Xavier Fresquet is a Technical Artist with over a decade of 3D art experience and seven years focused on production-ready visuals for games and simulation platforms. He has led art teams at the Computer Vision Center to deliver assets and automated workflows tailored to self-driving research and contributed technical visual improvements to the widely used CARLA autonomous driving simulator. Comfortable across Unreal and Unity pipelines, he blends hands-on modeling, Substance texturing, and post-processing tweaks with cross-disciplinary collaboration to meet platform-specific constraints. Based in Catalonia, he now applies that mix of creative craft and technical problem-solving to simulations and interactive projects, often optimizing render and semantic segmentation workflows that improve both image fidelity and ML utility.
7 years of coding experience
Master, Realización y Producción 3Dstudio max, Master, Realización y Producción 3Dstudio max at Escuela animación 9zeros BCN
ENVIRONMENT ARTS PROGRAM, Intro to Substance for Environment Art, ENVIRONMENT ARTS PROGRAM, Intro to Substance for Environment Art at CGMA | Computer Graphics Master Academy
Grado Superior en Diseño y Produccion Editorial, Artes Graficas, Grado Superior en Diseño y Produccion Editorial, Artes Graficas at Salesians de Sarrià
Intensive Course - Zbrush and Substance, Intensive Course - Zbrush and Substance at ENTI School of New Interactive Technologies
Master's degree, Master's degree at Universitat Pompeu Fabra
Postgraduate in Zbrush and Digital Sculping, Postgraduate in Zbrush and Digital Sculping at SEEWAY School of Design, Animation, Digital Communication and Photography
Open-source simulator for autonomous driving research.
Role in this project:
ML Engineer
Contributions:10 reviews, 22 commits, 11 PRs in 4 years 4 months
Contributions summary:Xavier primarily contributed to the enhancement and refinement of the CARLA simulator's visual features, focusing on improving the quality of the rendered images. They made several changes to the SceneCaptureSensor.cpp file, adjusting post-processing effects such as bloom, ambient occlusion, and exposure to optimize the visual output. Additionally, they made changes related to semantic segmentation to improve the accuracy of object recognition within the simulation environment.
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.