Interest
Computer Vision, NLP, Web
Contact
mjun __at__ mjunya.com
Skill
Education
- Doctor's Degree in Computer Science2023.03 - 2026.03 Computer Science Program, Graduate School of Science and Technology, Meiji University Image Processing Laboratory (IPLab)
- Master's Degree in Computer Science2021.04 - 2023.03 Computer Science Program, Graduate School of Science and Technology, Meiji University Image Processing Laboratory (IPLab)
- Bachelor's Degree in Computer Science2017.04 - 2021.03 Department of Computer Science, School of Science and Technology, Meiji University Image Processing Laboratory (IPLab)
Work Experience
- Meiji University2023.04 - 2026.03 Research Associate
- Yahoo Japan 2022 Summer Internship
- RECRUIT Job for Student 2022 Autumn ~Engineer/Data Specialist~
- SPIC
- SensAI
- Meiji University2021.04 - 2023.03 Teaching Assistant
- Qdoga Inc.
Publication
- 領域分割結果から得られるエッジを手がかりとした部屋の3次元構造推定画像電子学会誌 第55巻 第1号, 2026.1
- Automatic annotation method for day–night aerial infrared image dataset creation and its application to semantic segmentationOptical Engineering, 2025.9
- Semantic Edge Extraction by Logical Operations for Room Structure Estimation Using a Segmentation ResultInternational Conference on Extended Reality, 2025.6
- 屋内環境における単一画像からの3次元情報推定手法の回転耐性の向上電子情報通信学会(IEICE) ライフインテリジェンスとオフィス情報システム研究会(LOIS), 2025.03
- バーチャル内見を目的とする3次元構造推定のための効率的なセマンティックエッジ抽出電子情報通信学会(IEICE) MVE研究会(SIS), 2025.03
- CNN における積和演算の高速化に関する一検討第50回 パルテノン研究会, 2024.12
- AMD Ryzen CPUを対象としたCNNにおける積和演算の並列実装第50回 パルテノン研究会, 2024.12
- Creation of Day-Night Visible-Thermal Paired Image Dataset via Image RegistrationIEEE IRC, 2024.12
- Improving Resolution of Translated Infrared ImagesIEEE SENSORS, 2024.10
- 合成画像を訓練サンプルとする分類器のバイラテラルフィルタによる精度向上電子情報通信学会(IEICE) スマートインフォメディアシステム研究会(SIS), 2024.10
- 3D Structure Estimation of Room Environment Using Semantic Segmentation and Model FittingIEEE International Workshop on Metrology for Living Environment (MetroLivEnv) , 2024.06
- 遠隔協調作業における臨場感向上のための単眼カメラによる部屋の3次元構造の推定ライフインテリジェンスとオフィス情報システム研究会(LOIS), 2024.03
- Data Augmentation for Semantic Segmentation Using a Real Image Dataset Captured around the Tsukuba City HallJournal of Robotics and Mechatronics, 2023.12
- Dataset Creation for Semantic Segmentation Using Colored Point Clouds Considering Shadows on Traversable AreaJournal of Robotics and Mechatronics, 2023.12
- Human Pose Estimation Based on Part-Wise 6-DoF Pose Estimation2023 International Workshop on Smart Info-Media Systems in Asia, pp.77-81, 2023.9
- 空撮画像を対象としたInformed-Filtersに基づく人検出のC++AMPを用いたリアルタイム実装画像電子学会 画像電子学誌 第52巻 第2号 pp.329-338, 2023.4
- 意味論的領域分割の計算コストと精度の関係に関する研究電子情報通信学会(IEICE) スマートインフォメディアシステム研究会(SIS), 2022.12
- 深層学習に基づく小物体検出の精度向上に関する一検討電子情報通信学会(IEICE) スマートインフォメディアシステム研究会(SIS), 2022.12
- Testing environment for developing a wireless networking system based on image-assisted routing for sports applicationsProceedings of the 9th International Conference on Sport Sciences Research and Technology Support, icSPORTS 2021, October 28-29, 2021
- A study on accuracy improvement of small object detection using deep neural networksIEEE Asia Pacific Conference on Circuit and Systems, APCCAS 2021, Penang, Malaysia, November 22-26, 2021
Award
- Best Presentation Award "AMD Ryzen CPUを対象としたCNNにおける積和演算の並列実装"第50回 パルテノン研究会, 2024.12
- Good Presentation Award "遠隔協調作業における臨場感向上のための単眼カメラによる部屋の3次元構造の推定"ライフインテリジェンスとオフィス情報システム研究会(LOIS), 2024.03
Open Source
Writing
Current Projects
Search System Development using NLP Embedding Models
I am developing a search system using embedding models with BERT and Faiss from natural language processing. The server side uses FastAPI, and the infrastructure uses both AWS and on-premises environments. The search target is 60TB of PDF documents, for which high-speed search is required. I am creating HuggingFace Datasets, training tokenizers and models, and building custom models.
Past Projects
3D Room Structure Reconstruction using a Monocular Camera
In recent years, the spread of VR devices and advances in technology have increased demand for reflecting real space in virtual space. In particular, technologies for reflecting indoor environments into virtual space are used in various fields such as architecture, interior design, and robotics. Reflecting real space in virtual space requires estimating the 3D structure of real space, but this typically requires expensive equipment and faces challenges in terms of computational cost and ease of measurement. In this research, I limit the estimation target to indoor environments and propose a 3D structure estimation method using a single image. While existing methods generally use depth estimation, this research proposes a novel approach based on semantic segmentation and cuboid fitting. Experiments using 3D CG show that the proposed method achieves accuracy exceeding existing methods and delivers competitive results.6DoF Pose Estimation of Objects using Deep Learning Models
This research aims to devise a high-precision 3D object pose estimation method. High-precision 3D object pose estimation involves various challenges, including datasets for training, handling occlusion, and camera calibration. This research pursues everything from dataset creation to practical application of the models.
SPIC Inc. Internal System Development
I am building internal systems for SPIC Inc., which develops and sells health-related products including Lypo-C, beauty-related products, and original brand products.
Video Streaming Service Development
Developed a video streaming service for iOS/Android. The server side used Ruby's Sinatra, and AWS was used for the infrastructure. Firebase Authentication was used for authentication. I was responsible for backend API development, Firebase Authentication implementation, iOS app implementation with SwiftUI, and building CI/CD using Xcode Cloud and GitHub. In particular, I migrated the iOS app from UIKit to SwiftUI entirely from scratch by myself. The video streaming service has a multi-tenant architecture, enabling genre-specific streaming services to be launched easily by simply specifying the app design and related settings.Small Object Detection using Deep Learning
Various methods for object detection based on deep learning have been proposed, but there is still significant room for improvement in the accuracy of small object detection. This research examines which processing is important for improving the detection accuracy of small objects, and proposes a novel method to improve small object detection accuracy based on the findings.