of swimming motions in the SMPL parameters format. In addition to making this dataset publicly available, we present use cases for SwimXYZ in swimming stroke clustering and 2D pose estimation.