Amir Mohammad Babaei

Computer Engineering M.Sc. Student @ Sharif University of Technology

Tehran, Iran

CV (October, 2025)

I’m a computer vision researcher who enjoys turning tough visual problems into clean, reproducible solutions. I’m doing my M.Sc. at Sharif University of Technology in the Image Processing Lab (IPL), where I work at the intersection of generative models and super-resolution, lately exploring diffusion-based approaches for hard, blind settings.

Along the way, I’ve been lucky to learn from outstanding mentors. At IPL (advised by Prof. Shohreh Kasaei), I’ve built and evaluated models with care (tight ablations, clear baselines, and code that others can run). I also collaborated with Dr. Alireza Esmaeilzehi on image super-resolution ideas and kernel-estimation theory, which sharpened my taste for practical yet principled research.

What I work with. PyTorch, diffusion/VAEs/GANs, BasicSR/KAIR/MMCV, Detectron, OpenCV, CUDA, Transformers; rigorous evaluation, dataset hygiene, experiment tracking, and readable research code. (If you’re building in these areas (or teaching them) I’m your person.)

What I’m aiming for. I love collaborating on projects that sit where theory meets deployment: efficient generative models, blind SR, and multimodal vision tasks. If you’re exploring these topics, I’d love to connect.

Links:
— Lab: Image Processing Lab (IPL), SUT · Advisor: Prof. Shohreh Kasaei · Collaborator: Dr. Alireza Esmaeilzehi.

News

Sep 27, 2025

We’re delighted to announce that our survey, A Comprehensive Survey on Knowledge Distillation, has been accepted and published in Transactions on Machine Learning Research (TMLR); the preprint is available on arXiv.

Mar 15, 2025

We are pleased to announce the publication of the preprint of our survey, A Comprehensive Survey on Knowledge Distillation, on ArXiv.

Jan 19, 2025

Our Paper CLBSR: A deep curriculum learning-based blind image super resolution network using geometrical prior has been accepted at Image and Vision Computing.