A Dissertation on Deep Generative Models for Domain Translation [Spanish]
An overview of deep generative model families for cross-modal generation, particularly between textual, audio, and still image or video.
Personal artworks and experiments where technology, perception and creative practice meet. This site is an expression of my curiosity about learning new things and experiencing arts to keep myself emotionally aware. More creative work is available at valillon.art.
Happy reading!
An overview of deep generative model families for cross-modal generation, particularly between textual, audio, and still image or video.
The search for imaginary faces by softening deep learning face recognition.
An essay about writing systems throughout history and their shared visual features detected with neural networks exclusively trained with the Latin alphabet.
About deep learning enabling to reconstruct depth of paintings
Some examples of facial expression transference between two faces with Dlib and OpenCV to automatically create facial caricatures.