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
Automatic Registration of Images with Inconsistent Content Through Line-Support Region Segmentation and Geometrical Outlier Removal
Ming Zhao, Yongpeng Wu, Shengda Pan, Fan Zhou, Bowen An, André Kaup
RFVTM: A Recovery and Filtering Vertex Trichotomy Matching for Remote Sensing Image Registration
Ming Zhao, Bowen An, Yongpeng Wu, Huynh Van Luong, André Kaup
MICDIR: Multi-scale Inverse-consistent Deformable Image Registration using UNetMSS with Self-Constructing Graph Latent
Soumick Chatterjee, Himanshi Bajaj, Istiyak H. Siddiquee, Nandish Bandi Subbarayappa, Steve Simon, Suraj Bangalore Shashidhar, Oliver Speck, Andreas Nürnberge
Region Specific Optimization (RSO)-based Deep Interactive Registration
Ti Bai, Muhan Lin, Xiao Liang, Biling Wang, Michael Dohopolski, Bin Cai, Dan Nguyen, Steve Jiang