We are interested in

1. Image Recognition
画像認識

2. Deep Learning
深層学習

3. Omni-directional Video Processing
全天球映像処理

4. SLAM, PTAM and SfM
多視点映像からの3次元物体再構成

5. Modeling, Optimization
モデル化と最適化

6. Special Projects (*blue: Joint Research with other organization)

  • Image Coding for Machines (Shindo, Tatsumi, Watanabe)
  • Diffusion Model (Jin, Zneg)
  • Pose Estimation (Htwe, Zhao, Nakashima, Fukuta, Xinyi Liu)
  • Point Cloud Processing (Yunlong Liu, Nakayama, Ono)
  • NerF, NerV and 3D representation (Hayami)
  • Surveillance, Object Detection (Haoyuan Liu, Fan)
  • Anormaly Detection, Object Detection (Nguyen, Koizumi, Lu)
  • Gaze Detection (Sugiyama)
  • Mulimodal Action Recognition (Saigo)
  • Smartphone Dependency Analysis (Yamanda)
  • Speeker Recognition (Duan)
  • Image Coding Model (Tanaka)
  • Splatteting (Takabe)
  • Federated Learning (Nutaba)
  • Application of Prompt-based Image Coding (Fujinami)

Past research topics