Master Thesis — Multimodal Floorplan Encoding
Representation learning and geometry grounded features for multimodal floorplan understanding.
Experience
RobotX Summer Fellowship
3% acceptance ratio. Online scenegraphs from RGB-D videos for robotics and scene understanding.
AI/CV Researcher
Dense Visual SLAM for in-body robotics. Depth estimation and geometric SLAM combined with learned methods.
AI/CV Engineer
Learned semantic matching. Deep generative models and representation alignment.
AI/CV Engineer
Autonomous underground drones. Deep learning for perception and reconstruction (NeRF, Deep SLAM, SFM) on the edge.
Independent Consultant
Diffusion models and neural implicit representations inside game engines.
Study and Research Program
Research and formation on deep learning techniques applied to computer vision, including reading groups and scientific writing.
VR Intern
3D capture (NeRF) and holographic display. Brain-Computer Interfaces in VR.
Robotics Apprenticeship
Integrating 4 RGB-D cameras to perform SLAM in simulated forestal environments.
Research Assistant
Machine learning applied to computer vision. Modeling salience of video frames using 3D-CNN.