The paper, "Keypoint Matching for Instrument-Free 3D Registration in Video-based Surgical Navigation", presents a thorough analysis of the performance of classical and learning-based approaches for keypoint matching in arthroscopic images acquired in the knee joint. The study demonstrates that by employing learning-based methods in such imagery, it becomes possible, for the first time, to accomplish registration in the context of Video-Based Surgical Navigation without the aid of any instruments, i.e., in an instrument-free manner.
I'm particularly interested in exploring topics related to 3D reconstruction, keypoint matching, Structure from Motion (SfM), and Simultaneous Localization and Mapping (SLAM). These areas are directly relevant to my research, and I look forward to learning about the latest advancements in these fields.
I'm also excited to attend such a high-profile conference, where I can engage with experts from around the world, exchange ideas, and gain new insights to advance my research. Additionally, experiencing the local culture of Morocco will be an enriching aspect of the trip.