Pose-Based Retrieval Web Tool

Official implementation of 'MCDS-VSS: Moving Camera Dynamic Scene Video Semantic Segmentation by Filtering with Self-Supervised Geometry and Motion' BMVC. 2024

Code to reproduce our NimbRoNet3 results for real-time preception on the soccer field

Simple template for quick prototyping and standardization of deep learning projects

Helpers for loading, perprocessing and visualizing the SynpickVP dataset for video-based prediciton tasks

Offical implementation of "Enhancing Human Pose Estimation in Ancient Vase Paintings via Perceptually-Grounded Style Transfer Learning" by Mahdu, Villar-Corrales, et al.

Official implementation of "Video Prediction at Multiple Spatio-Temporal Scales with Hierarchical Recurrent Networks." by Villar-Corrales et al.

Official implementation of "Deep learning architectural designs for super-resolution of noisy images" by Villar et al. ICASSP 2021

Prject for the HackZurich 2020 Hacktohn

Tutorial on Autoencoders. The notebooks and code here contained explain how autoencoders work and illustrate some of their common applications

Unsupervised Learning and Pattern Analysis algortithms from the PA course offered by the Computer Science department at FAU.

This project uses image processing techniques to perform face detection and deep learning in order to replace the faces by an emoji similar to the detected facial expression.

This project uses regular image processing techniques in order to emulate the invisble cloak from the movie Harry Potter and the Philosopher's Stone