About me

This is Aitor Alvarez-Gila’s personal webpage.

I am a lead researcher at Tecnalia’s Computer Vision and Visual Interaction group. My main research interests are deep learning and other machine learning / computer vision models for image and 3D understanding, and spectral imaging. UPDATE 2022-: I now also care about multimodal (e.g. Vision & Language) models and the latest trends in generative deep learning and 3D neural scene representations (e.g. NeRF, 3D Gaussians), of course, who doesn’t? Anyway, I have been building stuff that works based on these techniques since 2010 for biomedical, steelmaking, agro, waste management and packaging industries, among others.

I got my PhD on deep learning in 2022 from Universitat Autònoma de Barcelona (UAB). The thesis was developed at Computer Vision Center’s LAMP (Learning And Machine Perception) team, under the supervision of Joost van de Weijer (CVC) and Estibaliz Garrote (Tecnalia).

Prior to that, I completed the Erasmus Mundus CIMET Master (now COSI-Computational Colour and Spectral Imaging) in color science and computer vision and made research stays at the Universities of Granada (ES), Jean Monnet (Saint-Etienne, FR), NTNU (Gjøvik, NO) and UvA (Amsterdam, NL) from 2008 until 2010.

In past lives, I’ve also been a consultant in a dark suit working for multinational financial companies and public administration.

Even before that, I did some research on network security at the University of the Basque Country, where I first graduated as Telecommunications Engineer (2005).