2 Dimensional Detection
Two-dimensional (2D) detection, primarily focusing on image-based object identification, plays a crucial role in various applications, particularly as a foundational step for more complex 3D tasks. Current research emphasizes improving 2D detection accuracy and efficiency, often integrating it with 3D detection pipelines through techniques like query generation and fusion of 2D and 3D data using transformer networks and other deep learning architectures. This work is significant because robust 2D detection is essential for advancing fields like autonomous driving, robotics, and medical image analysis, where accurate and real-time object identification is paramount.
Papers
BOP Challenge 2023 on Detection, Segmentation and Pose Estimation of Seen and Unseen Rigid Objects
Tomas Hodan, Martin Sundermeyer, Yann Labbe, Van Nguyen Nguyen, Gu Wang, Eric Brachmann, Bertram Drost, Vincent Lepetit, Carsten Rother, Jiri Matas
Improving Real-Time Omnidirectional 3D Multi-Person Human Pose Estimation with People Matching and Unsupervised 2D-3D Lifting
Pawel Knap, Peter Hardy, Alberto Tamajo, Hwasup Lim, Hansung Kim