Amirhossein Kazerouni

About

I am a Ph.D. candidate in Computer Science at the University of Toronto, working under the supervision of Michael Brudno and Babak Taati. I am also a graduate researcher at the Vector Institute.

My research explores the synergy between generative models and 3D reconstruction, focusing on 3D data generation, representation, and editting.

I hold a Bachelor of Science in Electrical Engineering from the Iran University of Science and Technology. I am always eager to discuss research ideas and collaborate on exciting projects. Feel free to reach out!

📄 [My CV]

Experience

Research Intern, Samsung Research America (SRA), Toronto, Canada
Graduate Research Assistant, University of Toronto, Toronto, Canada
Graduate Research Assistant, Vector Institute, Toronto, Canada
Remote Research Assistant, RWTH University, Aachen, Germany
Co-founder, AIR Center, Tehran, Iran
B.Sc. in Electrical Engineering, Iran University of Science and Technology, Iran

May 2025 - Present
Jan. 2024 - Present
Jan. 2024 - Present
Mar. 2022 - Jan. 2024
Jul. 2020 - Jul. 2022
Sep. 2017 - Feb. 2022

News

[Jul. 2025] 🎉 Paper LIFT accepted at ICCV'25.

[May 2025] 🪐 Started my research internship at Samsung Research America (SRA).

[Jan. 2025] 🎉 One paper, SUM, accepted as an oral presentation at WACV'25.

[Feb. 2024] 🎉 Paper FuseNet accepted at ISBI'24.

[Jan. 2024] 🎓 Started my Ph.D. in Computer Science at the University of Toronto.

[Oct. 2023] 🎉 Two papers, INCODE and D-LKA Net, accepted at WACV'24.

[Oct. 2023] 🎉 Our survey paper on Vision Transformers in Medical Imaging accepted in the Medical Image Analysis Journal.

[Aug. 2023] 🎉 One main paper, LaplacianFormer, and three workshop papers, DermoSegDiff, WaveFormer, and DAE-Former, accepted at MICCAI'23.

[Aug. 2023] 🎉 Two papers, S³-Net and INR Survey in Medical Imaging, accepted at ICCV'23 CVAMD Workshop.

[Aug. 2022] 🎉 Our survey paper on Diffusion Models in Medical Imaging accepted in the Medical Image Analysis Journal.

[Apr. 2023] 🎉 Two papers, MS-Former and MMCFormer, accepted for oral presentations at MIDL'23.

[Oct. 2022] 🎉 Paper HiFormer on medical image segmentation accepted at WACV’23.

[Oct. 2022] 🎉 Paper on a real-time vision-based environment perception system accepted at a NeurIPS'22 Workshop.

[Sep. 2021] 🎓 Successfully defended my bachelor's thesis on designing, simulating, and building a self-driving car.

Publications

LIFT: Latent Implicit Functions for Task- and Data-Agnostic Encoding

Amirhossein Kazerouni, Soroush Mehraban, Michael Brudno, Babak Taati

Conference: ICCV 2025

Project Page | Paper

MedScale-Former: Self-guided multiscale transformer for medical image segmentation

Sanaz Karimijafarbigloo, Reza Azad, Amirhossein Kazerouni, Dorit Merhof

Journal: Medical Image Analysis (MedIA)

Paper

SUM: Saliency Unification through Mamba for Visual Attention Modeling

Alireza Hosseini*, Amirhossein Kazerouni*, Saeed Akhavan, Michael Brudno, Babak Taati

Conference: WACV 2025 | Oral presentation

Project Page | Paper | GitHub

FuseNet: Self-Supervised Dual-Path Network for Medical Image Segmentation

Amirhossein Kazerouni, Sanaz Karimijafarbigloo, Reza Azad, Yury Velichko, Ulas Bagci, Dorit Merhof

Conference: ISBI 2024

Paper | GitHub

INCODE: Implicit Neural Conditioning with Prior Knowledge Embeddings

Amirhossein Kazerouni, Reza Azad, Alireza Hosseini, Dorit Merhof, Ulas Bagci

Conference: IEEE/CVF WACV 2024

Project Page | Paper | GitHub

Deformable Large Kernel Attention visual teaser

Beyond Self-Attention: Deformable Large Kernel Attention for Medical Image Segmentation

Reza Azad, Leon Niggemeier, Michael Huttemann, Amirhossein Kazerouni, Ehsan Khodapanah Aghdam, Yury Velichko, Ulas Bagci, Dorit Merhof

