CV

Education

Bachelor of Science, Tsukuba University, 2013
Master of Engineering, Tokyo Institute of Technology, 2015
Doctor of Engineering, Tokyo Institute of Technology, 2022 (Doctor of Engineering)

Work experience

2015- : Researcher
- Geospatial Private Corporation
  - 2015
    - Traffic sign detection by rule-based algorithm.
    - Develop SfM software.
  - 2016-2017
    - Image classification and image segmentation using deep learning.
      - Pavement Crack Estimation
      - Road Sign Segmentation
      - Semi-supervised learning for disaster damage detection using GANs
      - Domain Adaptation for sem.seg.
      - Landslide estimation
  - 2018
    - RPA system development for OCR using win32 APIs.
  - 2019
    - 3D point cloud labeling using deep learnig
    - Vehicle segmentation from aerial image
  - 2020
    - 3D point cloud labeling using deep learning
    - Image colonization using deep learning
    - Super resolution using deep learning

Skills

Programming
- C++
- C#
- Python
Computer Vision
- Image
  - Classification
  - Segmentation
- Point Cloud
  - Segmentation
Neural Network
- GAN
  - Domain Adaptation
  - Semi-supervised learning

Awards and honors

令和５年度（第30回）前田工学賞(IC部門)
令和3年度(2021)測量・地理空間情報技術奨励賞
平成29年度日本地震工学会大会優秀発表賞
2018年応用測量論文奨励賞

Publications

Point2Wave: 3D Point Cloud to Waveform Translation Using a Conditional Generative Adversarial Network with Dual Discriminators

T. Shinohara, H. Xiu and M. Matsuoka, "Point2Wave: 3D Point Cloud to Waveform Translation Using a Conditional Generative Adversarial Network with Dual Discriminators," in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, doi: 10.1109/JSTARS.2021.3124610.

3D POINT CLOUD GENERATION USING ADVERSARIAL TRAINING FOR LARGE-SCALE OUTDOOR SCENE

T. Shinohara, H. Xiu and M. Matsuoka, "3D Point Cloud Generation Using Adversarial Training for Large-Scale Outdoor Scene," 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, 2021, pp. 2935-2938, doi: 10.1109/IGARSS47720.2021.9554523.

IMAGE TO POINT CLOUD TRANSLATION USING CONDITIONAL GENERATIVE ADVERSARIAL NETWORK FOR AIRBORNE LIDAR DATA

Shinohara, T., Xiu, H., and Matsuoka, M.: IMAGE TO POINT CLOUD TRANSLATION USING CONDITIONAL GENERATIVE ADVERSARIAL NETWORK FOR AIRBORNE LIDAR DATA, ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., V-2-2021, 169–174, https://doi.org/10.5194/isprs-annals-V-2-2021-169-2021, 2021.

Point2color: 3D Point Cloud Colorization Using a Conditional Generative Network and Differentiable Rendering for Airborne LiDAR

Shinohara, Takayuki, Haoyi Xiu, and Masashi Matsuoka. "Point2color: 3D Point Cloud Colorization Using a Conditional Generative Network and Differentiable Rendering for Airborne LiDAR." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2021.

Semantic Segmentation for Full-Waveform LiDAR Data Using Local and Hierarchical Global Feature Extraction

Takayuki Shinohara, Haoyi Xiu, and Masashi Matsuoka. 2020. Semantic Segmentation for Full-Waveform LiDAR Data Using Local and Hierarchical Global Feature Extraction. In 28th International Conference on Advances in Geographic Information Systems (SIGSPATIAL 2020), November 3–6, 2020, Seattle, WA, USA. ACM, New York, NY, USA, 11 pages. https://doi.org/10.1145/3397536.3422209

FWNet: Semantic Segmentation for Full-Waveform LiDAR Data Using Deep Learning

Shinohara T, Xiu H, Matsuoka M. FWNet: Semantic Segmentation for Full-Waveform LiDAR Data Using Deep Learning. Sensors. 2020; 20(12):3568.

FWNetAE: Spatial Representation Learning for Full Waveform Data Using Deep Learning

T.Shinohara,et.al. (2019). "FWNetAE: Spatial Representation Learning for Full Waveform Data Using Deep Learning." 2019 IEEE International Symposium on Multimedia (ISM).

Point2color: 3D Point Cloud Colorization Using a Conditional Generative Network and Differentiable Rendering for Airborne LiDAR

June 19, 2021

Talk at CVPR Earth Vision 2021 Oral presentation, on-line

Takayuki Shinohara

CV

Education

Work experience

Skills

Awards and honors

Publications

Point2Wave: 3D Point Cloud to Waveform Translation Using a Conditional Generative Adversarial Network with Dual Discriminators

3D POINT CLOUD GENERATION USING ADVERSARIAL TRAINING FOR LARGE-SCALE OUTDOOR SCENE

IMAGE TO POINT CLOUD TRANSLATION USING CONDITIONAL GENERATIVE ADVERSARIAL NETWORK FOR AIRBORNE LIDAR DATA

Point2color: 3D Point Cloud Colorization Using a Conditional Generative Network and Differentiable Rendering for Airborne LiDAR

Semantic Segmentation for Full-Waveform LiDAR Data Using Local and Hierarchical Global Feature Extraction

FWNet: Semantic Segmentation for Full-Waveform LiDAR Data Using Deep Learning

FWNetAE: Spatial Representation Learning for Full Waveform Data Using Deep Learning

Talks

点群深層学習に計測の気持ちを入れた研究の紹介

3D POINT CLOUD GENERATION USING ADVERSARIAL TRAINING FOR LARGE-SCALE OUTDOOR SCENE

Image to Point Cloud Translation using Conditional Generative Adversarial Network for Airborne LiDAR data

Point2color: 3D Point Cloud Colorization Using a Conditional Generative Network and Differentiable Rendering for Airborne LiDAR

Semantic Segmentation for Full-Waveform LiDAR Data Using Local and Hierarchical Global Feature Extraction

深層学習を用いた点群処理の紹介とFull waveform lidar データへの応用

FWNetAE: Spatial Representation Learning for Full Waveform Data Using Deep Learning

Do Deep Neural Networks Learn Full Waveform LiDAR Data?