Research Assistant
Machine learning applied to computer vision. Modeling salience of video frames using 3D-CNN.
Machine learning applied to computer vision. Modeling salience of video frames using 3D-CNN.
Research and formation on deep learning techniques applied to computer vision, including reading groups and scientific writing.
Integrating 4 RGB-D cameras to perform SLAM in simulated forestal environments.
3D capture (NeRF) and holographic display. Brain-Computer Interfaces in VR.
Diffusion models and neural implicit representations inside game engines.
Autonomous underground drones. Deep learning for perception and reconstruction (NeRF, Deep SLAM, SFM) on the edge.
Learned semantic matching. Deep generative models and representation alignment.
Dense Visual SLAM for in-body robotics. Depth estimation and geometric SLAM combined with learned methods.
3% acceptance ratio. Online scenegraphs from RGB-D videos for robotics and scene understanding.
Representation learning and geometry grounded features for multimodal floorplan understanding.
Build scene graphs incrementally from an RGB-D data stream. Scene Understanding · RGB-D · Robotics · Rerun.
Remove outliers and densify maps of sparse endoscopy multi-map CudaSIFT-SLAM. SLAM · Depth Estimation · Surgical Robotics.
Display Instant-NGP scenes in Looking Glass holographic displays. NeRF · VR · 3D Reconstruction.
Published in UMAP '21: Adjunct Proceedings of the 29th ACM Conference, 2021
UMAP ‘21: Adjunct Proceedings of the 29th ACM Conference on User Modeling, Adaptation and Personalization.
Recommended citation: Xavier Anadón García-Arquimbau et al. (2021). "Characterizing Players of a Cube Puzzle Game with a Two-level Bag of Words." UMAP '21.
Download Paper