Mehmet Aygün

I am a Ph.D. student at the University of Edinburgh working with Oisin Mac Aodha. My research revolves around 3D computer vision (reconstruction/generation) and self-supervised learning. Prior, I had the privilege of collaborating with Laura Leal-Taixé on problems related to 3/4D scene understanding at the Technical University of Munich.

CV  /  Google Scholar  /  Twitter

• Feb 2024, SAOR got accepted to CVPR 2024.
• 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 benchmark designed to evaluate depth cue understanding, with findings across 20 diverse and representative pre-trained vision models.

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

A new approach using 3D reconstruction to enhance the robustness of self-supervised vision models.

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