3260 papers • 126 benchmarks • 313 datasets
Image registration is the process of transforming different sets of data into one coordinate system. Data may be multiple photographs, data from different sensors, times, depths, or viewpoints. It is used in computer vision, medical imaging, and compiling and analyzing images and data from satellites. Registration is necessary in order to be able to compare or integrate the data obtained from these different measurements. Source: Image registration | Wikipedia ( Image credit: Kornia )
(Image credit: Papersgraph)
These leaderboards are used to track progress in image-registration-10
Use these libraries to find image-registration-10 models and implementations
VoxelMorph promises to speed up medical image analysis and processing pipelines while facilitating novel directions in learning-based registration and its applications and demonstrates that the unsupervised model’s accuracy is comparable to the state-of-the-art methods while operating orders of magnitude faster.
A new unsupervised learning method using convolutional neural networks under an end-to-end framework, Volume Tweening Network (VTN), for 3D medical image registration is proposed, which is 880x faster (or 3.3x faster without GPU acceleration) than traditional optimization-based methods and achieves state-of-the-art performance inmedical image registration.
This work presents recursive cascaded networks, a general architecture that enables learning deep cascades, for deformable image registration, and demonstrates that these networks achieve consistent, significant gains and outperform state-of-the-art methods.
Kornia is composed of a set of modules containing operators that can be inserted inside neural networks to train models to perform image transformations, camera calibration, epipolar geometry, and low level image processing techniques, such as filtering and edge detection that operate directly on high dimensional tensor representations.
The paper adapts the large deformation diffeomorphic metric mapping framework for image registration to the indirect setting where a template is registered against a target that is given through indirect noisy observations and proves that indirect image registration has solutions that are stable and converge as the data error tends so zero.
The proposed method uses a spatial transform layer to reconstruct one image from another while imposing smoothness constraints on the registration field, and demonstrates registration accuracy comparable to state-of-the-art 3D image registration, while operating orders of magnitude faster in practice.
TractSeg is a novel convolutional neural network‐based approach that directly segments tracts in the field of fiber orientation distribution function (fODF) peaks without using tractography, image registration or parcellation, and is demonstrated to be much faster than existing methods while providing unprecedented accuracy.
The "Autograd Image Registration Laboratory" (AIRLab), an open laboratory for image registration tasks, where the analytic gradients of the objective function are computed automatically and the device where the computations are performed, on a CPU or a GPU, is transparent.
A self-supervised algorithm for learning image registration, which can keep track of objects of interest for the duration of the trial, and can be combined with a video-prediction based controller to enable complex behaviors to be learned from scratch using only raw visual inputs.
Adding a benchmark result helps the community track progress.