Matiur Minar
Graduate Research Assistant
Seoul, South Korea
Summary
🤩
Rockstar🎓
Top SchoolMatiur Minar is a computer vision researcher and AI/ML engineer with 11 years of experience building production-grade deep learning systems across academia and industry. He has driven research in 3D vision and generative models at top Korean labs and implemented practical solutions—from CVPRW virtual try-on codebases to LLM-powered virtual mall assistants and geospatial digital twins for smart cities. His work spans end-to-end deployment: dataset curation and model architecture tweaks to REST API integration and SLA-driven telecom systems that served tens of millions with 99.99% uptime. He has a strong track record in translating research into commercial impact in fashion, healthcare drug-discovery, and urban infrastructure across Asia and the Gulf. Currently a Graduate Research Assistant at Sogang University and incoming PhD student, he combines rigorous academic output with hands-on engineering and notable open-source contributions to CP-VTON+. Fluent in cross-domain problem solving, he brings both systems-level reliability and experimental creativity to complex AI projects.
11 years of coding experience
11 years of employment as a software developer
Doctor of Philosophy - PhD, Computer Science and Engineering, Doctor of Philosophy - PhD, Computer Science and Engineering at Sogang UniversityMaster's degree, Electrical and Information Engineering, Master's degree, Electrical and Information Engineering at Seoul National University of Science and TechnologyBachelor of Science (BSc), Computer Science and Engineering, Bachelor of Science (BSc), Computer Science and Engineering at Bangladesh University of Engineering and Technology
English, Bangla, Japanese, Korean, Arabic
Stackoverflow
462reputation
36kreached
10answers
3questions
Github Skills (15)
computer-vision10
image-segmentation10
pytorch10
segmentation10
python9
machine-learning8
modeling8
trainings8
data-preprocessing7
ui-automation6
appium6
caffe6
deep-learning6
automation6
android6
Programming languages (4)
Github contributions (5)
minar09/cp-vton-plus
May 2020 - Nov 2022
Official implementation for "CP-VTON+: Clothing Shape and Texture Preserving Image-Based Virtual Try-On", CVPRW 2020
Role in this project:
ML Engineer
ML EngineerContributions:2 reviews, 75 commits, 4 PRs in 2 years 5 months
Contributions summary:Matiur's contributions center around modifying and refining the code for a virtual try-on system (CP-VTON+). Their work includes adjustments to dataset processing, specifically related to segmentation and body masking, along with modifications to the testing and training scripts. Code changes encompass updates to data paths, modifications to model architectures, and adjustments to the loss functions, indicating a focus on model training and evaluation.
pytorchvirtual-try-ondeep-learningcomputer-graphicscomputer-vision
minar09/Fashion-Clothing-Parsing
Jan 2019 - May 2020
FCN, U-Net models for fashion clothing parsing
Contributions:62 commits, 2 PRs, 54 pushes in 1 year 4 months
fcnclothingparsingu-netfashion
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.