Camera Model
Camera models are fundamental to computer vision, aiming to accurately represent how cameras capture and process light to form images. Current research focuses on improving robustness and accuracy in various applications, including depth estimation using multiple cameras and LiDAR, object detection and tracking, and mitigating adversarial attacks. These advancements are crucial for autonomous driving, robotics, surveillance, and other fields requiring reliable visual perception, driving progress in both theoretical understanding and practical deployment of vision systems.
Papers
INF: Implicit Neural Fusion for LiDAR and Camera
Shuyi Zhou, Shuxiang Xie, Ryoichi Ishikawa, Ken Sakurada, Masaki Onishi, Takeshi Oishi
End-to-End Driving via Self-Supervised Imitation Learning Using Camera and LiDAR Data
Jin Bok Park, Jinkyu Lee, Muhyun Back, Hyunmin Han, David T. Ma, Sang Min Won, Sung Soo Hwang, Il Yong Chun