This paper presents an automatic subpixel registration algorithm that minimizes the mean square intensity difference between a reference and a test data set, which can be either images (two-dimensional) or volumes (three-dimensional). The algorithm uses an explicit spline representation of the images in conjunction with spline processing and is based on a coarse-to-fine iterative strategy (pyramid approach). The minimization is performed according to a new variation (ML*) of the Marquardt–Levenberg algorithm for nonlinear least-square optimization. The geometric deformation model is a global three-dimensional (3-D) affine transformation that can be optionally restricted to rigid-body motion (rotation and translation), combined with isometric scaling. It also includes an optional adjustment of image contrast differences. The algorithm is entirely automatic, pixel-based, and does not require landmarks. It has been successfully applied to the registration of intramodal PET and fMRI data. The multiresolution refinement strategy is more robust than a comparable single-stage method, being less likely to be trapped into a false local optimum. The improved version of the Marquardt–Levenberg algorithm is faster. The algorithm uses cubic splines for interpolation, which are well-suited for computing image pyramids and performing geometric transformations at various resolutions. The algorithm is based on a multiresolution pyramid approach, which allows for efficient and accurate registration by starting with a coarse approximation and refining it iteratively. The algorithm is robust and efficient, and has been successfully applied to a variety of biomedical images, including PET, MRI, and fMRI data. The algorithm is based on a least-squares criterion and uses a multiresolution approach to improve robustness and speed. The algorithm is based on a combination of affine transformations and contrast changes, and has been shown to be effective in registration tasks. The algorithm is based on a combination of affine transformations and contrast changes, and has been shown to be effective in registration tasks. The algorithm is based on a combination of affine transformations and contrast changes, and has been shown to be effective in registration tasks.This paper presents an automatic subpixel registration algorithm that minimizes the mean square intensity difference between a reference and a test data set, which can be either images (two-dimensional) or volumes (three-dimensional). The algorithm uses an explicit spline representation of the images in conjunction with spline processing and is based on a coarse-to-fine iterative strategy (pyramid approach). The minimization is performed according to a new variation (ML*) of the Marquardt–Levenberg algorithm for nonlinear least-square optimization. The geometric deformation model is a global three-dimensional (3-D) affine transformation that can be optionally restricted to rigid-body motion (rotation and translation), combined with isometric scaling. It also includes an optional adjustment of image contrast differences. The algorithm is entirely automatic, pixel-based, and does not require landmarks. It has been successfully applied to the registration of intramodal PET and fMRI data. The multiresolution refinement strategy is more robust than a comparable single-stage method, being less likely to be trapped into a false local optimum. The improved version of the Marquardt–Levenberg algorithm is faster. The algorithm uses cubic splines for interpolation, which are well-suited for computing image pyramids and performing geometric transformations at various resolutions. The algorithm is based on a multiresolution pyramid approach, which allows for efficient and accurate registration by starting with a coarse approximation and refining it iteratively. The algorithm is robust and efficient, and has been successfully applied to a variety of biomedical images, including PET, MRI, and fMRI data. The algorithm is based on a least-squares criterion and uses a multiresolution approach to improve robustness and speed. The algorithm is based on a combination of affine transformations and contrast changes, and has been shown to be effective in registration tasks. The algorithm is based on a combination of affine transformations and contrast changes, and has been shown to be effective in registration tasks. The algorithm is based on a combination of affine transformations and contrast changes, and has been shown to be effective in registration tasks.