Mehmet Aygün

I am currently a Ph.D. student at the University of Edinburgh under the guidance of Oisin Mac Aodha. My research revolves around developing methods for image and video understanding, where I aim to create systems that capable of reasoning about objects and their intricate relationships with minimal or no supervision.

Prior, I had the privilege of collaborating with Laura Leal-Taixé on problems related to 3-4D scene understanding during my master's degree at the Technical University of Munich (TUM).

CV  /  Google Scholar  /  GitHub /  Twitter  /  LinkedIn

• Aug 2023, I joined Meta AI as a Research Scientist Intern.
• Jul 2022, Our paper about unsupervised semantic correspondence is accepted to ECCV, 2022.
• Feb 2021, Our paper titled 4D Panoptic Lidar Segmentation is accepted to CVPR, 2021.
• Oct 2020, Our paper about 3D shape correspondence is accepted to 3DV, 2020.
• Jun 2018, I received DAAD scholarship for studying in Germany.
• Oct 2017, at ICCV 2017, our paper received Honorable Mention Award from TASK-CV workshop.

I am interested in computer vision and machine learning. In particular, I am interested in developing image understanding models that can learn fundamental priors and representations through self-supervision alone. Examples of which include investigating the role of shape in semantic understanding.

A new self-supervised approach for estimating shape of highly articulated objects such as animals from single-view images.

A novel unsupervised approach for semantic correspondence problem, an evaluation framework along with a metric, and through evaluation of current methods.

A new method and evaluation metric for the task of 4D panoptic segmentation.

An emprical study showing that Heat Kernels can replace Geodesic Matrices for unsupervised dense shape correnspondence problem

This ubiquitous CS researcher website template spawned from here.
Last updated: Jul 2022