Kohta Ishikawa

Papers

Total Citations

H-Index

About

Kohta Ishikawa is a researcher whose work sits at the intersection of computer vision and robotics, with a primary focus on 3D point cloud processing. His most significant contribution is the development of CorsNet, a deep neural network designed to solve the fundamental problem of point cloud registration—the task of aligning two 3D point clouds by estimating an optimal rigid transformation. This is a critical challenge for applications ranging from autonomous navigation to 3D reconstruction. While classical methods like Iterative Closest Point (ICP) have long been the standard, they often struggle with large initial misalignments or noisy data. Ishikawa’s CorsNet, published in 2020 and now with 80 citations, offers a learning-based alternative that directly predicts alignment parameters, demonstrating superior robustness and accuracy. This work has positioned him as a contributor to the growing field of deep learning for geometric data, providing a modern solution to a classic problem. His research continues to push the boundaries of how machines perceive and interact with three-dimensional environments.