Conference: IEEE/CVF WACV 2024

Paper | GitHub

Laplacian-Former: Overcoming the Limitations of Vision Transformers in Local Texture Detection

Reza Azad, Amirhossein Kazerouni, Babak Azad, Ehsan Khodapanah Aghdam, Yury Velichko, Ulas Bagci, Dorit Merhof

Conference: MICCAI 2023

Paper | GitHub

Unlocking Fine-Grained Details with Wavelet-based High-Frequency Enhancement in Transformers

Reza Azad, Amirhossein Kazerouni, Alaa Sulaiman, Afshin Bozorgpour, Ehsan Khodapanah Aghdam, Abin Jose, Dorit Merhof

Conference: MICCAI 2023 MLMI Workshop

Paper | GitHub

DermoSegDiff: A Boundary-aware Segmentation Diffusion Model for Skin Lesion Delineation

Afshin Bozorgpour*, Yousef Sadegheih*, Amirhossein Kazerouni*, Reza Azad, Dorit Merhof

Conference: MICCAI 2023 PRIME Workshop

Paper | GitHub

Self-supervised Semantic Segmentation: Consistency over Transformation

Sanaz Karimijafarbigloo, Reza Azad, Amirhossein Kazerouni, Yury Velichko, Ulas Bagci, Dorit Merhof

Conference: ICCV 2023 CVAMD Workshop

Paper | GitHub

INR in Medical Imaging Survey visual teaser

Implicit Neural Representation in Medical Imaging: A Comparative Survey

Amirali Molaei, Amirhossein Aminimehr, Armin Tavakoli, Amirhossein Kazerouni, Bobby Azad, Reza Azad, Dorit Merhof

Conference: ICCV 2023 CVAMD Workshop

Paper | GitHub

Diffusion Models in Medical Imaging Survey visual teaser

Diffusion Models in Medical Imaging: A Comprehensive Survey

Amirhossein Kazerouni, Ehsan Khodapanah Aghdam, Moein Heidari, Reza Azad, Mohsen Fayyaz, Ilker Hacihaliloglu, Dorit Merhof

Journal: Medical Image Analysis (MedIA)

Paper | GitHub

Vision Transformers in Medical Imaging Survey visual teaser

Advances in Medical Image Analysis with Vision Transformers: A Comprehensive Review

Reza Azad, Amirhossein Kazerouni, Moein Heidari, Ehsan Khodapanah Aghdam, Amirali Molaei, Yiwei Jia, Abin Jose, Rijo Roy, Dorit Merhof

Journal: Medical Image Analysis (MedIA)

Paper | GitHub

DAE-Former: Dual Attention-guided Efficient Transformer for Medical Image Segmentation

Reza Azad, René Arimond, Ehsan Khodapanah Aghdam, Amirhossein Kazerouni, Dorit Merhof

Conference: MICCAI 2023 PRIME Workshop

Paper | GitHub

MS-Former: Multi-Scale Self-Guided Transformer for Medical Image Segmentation

Sanaz Karimijafarbigloo, Reza Azad, Amirhossein Kazerouni, Dorit Merhof

Conference: MIDL 2023 | Oral presentation

Paper | GitHub

MMCFormer: Missing Modality Compensation Transformer for Brain Tumor Segmentation

Sanaz Karimijafarbigloo, Reza Azad, Amirhossein Kazerouni, Saeed Ebadollahi, Dorit Merhof

Conference: MIDL 2023 | Oral presentation

Paper | GitHub

HiFormer: Hierarchical Multi-scale Representations Using Transformers for Medical Image Segmentation

Moein Heidari*, Amirhossein Kazerouni*, Milad Soltany*, Reza Azad, Ehsan Khodapanah Aghdam, Julien Cohen-Adad, Dorit Merhof

Conference: IEEE/CVF WACV 2023

Paper | GitHub

Real-Time Vision-Based System visual teaser

An Intelligent Modular Real-Time Vision-Based System for Environment Perception

Amirhossein Kazerouni, Amirhossein Heydarian, Milad Soltany, Aida Mohammadshahi, Abbas Omidi, Saeed Ebadollahi

Conference: NeurIPS 2022 Workshop on Machine Learning for Autonomous Driving

Paper | GitHub

Contact

For inquiries or feedback on my research, don't hesitate to reach out. I’m always happy to hear from you and exchange ideas.

Email:

amirhossein@cs.toronto.edu