Takayuki Shinohara

Takayuki Shinohara

Hi! My name is Takayuki. I was originally born in Tochigi, Japan, and now I’m a Ph.D. student at the Tokyo Institute of Technology in Yokohama, Japan. I study full-waveform LiDAR data analysis with a Deep Learning method.

Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Pages

Posts

Story of entering the doctoral program at Tokyo Tech

less than 1 minute read

Published:

Overview

  • Often a doctorate is needed to work
  • Doctoral degree is required when working overseas
  • If I do not have a doctorate, I will not be treated as an engineer
  • I decided to enter because I wanted to live as an engineer rather than a worker.

portfolio

publications

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

Published in 2019 IEEE International Symposium on Multimedia (ISM), 2019

This paper is about a novel representation learning method for raw full waveform lidar data, using spatial deep learning method.

Recommended citation: T.Shinohara,et.al. (2019). "FWNetAE: Spatial Representation Learning for Full Waveform Data Using Deep Learning." 2019 IEEE International Symposium on Multimedia (ISM). https://ieeexplore.ieee.org/document/8959007

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

Published in ACM SIGSPATIAL 2020, 2020

This paper is about a novel semantic segmentation method for raw full waveform lidar data, using deep learning method with local feature extraction module and global feture extraction module.

Recommended citation: 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 https://dl.acm.org/doi/10.1145/3397536.3422209

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

Published in CVPR 2021 Workshop EarthVision2021, 2021

This paper is about a novel Point Cloud colorization method for airborne lidar data, using deep learning method with conditional GAN and differentiable rendering.

Recommended citation: 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. https://openaccess.thecvf.com/content/CVPR2021W/EarthVision/html/Shinohara_Point2color_3D_Point_Cloud_Colorization_Using_a_Conditional_Generative_Network_CVPRW_2021_paper.html

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

Published in ISPRS 2020, 2021

This paper is about a novel generative model for Poiint Cloud generatation for airborne LiDAR data, using deep learning method with VAE and GAN.

Recommended citation: 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. https://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/V-2-2021/169/2021/

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

Published in IEEE IGARSS 2021, 2021

This paper is about a novel generative model for Poiint Cloud generatation for airborne LiDAR data, using deep learning method with VAE and GAN.

Recommended citation: 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. https://ieeexplore.ieee.org/document/9554523

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

Published in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 2021

This paper is about a novel generative model for Waveform generatation from Point Cloud for airborne Full Waveform LiDAR data, using deep learning method with cGAN.

Recommended citation: 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. https://ieeexplore.ieee.org/document/9599498

talks