Patrick Hsu
AI Research & Development
As a seasoned AI engineer with six years of experience, I specialize in computer vision, 3D body model reconstruction, generative AI, and possessing some knowledge in natural language processing (NLP).
| New Taipei City, Taiwan 0958881053 [email protected]
Work Experience (6 years)
Algorithm Research & Design• TG3D Studio
May 2021 - Present
A skilled engineer specialized in computer vision and generative AI with experience in developing and training AI models for digital fashion applications.
Body AI: Virtual Try On
Integrated cutting-edge technologies such as Stable Diffusion, ControlNet, and Prompt Engineering to create a sophisticated system for generating virtual try-on images, ensuring seamless and realistic visualization of clothing items on virtual avatars.
- Computer Vision
- Stable Diffusion
Body AI: Mobile Scanner
Successfully reconstructed highly accurate 3D body models by leveraging two full-body side profile photos, achieving a remarkable precision level with a size error margin of less than 3 cm.
- Computer Vision
- Body Reconstruction
- Stable Diffusion
DApp: Exercise Classification
Implemented real-time activity recognition for specified exercises, including but not limited to push-ups and squats, enabling accurate tracking and analysis of workout routines.
- Skeleton Detection
- Motion Classification
Body AI: 3D Body Data Analysis
Engage in a variety of AI side projects focused on leveraging 3D body data, encompassing tasks such as Body ID Recognition, Body Measurements Prediction, and Body Shape Classification.
- Mesh Data Processing
- Body Modulization: SMPL
Project Engineer • Acer Inc.
Jan 2018 - May 2021
Working in research and development (RND), I provided demand analysis, conceived system architecture, and developed core technology in AI projects
Medical AI: Cancer Cells Detection
Designed an image preprocessing algorithm and conducted training and optimization for a cancer cell detection model. Assisted in planning and implementing cancer cell detection applications, as well as developing an auto-training application for the detection model.
Computer Vision: Human Action Recognition
Conducted training for a human skeleton detection model. Developed static human action recognition model based on images and dynamic human action recognition model based on videos.
Autonomous Vehicle: Conducted Multiple AI Models in Perception System
Trained and optimized 2D and 3D object detection models, as well as traffic light recognition models. Developed inference models using CUDA library and facilitated integration into Apollo environment for perception system.
Computer Vision: Face Recognition
Developed an Image Collection System, assessed Inference Model performance, and aided in integrating systems with Inference Model APIs.
Education
National Taiwan University
Sep 2015 – June 2017
Master of Engineering in Department of Bio-mechatronics Engineering
Master's Thesis: An Evaluation Approach for Photovoltaic System Operation: Fault Detection and Diagnosis
National Cheng Kung University
Sep 2010 – June 2015
Bachelor of Engineering in Department of Aeronautics and Astronautics
Skills
Programming
Linux OS
Python
Docker
Git
AWS Service
AI: Deep Learning
Pytorch Framework
Computer Vision Model Training and Development
Generative AI Model Development
Hugging Face Framework
LLM development
