Most Likely Separation of Intensity and Warping Effects in Image Registration
This addresses the issue of estimation bias in image registration for applications like facial and brain MRI analysis, but it is incremental as it builds on existing mixed-effects frameworks.
The paper tackles the problem of jointly modeling intensity and warping variations in image registration by introducing a mixed-effects model that avoids bias from preprocessing steps, resulting in simultaneous estimation of template and model parameters through likelihood optimization.
This paper introduces a class of mixed-effects models for joint modeling of spatially correlated intensity variation and warping variation in 2D images. Spatially correlated intensity variation and warp variation are modeled as random effects, resulting in a nonlinear mixed-effects model that enables simultaneous estimation of template and model parameters by optimization of the likelihood function. We propose an algorithm for fitting the model which alternates estimation of variance parameters and image registration. This approach avoids the potential estimation bias in the template estimate that arises when treating registration as a preprocessing step. We apply the model to datasets of facial images and 2D brain magnetic resonance images to illustrate the simultaneous estimation and prediction of intensity and warp effects.