Publications

NTIRE 2021 Challenge on Burst Super-Resolution: Methods and Results

Published in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2021, 2021

The report of the challenge. 4th Place.

Recommended citation: Bhat, G., Danelljan, M., & Timofte, R. (2021). NTIRE 2021 challenge on burst super-resolution: Methods and results. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 613-626).

Data Augmentation for Human Motion Prediction

Published in 2021 17th International Conference on Machine Vision Applications (MVA), 2021

We proposed two data augmentation approaches using VAE and IK, and a motion refinement using Imitation Learning for Motion Prediciton

Recommended citation: T. Maeda and N. Ukita, "Data Augmentation for Human Motion Prediction," 2021 17th International Conference on Machine Vision and Applications (MVA), 2021, pp. 1-5, doi: 10.23919/MVA51890.2021.9511368.

Grasp and Motion Planning for Dexterous Manipulation for the Real Robot Challenge

Published in arXiv preprint, 2021

This paper is a technical report for Real Robot Challenge Competition 2020, the Max Planck Institute for Intelligent Systems.

Recommended citation: Yoneda, T., Schaff, C., Maeda, T., & Walter, M. (2021). Grasp and motion planning for dexterous manipulation for the real robot challenge. arXiv preprint arXiv:2101.02842.

Human Pose Annotation Using a Motion Capture System for Loose-Fitting Clothes

Published in 2020 IEICE Transactions on Information and Systems 103 (6), 1257-1264, 2020

This paper proposes a framework for automatically annotating the keypoints of a human body in images for learning 2D pose estimation models.

Recommended citation: Matsumoto, T., Shimosato, K., Maeda, T., Murakami, T., Murakoso, K., Mino, K., & Ukita, N. (2020). Human Pose Annotation Using a Motion Capture System for Loose-Fitting Clothes. IEICE Transactions on Information and Systems, 103(6), 1257-1264.

Automatic human pose annotation for loose-fitting clothes

Published in 2019 16th International Conference on Machine Vision Applications (MVA), 2019

This paper proposes a framework for automatically annotating the keypoints of a human body in images for learning 2D pose estimation models.

Recommended citation: Matsumoto, T., Shimosato, K., Maeda, T., Murakami, T., Murakoso, K., Mino, K., & Ukita, N. (2019, May). Automatic human pose annotation for loose-fitting clothes. In 2019 16th International Conference on Machine Vision Applications (MVA) (pp. 1-6). IEEE.