Juan Raúl Padrón Griffe

About me
I am a researcher in computer graphics at the Graphics and Imaging Lab at the Universidad de Zaragoza, working at the intersection of physically-based rendering, material modeling, and geometry processing. My research centers on multi-scale materials, from biological tissues such as human skin, scales, and feathers, to intricate human-made structures like cosmetics and granular media. Recently, I have also explored particle dynamics for sampling in computer graphics, including our recent paper accepted to EGSR 2026. My work has been published at different computer graphics venues including the Eurographics Symposium on Rendering (EGSR), Pacific Graphics (PG), and SIGGRAPH. I am currently collaborating with Zahra Montazeri's group on the representation and rendering of textiles, with a submission under review and a second project underway.

I completed my PhD as a Marie Sklodowska-Curie Fellow of the EU Project PRIME, supervised by Prof. Adolfo Muñoz and Prof. Adrian Jarabo. Earlier, during my Master of Science in Informatics at the Technical University of Munich, I conducted research on 3D scanning and neural rendering for object and face relighting, advised by Prof. Justus Thies; this followed a Bachelor of Science in Computer Science at the Universidad Central de Venezuela, where my thesis explored procedural terrain generation and visualization.

Looking for Opportunities
I recently defended my Ph.D. dissertation, Modeling and Rendering of Multiscale Materials. I am currently seeking postdoctoral and faculty positions, as well as research scientist roles, where I can continue developing my research agenda in computer graphics and computer vision for the digital acquisition, representation, and simulation of virtual worlds. If you are building a research group, have a postdoctoral or faculty opening, or simply want to discuss a potential collaboration, please feel free to reach out!

Projects

Deep Reinforcement Learning for Protein Folding

2018, Oct 02    

The protein structure determines properties and functions of the protein. Therefore, scientistic can develop drugs for this specific unique protein shape in order to cure diseases. Nowadays, Machine Learning methods arise as an alternative to the costly experimentation techniques (cryo-electron microscopy, nuclear magnetic resonance, X-ray crystallography) to help accelerate research.

For the Hands-on Deep Learning for Computer Vision practical course at the Technical University of Munich, we implement the infamous AlphaGo algorithm in C++ to address the protein folding problem with the reinforcement learning approach. The main idea of the algorithm is training a neural network to estimate the policy and the values estimates, where the policy is improved by looking ahead into the future via Monte Carlo Tree Search guided by the value network. The environment (Rosetta 2017.39) and the Monte Carlo Tree Search algorithm were implemented in C++ 17, while the neural network was written in Python (TensorFlow 1.4.1). We rely on the TensorRT library to improve significantly the performance of the neural network inference. As a result, we could speed up the implementation 18.95 times regarding to the python version. Nevertheless, the approach is still unfeasible for large proteins (e.g. L = 332).

Results overfitting a single protein:

Smooth Return Value Loss Policy Loss

Team Members: Juan Raul Padron Griffe, Matthias Humt, Felix Opolka
Instructors: Vladimir Golkov, Daniel Cremers

Presentation

DeepMind implemented successfully this project idea in a system called AlphaFold. If you want to know more about cool projects in biomedicine, please contact Vladimir Golkov. Felix Opolka, which was the main author of this project, is currently working on cool publications about neural networks for graph-structured data.

Twitter
# Protein Folding # Reinforcement Learning