Updated on 2026/04/24

写真a

 
IGAUE Takuya
 
Organization
School of Science and Engineering Research Associate
Contact information
The inquiry by e-mail is 《here
External link

Degree

  • 博士(工学) ( 東京大学 )

  • 修士(工学) ( 東京大学 )

Education

  • 2025.3
     

    The University of Tokyo   doctor course   completed

  • 2022.3
     

    The University of Tokyo   master course   completed

  • 2020.3
     

    Hiroshima University   graduated

Papers

▼display all

MISC

  • Motion Transfer-Enhanced StyleGAN for Generating Diverse Macaque Facial Expressions

    Takuya Igaue, Catia Correia-Caeiro, Akito Yoshida, Takako Miyabe-Nishiwaki, Ryusuke Hayashi

    2025.11

     More details

    Generating animal faces using generative AI techniques is challenging because the available training images are limited both in quantity and variation, particularly for facial expressions across individuals. In this study, we focus on macaque monkeys, widely studied in systems neuroscience and evolutionary research, and propose a method to generate their facial expressions using a style-based generative image model (i.e., StyleGAN2). To address data limitations, we implemented: 1) data augmentation by synthesizing new facial expression images using a motion transfer to animate still images with computer graphics, 2) sample selection based on the latent representation of macaque faces from an initially trained StyleGAN2 model to ensure the variation and uniform sampling in training dataset, and 3) loss function refinement to ensure the accurate reproduction of subtle movements, such as eye movements. Our results demonstrate that the proposed method enables the generation of diverse facial expressions for multiple macaque individuals, outperforming models trained solely on original still images. Additionally, we show that our model is effective for style-based image editing, where specific style parameters correspond to distinct facial movements. These findings underscore the model's potential for disentangling motion components as style parameters, providing a valuable tool for research on macaque facial expressions.

    arXiv

    researchmap

    Other Link: https://arxiv.org/pdf/2511.16711v1

  • Cross Line Structured via Mutual Pose Estimation of Two Sets of Spherical Camera and Cross Line Laser

    朝倉友和, 伊賀上卓也, 安き, 山下淳

    精密工学会大会学術講演会講演論文集(CD-ROM)   2024   290 - 291   2024

     More details

    Language:Japanese   Publisher:The Japan Society for Precision Engineering  

    The structural light method is capable of texture-free 3D measurement and has been studied for large structures. In this study, we propose a surface measurement method that simultaneously performs 3D measurement and orientation estimation using a 360° camera.

    DOI: 10.11522/pscjspe.2024a.0_290

    CiNii Research

    J-GLOBAL

    researchmap

  • 360°カメラを用いた光切断法によるトンネル覆工出来形計測システムの開発

    黄再弘, 渡辺大介, 元村亜紀, 伊賀上卓也, 山下淳

    土木学会全国大会年次学術講演会(Web)   79th   2024

  • Reference Region Extraction Preserving Positional Consistency Based on Multi-View Stereo for Change Detection with a Mobile Robot

    星井智仁, 荻原佑介, 伊賀上卓也, ルイ笠原純ユネス, 木下将嘉, 笠原清司, 伊藤裕之, 甲田梨沙, 田村直, 加藤俊哉, 野中史彦, 神田真司, 永谷圭司, 淺間一, AN Qi, 山下淳

    知能メカトロニクスワークショップ講演論文集(CD-ROM)   29th   2024

  • 表情編集のためのマカクサル顔画像生成モデルの開発

    伊賀上卓也, 伊賀上卓也, 宮部貴子, 林隆介

    Vision   36 ( 1 )   2024

  • 人工ニューラルネットワークにおける「不気味の谷」効果

    林隆介, 伊賀上卓也, 伊賀上卓也

    Vision   35 ( 1 )   2023

  • Change Detection on Pipe Outer Surface via Reference Image Extraction from Past Video Using Feature Points

    清水進, 伊賀上卓也, ルイ笠原純ユネス, 大和尚也, 笠原清司, 伊藤裕之, 大東泰三, 田村直, 笹村晃伸, 加藤俊哉, 神田真司, 永谷圭司, 淺間一, 安き, 山下淳

