Hernán CARRILLO ☕️

Hernán CARRILLO

PhD Candidate

Bordeaux University

I am a recent Ph.D. graduate in Computer Science from the University of Bordeaux, currently looking for professional opportunities in the field of computer vision. During my time with the image and sound team at LaBRI, I gained research experience and contributed to the ANR-funded PostProdLEAP project. This has helped me develop expertise in deep learning, imaging inverse problems, and image and video processing. I would like to utilize this expertise in a professional setting and continue to grow in the field of computer vision.

Education

 
 
 
 
 
Bordeaux University
PhD. in Computer Science
Bordeaux University
October 2020 – February 2024 Bordeaux, France
 
 
 
 
 
Ecole Centrale de Nantes
Msc. in Signal and image processing
Ecole Centrale de Nantes
October 2018 – September 2020 Nantes, France
 
 
 
 
 
Universidad del Norte
B.Eng in Electronics
Universidad del Norte
February 2013 – December 2017 Barranquilla, Colombia

Publications

Diffusart: Enhancing Line Art Colorization With Conditional Diffusion Models
his paper presents a novel interactive approach for line art colorization using conditional Diffusion Probabilistic Models (DPMs). In our proposed approach, the user provides initial color strokes for colorizing the line art….
Hernán CARRILLO, Michael Clément, Aurélie Bugeau, Edgar Simo-Serra
PDF Cite Code
Diffusart: Enhancing Line Art Colorization With Conditional Diffusion Models
Super-attention for exemplar-based image colorization
This article presents a deep learning approach for exemplar-based image colorization. It propose a novel attention block called super-attention, which is computed from superpixel features….
Hernán CARRILLO, Michael Clément, Aurélie Bugeau
PDF Cite Code
Super-attention for exemplar-based image colorization
Analysis of different losses for deep learning image colorization
In this article, we examine how various loss functions impact the process of automatic image colorization. Here, we specifically answer the question, ‘Does the choice of the objective function plays an important role in the colorization results?’.
Coloma Ballester, Aurélie Bugeau, Hernán CARRILLO, Michael Clément, Rémi Giraud, Lara Raad, Patricia Vitoria
PDF Cite
Analysis of different losses for deep learning image colorization
Influence of Color Spaces for Deep Learning Image Colorization
In this article, we examine how various color spaces impact the process of automatic image colorization. Here, we specifically answer the question, ‘Is it crucial to correctly choose the right color space in deep learning-based colorization?’.
Coloma Ballester, Aurélie Bugeau, Hernán CARRILLO, Michael Clément, Rémi Giraud, Lara Raad, Patricia Vitoria
PDF Cite
Influence of Color Spaces for Deep Learning Image Colorization
Non-local matching of superpixel-based deep features for color transfer
We proposes a new method for efficiently matching high-resolution feature maps from CNNs using attention mechanisms, which relies on a superpixel-based pooling dimensionality reduction strategy….
Hernán CARRILLO, Michael Clément, Aurélie Bugeau
PDF Cite
Non-local matching of superpixel-based deep features for color transfer
See all publications