Image Generation

Angela Castillo
Maria Escobar
Diego Valderrama
Andrés Romero
Pablo Arbeláez
Collaboration with Luc Van Gool, Radu Timofte.

Generation is the task of creating new data from a specific dataset. Image generation is the line of research that focuses on creating images whose distribution is similar to that of the training dataset. We aim at designing novel methods that might be conditioned on specific attributes of the training dataset to create high-quality images not only for natural images but also for medical images.

Presentation Video


UltraGAN: Ultrasound Enhancement through Adversarial Generation

M. Escobar*, A. Castillo*, A. Romero, P. Arbeláez

Workshop on Simulation and Synthesis in Medical Imaging (SASHIMI) 2020

SMIT: Stochastic Multi-Label Image-to-Image Translation

A. Romero, P. Arbeláez, L. Vann Gool and R. Timofte

17th International Conference on Computer Vision (ICCV) Workshops, 2019

"Ideas are easy. It's the execution of ideas that really separates the sheep from the goats" - Sue Grafton

Cra. 1 E No. 19A - 40.  

Mario Laserna Building - School of Engineering 

Bogotá, Colombia

Cód. Postal: 111711

+(571) 332 4327, 332 4328, 332 4329