|
Hi, I am Hiroyasu Akada (朱田 浩康).
Previously, I obtained my MS and BS at Keio University, with Prof. Masaki Takahashi.
During my MS, I had a great opportunity to work with Prof. Peter
Wonka at KAUST.
E-mail: hakada@mpi-inf.mpg.de |
|
|
[May 2024] Two papers were invited to a poster session in EgoVis workshop at CVPR 2024.
|
|
My research focus lies at the intersection of Computer Vision and Deep Learning. In particular, I am interested in Egocentric 3D Human Pose Estimation, 3D Object Reconstruction, and Synthetic-to-Real Domain Adaptation. |
|
Hiroyasu Akada, Jian Wang, Vladislav Golyanik, and Christian Theobalt Computer Vision and Pattern Recognition (CVPR), 2024, Highlight (top 3.5%) [Project page] [Benchmark Challenge] [Paper] [Code] In this work, we propose a new transformer-based framework to improve egocentric stereo 3D human pose estimation, which leverages the scene information and temporal context of egocentric stereo videos. Furthermore, we introduce two new benchmark datasets, i.e., UnrealEgo2 and UnrealEgo-RW (RealWorld). Our extensive experiments show that the proposed approach significantly outperforms previous methods. |
|
Christen Millerdurai, Hiroyasu Akada, Jian Wang, Diogo Luvizon, Christian Theobalt, Vladislav Golyanik Computer Vision and Pattern Recognition (CVPR), 2024 [Project page] [Paper] [Code] We tackle a new problem, i.e. 3D human motion capture from an egocentric monocular event camera with a fisheye lens. Event streams have high temporal resolution and could provide reliable cues for 3D human motion capture under high-speed human motions and rapidly changing illumination. We leverage these characteristics and propose the first approach for event-based 3D human pose estimation, EventEgo3D (EE3D). The proposed EE3D framework is specifically tailored for learning with event streams in the LNES representation, enabling high 3D reconstruction accuracy. We also provide two new datasets, EE3D-S and EE3D-R. |
|
Hiroyasu Akada, Jian Wang, Soshi Shimada, Masaki Takahashi, Christian Theobalt, and Vladislav Golyanik European Conference on Computer Vision (ECCV), 2022 [Project page] [Paper] [Code] We present UnrealEgo, i.e. a new large-scale naturalistic dataset for egocentric 3D human pose estimation. UnrealEgo is based on an advanced concept of eyeglasses equipped with two fisheye cameras that can be used in unconstrained environments. UnrealEgo is the first dataset to provide in-the-wild stereo images with the largest variety of motions among existing egocentric datasets. We also propose a new benchmark method that achieves the state-of-the-art results on UnrealEgo. |
|
Hiroyasu Akada, Shariq Farooq Bhat, Ibraheem Alhashim, Peter Wonka IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2022 [Paper] [Code] We tackle the problem of unsupervised synthetic-to-real domain adaptation for single image depth estimation. An essential building block of single image depth estimation is an encoder-decoder task network that takes RGB images as input and produces depth maps as output. In this paper, we propose a novel training strategy to force the task network to learn domain invariant representations in a self-supervised manner. |
|
Hiroyasu Akada and Masaki Takahashi International Conference on Intelligent Autonomous Systems (IAS), 2021 [Paper] We developed a GAN-based stem that remove dynamic objects in images. The system can be trained without using paired images with/without the dynamic objects. |
|
[Sep 2022 - Present] Ph.D. student, Max Planck
Institute for Informatics (Saarbrucken, Germany) |
|
Nakajima Foundation (中島記念国際交流財団), 2022-2027 (expected) |
|
Lab Visits:
Conference Participation: |
|
© Hiroyasu Akada 2022 / Design: jonbarron |