3D video and information processing

Technology

NTT Human Informatics Laboratories aims to map the real world itself into the cyber world and make it possible to simulate it in time and space. We are researching technologies for analyzing information, such as video, sound, and 3D point clouds for the simulation. We call the cyber world, which reflects the real world itself, the "Ultra Realistic Metaverse." We use the ultra realistic metaverse to realize communication that transcends distance and time. Our aim is to extend human activities and capabilities.

Research

  1. 3D point clouds processing
  2. Video and audio media processing

Publications

2023

Journal Papers

  1. Shogo Sato, Yasuhiro Yao, Taiga Yoshida, Shingo Ando, Jun Shimamura, "Shadow Detection Based on Luminance-LiDAR Intensity Uncorrelation", IEICE Transactions on Information and Systems, 2023.

Conference Papers

  1. Shogo Sato, Yasuhiro Yao, Taiga Yoshida, Takuhiro Kaneko, Shingo Ando, Jun Shimamura, "Unsupervised Intrinsic Image Decomposition with LiDAR Intensity", CVPR, 2023.

2022

Journal Papers

  1. Kazuhiko Murasaki, Shingo Ando, Jun Shimamura, "Semi-Supervised Representation Learning via Triplet Loss Based on Explicit Class Ratio of Unlabeled Data", IEICE Trans. Inf. Syst., 2022.
  2. Kana Kurata, Yasuhiro Yao, Shingo Ando, Naoki Ito, and Jun Shimamura, "Aggregative Input Convolution for Large-scale Point Cloud Semantic Segmentation", IIEEJ Transactions on Image Electronics and Visual Computing, 2022.

2021

Journal Papers

  1. Yasuhiro Yao, Ryoichi Ishikawa, Shingo Ando, Kana Kurata, Naoki Ito, Jun Shimamura, Takeshi Oishi, "Non-Learning Stereo-Aided Depth Completion Under Mis-Projection via Selective Stereo Matching", IEEE Access, 2021.
  2. Motohiro Takagi, Kazuya Hayase, Masaki Kitahara, Jun Shimamura, "Building Change Detection by Using Past Map Information and Optical Aerial Images", IEICE Trans. Inf. Syst. , 2021.

Conference Papers

  1. Kana Kurata, Yasuhiro Yao, Shingo Ando, Naoki Ito and Jun Shimamura, "Aggregative Input Convolution for Large-Scale Point Cloud Semantic Segmentation", IEVC, 2021