Image Registration
Image registration aims to precisely align images from different sources or time points, a crucial preprocessing step for many medical and remote sensing applications. Current research emphasizes developing faster, more accurate, and robust registration methods, focusing on deep learning architectures like transformers and diffusion models, as well as incorporating probabilistic uncertainty quantification and techniques to handle multimodal data and complex deformations. These advancements are improving the accuracy and efficiency of various downstream tasks, including medical image analysis, surgical planning, and geospatial data integration.
Papers
Mutual information neural estimation for unsupervised multi-modal registration of brain images
Gerard Snaauw, Michele Sasdelli, Gabriel Maicas, Stephan Lau, Johan Verjans, Mark Jenkinson, Gustavo Carneiro
Self-Supervised Point Cloud Registration with Deep Versatile Descriptors
Dongrui Liu, Chuanchuan Chen, Changqing Xu, Robert Qiu, Lei Chu