Andrés Felipe Romero Vergara

I am currently a postdoctoral researcher in the Computer Vision Lab (CVL) at ETH Zürich, Switzerland, working with prof. Luc Van Gool and Dr. Radu Timofte. Before joining CVL, I spent 5 delightful years in the Biomedical Computer Vision (BCV) group working closely with prof. Pablo Arbelaez at the University of Los Andes (Colombia).

My areas of interest lie in the field of Machine Learning, Artificial Intelligence, and Technologies, namely Computer Vision and Pattern Recognition. Particularly, I am interested in developing techniques using Generative Adversarial Networks (GANs) for image-to-image translation problems such as image editing, semantic manipulations, style-guided transformations, super-resolution among others.

News

Reviewer Experience

I have served as a reviewer for top venue Computer Vision conferences such as CVPR, ECCV, ICCV, and ACCV, as well as journals such as TPAMI and Computer and Graphics.

Non-academical interests:

I am very much into the photography world. As to the date, I own a Sony α7III, and I love to shoot with an 18-35mm lens. You can check some of my pictures below.
In a very different scenario, I am a backpack traveler, I try to explore different places as much as possible, a gym enthusiast with empirical background, an not-so-pro player of Ultimate Frisbee, and I try to maintain my life eating as healthy as possible.

• SMILE: Semantically-guided Multi-attribute Image and Layout Editing.
  Andrés Romero, Luc Van Gool, Radu Timofte.
  Arxiv, 2020.
   

• DeepSEE: Deep Disentangled Semantic Explorative Extreme Super-Resolution.
  Marcel C. Bühler, Andrés Romero, Radu Timofte.
  ACCV, 2020.
   
  
  
• UltraGAN: Ultrasound Enhancement Through Adversarial Generation.
  Maria Escobar, Ángela Castillo, Andrés Romero, Pablo Arbeláez.
  MICCAI, Workshop on Simulation and Synthesis in Medical Imaging, 2020.
   
  
  
• SESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing Objects.
  Evangelos Ntavelis, Andrés Romero, Iason Kastanis,  Luc Van Gool, Radu Timofte.
  ECCV, 2020.
   
  
  
• Unsupervised Multimodal Video-to-Video Translation via Self-Supervised Learning.
  Kangning Liu, Shuhang Gu, Andrés Romero, Radu Timofte.
  WACV, 2021. To appear.
  
  
  
• SMIT: Stochastic Multi-Label Image-to-Image Translation (2019).
  Andrés Romero, Pablo Arbeláez, Luc Van Gool, Radu Timofte.
  ICCV, AIM Workshop, 2019.
   
  
  
• Multi-View Dynamic Facial Action Unit Detection (2018).
  Andrés Romero, Juan León, Pablo Arbeláez.
  Image and Vision Computing, 2018.