Augmented Reality
Augmented reality (AR) overlays digital information onto the real world, aiming to enhance user interaction and understanding of their environment. Current research focuses on improving the accuracy and robustness of AR systems, particularly in areas like 3D object recognition and pose estimation, often employing deep learning models (e.g., convolutional neural networks) and techniques such as simultaneous localization and mapping (SLAM) and 3D Gaussian splatting. These advancements are driving significant improvements in applications ranging from surgery and robotics to industrial automation and consumer experiences, enabling more precise and intuitive interactions with both physical and virtual worlds.
Papers
Impact of geolocation data on augmented reality usability: A comparative user test
Julien Mercier, N. Chabloz, G. Dozot, C. Audrin, O. Ertz, E. Bocher, D. Rappo
Communicating Robot's Intentions while Assisting Users via Augmented Reality
Chao Wang, Theodoros Stouraitis, Anna Belardinelli, Stephan Hasler, Michael Gienger
Encode-Store-Retrieve: Augmenting Human Memory through Language-Encoded Egocentric Perception
Junxiao Shen, John Dudley, Per Ola Kristensson
KS-APR: Keyframe Selection for Robust Absolute Pose Regression
Changkun Liu, Yukun Zhao, Tristan Braud
Robust Localization with Visual-Inertial Odometry Constraints for Markerless Mobile AR
Changkun Liu, Yukun Zhao, Tristan Braud