Yusuke Sekikawa

Papers

Total Citations

H-Index

About

Yusuke Sekikawa is a leading researcher in computer vision and robotics, with a primary focus on 3D point cloud registration and motion tracking. His most impactful work, "CorsNet: 3D Point Cloud Registration by Deep Neural Network" (2020, 80 citations), addresses a fundamental challenge in robotics and autonomous systems: aligning 3D point clouds with high accuracy. Sekikawa’s deep learning approach overcomes limitations of classical methods like Iterative Closest Point (ICP), which often fails under noisy or partial data. By introducing a neural network that learns robust transformations, his work has significantly advanced object recognition, SLAM, and scene reconstruction—critical for self-driving cars and robotic manipulation. More recently, Sekikawa has pioneered novel frameworks for motion tracking using event-based cameras, as seen in his 2022 work "Neural Implicit Event Generator for Motion Tracking." This innovative approach leverages implicit neural representations to generate event data and track motion in real-time, offering advantages in high-speed and low-light scenarios. His contributions blend classical geometry with modern deep learning, earning him recognition as a key innovator in 3D vision and sensor fusion.