    精密工学会大会学術講演会講演論文集   2023   589 - 590   2023

     More details

    Language:Japanese   Publisher:The Japan Society for Precision Engineering  

    In this study, we propose a method for detecting changes on the outer surface of pipes using inspection videos captured by a patrol inspection robot. In patrol inspections, it is important to detect changes on the outer surface of pipes by comparing them with their past normal state. Therefore, comparing the videos before and after the changes is crucial for change detection. In the proposed method, we extracted comparison image pairs using image features from videos captured by a camera on a mobile robot and performed change detection using deep learning. This method achieved a detection accuracy of 93.9% for changes in the inspection videos.

    DOI: 10.11522/pscjspe.2023a.0_589

    CiNii Research

    J-GLOBAL

    researchmap

  • Development of hole position detection method for remote installation of rock bolts

    伊藤哲, 谷口信博, 森野弘之, 速水桃子, 伊賀上卓也, 山下淳

    土木学会全国大会年次学術講演会(Web)   78th   2023

  • Digital Transformation for NATM Tunnel Lining Quality Control

    吉田健一, 谷口智洋, 伊賀上卓也, 速水桃子, 山下淳

    土木学会全国大会年次学術講演会(Web)   77th   2022

  • Estimation of Three-Dimensional Glass Coordinates with a LiDAR and a Polarization Camera for Indoor SLAM

    荻原佑介, 樋口寛, 伊賀上卓也, 淺間一, 山下淳

    計測自動制御学会システムインテグレーション部門講演会(CD-ROM)   23rd   2022

  • Comparison of Tunnel Three-Dimensional Measurement Based on Line-Structured Light Method Using Tripod, UAV and Quadruped Robot

    伊賀上卓也, 速水桃子, 吉田健一, 山中哲志, 淺間一, 山下淳

    建設ロボットシンポジウム論文集(CD-ROM)   20th   2022

  • 光切断法による高精度3次元モデル生成のためのリングレーザ照射光の2D-3Dマッチングに基づく計測断面統合

    伊賀上卓也, 樋口寛, 井倉幹大, 吉田健一, 伊藤哲, 谷口信博, 山下淳, 淺間一

    画像センシングシンポジウム講演資料集(Web)   27th   2021

  • AN UPPER-LIMB MOTION CLASSIFICATION METHOD BASED ON A SCALE MIXTURE-BASED STOCHASTIC MODEL OF EMG SIGNALS

    伊賀上卓也, 古居彬, 大西亮太, 島田恭平, 辻敏夫

    電子情報通信学会大会講演論文集(CD-ROM)   2020   2020

▼display all

Research Projects

  • Three-Dimensional Measurement via Camera Pose Estimation Based on Structured Light Pattern Learning

    Grant number:25K23422  2025.7 - 2027.3

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research  Grant-in-Aid for Research Activity Start-up  The University of Tokyo

      More details

    Grant amount: \2730000 ( Direct Cost: \2100000 、 Indirect Cost: \630000 )

    researchmap

  • レーザ照射熱伝搬による物体内部の構造推定

    2025 - 2027

    科学技術振興機構  戦略的な研究開発の推進 戦略的創造研究推進事業 ACT-X  東京大学

    伊賀上 卓也

      More details

    Authorship:Principal investigator 

    本研究では,移動ロボットによるインフラ構造物点検のために,物体の内部構造をレーザ光による熱の伝搬によって推定する手法を構築する.センサとコンクリートの接触が必要な従来手法では,大型構造物の網羅的計測に限界があった.一方,レーザ光はその直進性から,非接触に物質の温度を変化させる.本研究ではこの特性を活用し,レーザ光を照射した際の温度分布の時空間的変化から,コンクリート内部の構造を非接触に推定する.

    researchmap

    J-GLOBAL

  • Neural Network Approach for the Line-Structured Light Method under Partially-Textured Environments Using UAV Pairs

    Grant number:24KJ0704  2024.4 - 2026.3

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research  Grant-in-Aid for JSPS Fellows  The University of Tokyo

      More details

    Grant amount: \1500000 ( Direct Cost: \1500000 )

    researchmap