Surface Registration

Surface registration aims to align 3D shapes or images, establishing point-wise correspondences between surfaces to enable quantitative comparisons and analysis. Current research emphasizes developing robust and efficient algorithms, including those based on deep learning (e.g., using convolutional neural networks, graph neural networks, and diffusion models), quasi-conformal geometry, and Gaussian process regression, to handle challenges like partial data, large deformations, and varying image modalities. These advancements are crucial for applications across diverse fields, including medical image analysis (e.g., brain mapping, cardiac motion analysis), computer vision (e.g., facial recognition, object pose estimation), and digital pathology, improving diagnostic accuracy and accelerating research.