Skip to main content

About me

Gemma Canet Tarrés

I am currently a third year Computer Vision PhD student advised by Prof. John Collomosse and Dr Andrew Gilbert at the Center for Vision, Speech and Signal Processing at the University of Surrey. I am currently also a Research Scientist Intern at Adobe Research , under the supervision of Soo Ye Kim. I completed my first internship with this research group in the summer of 2023 and was fortunate enough to be invited back for a second internship starting in February 2024.

My research interests are in the broad areas of computer vision and machine learning, with a focus on deep learning. Particularly, I have an interest in image generation and my current research is in Multimodal Image Generation and Object Compositing using Diffusion Models.

Previously, I studied Mathematics and Physics Engineering at the Universitat Politècnica de Catalunya (UPC) under the double degree program of CFIS (Center for high interdisciplinary training). During my last year, I completed my thesis in University of Toronto, advised by Prof. Sven Dickinson. Later on, I completed the Masters in Computer Vision organized by Universitat Autònoma de Barcelona (UAB) where I worked with Montse Pardàs for my dissertation.

During my undergraduate studies, I worked as a software developer for two summer internships at Wiris Math and BaseTIS. While studying my masters, I concurrently worked part time in the former start-up Vilynx, taking part in different NLP projects. Finally, right before starting my PhD I spent 6 months at InterDigital, working as a research intern under the supervision of Louis Chevallier.

If you’re interested in knowing more about my work, check out my publications or feel free to contact me.


2024