Unsupervised Difference Learning for Noisy Rigid Image Alignment
This addresses a domain-specific challenge in computer vision for applications like cryo-EM imaging, where noise sensitivity is a bottleneck, though it appears incremental as it builds on spatial transformer networks.
The paper tackles the problem of rigid image alignment in noisy conditions by introducing an unsupervised difference learning (UDL) strategy, which converts the unsupervised task into a pseudo-supervised one, achieving accurate rotation estimation on both clean and noisy images.
Rigid image alignment is a fundamental task in computer vision, while the traditional algorithms are either too sensitive to noise or time-consuming. Recent unsupervised image alignment methods developed based on spatial transformer networks show an improved performance on clean images but will not achieve satisfactory performance on noisy images due to its heavy reliance on pixel value comparations. To handle such challenging applications, we report a new unsupervised difference learning (UDL) strategy and apply it to rigid image alignment. UDL exploits the quantitative properties of regression tasks and converts the original unsupervised problem to pseudo supervised problem. Under the new UDL-based image alignment pipeline, rotation can be accurately estimated on both clean and noisy images and translations can then be easily solved. Experimental results on both nature and cryo-EM images demonstrate the efficacy of our UDL-based unsupervised rigid image alignment method.