I am a PhD student in Computer Vision at the Institute of Robotics and Industrial Informatics (IRI, CSIC–UPC) in Barcelona, advised by Antonio Agudo. My research is on 3D scene understanding — turning multi-view imagery into faithful, editable 3D: reconstructing scenes, segmenting them, and decomposing them into clean, manipulable objects. I work with mesh- and splatting-based representations, multi-view segmentation, and generative models for 3D content, with the broader goal of bridging 2D perception and 3D structure.

Before starting the PhD I was an AI Engineer at Indra, where I built autonomous systems for European air-traffic-control operations and led a 3D simulation and rendering pipeline that generated realistic synthetic data for training computer-vision detection models. Earlier, as a research assistant in UPF’s Interactive Technologies Group (GTI), I contributed to SignOn — a European project on digital communication for deaf and hard-of-hearing people — taught the undergraduate Computer Graphics course, and developed a generative-AI framework for 3D asset creation as my Master’s thesis.

I hold an MSc in Intelligent Interactive Systems and a BSc in Computer Science, both from Universitat Pompeu Fabra. I’m always happy to discuss research, 3D vision and graphics, or potential collaborations.