Resume

Paper

[NEW] READ: Retrieval-Enhanced Asymmetric Diffusion for Motion Planning

Takeru Oba, Matthew Walter, Norimichi ukita. 

CVPR 2024

[project]

​

Efficient Reinforcement Learning Using State-Action Uncertainty with Multiple Heads

Tomoharu Aizu, Takeru Oba, Norimichi ukita. 

ICANN (8) 2023: 184-196

[paper]

​

Cold Diffusion on the Replay Buffer: Learning to Plan from Known Good States

Zidan Wang, Takeru Oba, Takuma Yoneda, Rui Shen, Matthew R. Walter, Bradly C. Stadie

CoRL 2023.

[paper]

​

Data-Driven Stochastic Motion Evaluation and Optimization with Image by Spatially-Aligned Temporal Encoding

Takeru Oba and Norimichi ukita. 

ICRA 2023: 5013-5019.

2023 IEEE Robotics and Automation Society Japan Joint Chapter Young Award

[paper] [project]

​

Future-guided offline imitation learning for long action sequences via video interpolation and future-trajectory prediction

Takeru Oba and Norimichi ukita. 

Neurocomputing 547: 126325 (2023)

[paper]

​

Instance Segmentation by Semi-Supervised Learning and Image Synthesis

Takeru Oba and Norimichi ukita. 

IEICE Transactions on Information and Systems, E103.D, 6,1247-1256,2020

[paper]

​

Competition

NTIRE 2021 challenge on burst super-resolution: Methods and results

Goutam Bhat, Martin Danelljan, and Radu Timofte, et al. (including Takeru Oba)

CVPR Workshops 2021.

[paper]

​

NTIRE 2020 Challenge on Perceptual Extreme Super-Resolution: Methods and Results

Kai Zhang, Shuhang Gu, Radu Timofte, et al. (including Takeru Oba)

CVPR Workshops 2020: 2045-2057.

[paper]

​

Poster

Future-guided imitation learning for improving recurrent training

Takeru Oba and Norimichi UKITA.

Sixth International Workshop on Symbolic-Neural Learning (SNL2022), 2022.7.9

​

インスタンスセグメンテーションのための半教師あり学習を用いた画像合成

大羽剛瑠, 浮田宗伯.

第 217 回 CVIM 研究会 2019.5.31