3 results
Search Results
Now showing 1 - 3 of 3
Item Two Examples of GPGPU Acceleration of Memory-intensive Algorithms(The Eurographics Association, 2010) Marras, Stefano; Mura, Claudio; Gobbetti, Enrico; Scateni, Riccardo; Scopigno, Roberto; Enrico Puppo and Andrea Brogni and Leila De FlorianiThe advent of GPGPU technologies has allowed for sensible speed-ups in many high-dimension, memory-intensive computational problems. In this paper we demonstrate the e ectiveness of such techniques by describing two applications of GPGPU computing to two di erent subfields of computer graphics, namely computer vision and mesh processing. In the first case, CUDA technology is employed to accelerate the computation of approximation of motion between two images, known also as optical flow. As for mesh processing, we exploit the massivelyparallel architecture of CUDA devices to accelerate the face clustering procedure that is employed in many recent mesh segmentation algorithms. In both cases, the results obtained so far are presented and thoroughly discussed, along with the expected future development of the work.Item Mutual Correspondences: An Hybrid Method for Image-to-geometry Registration(The Eurographics Association, 2010) Sottile, Michele; Dellepiane, Matteo; Cignoni, Paolo; Scopigno, Roberto; Enrico Puppo and Andrea Brogni and Leila De FlorianiImage registration is an important task in several applications of Computer Graphics and Computer Vision. Among the large number of proposed approaches, currently there is no solution which is automatic and robust enough to handle any general case. The most robust methods usually require a significant intervention by the user to specify many 2D-3D correspondences, while automatic techniques often rely on strong assumptions about the quality of 2D and 3D data. In this paper we present Mutual Correspondences, which is based on a minimization function which combines correspondences based and Mutual Information based approaches, and takes advantage of the strong points of both. Mutual Correspondences give the user the possibility to "guide" Mutual Information with only a few 2D- 3D correspondences. The proposed approach results in a wider convergence range and in higher registration accuracy, regardless of the quality of both the image and the 3D model. Mutual Correspondences were applied on some practical cases, where state-of-the-art approaches tended to fail, and they provided a mean to obtain accurate results. This led to a simple, robust and practical approach that can provide a way to register images in a few seconds.Item Improving 2D-3D Registration by Mutual Information using Gradient Maps(The Eurographics Association, 2010) Palma, Gianpaolo; Corsini, Massimiliano; Dellepiane, Matteo; Scopigno, Roberto; Enrico Puppo and Andrea Brogni and Leila De FlorianiIn this paper we propose an extension for the algorithms of image-to-geometry registration by Mutual Information( MI) to improve the performance and the quality of the alignment. Proposed for the registration of multi modal medical images, in the last years MI has been adapted to align a 3D model to a given image by using different renderings of the model and a gray-scale version of the input image. A key aspect is the choice of the rendering process to correlate the 3D model to the image without taking into account the texture data and the lighting conditions. Even if several rendering types for the 3D model have been analyzed, in some cases the alignment fails for two main reasons: the peculiar reflection behavior of the object that we are not able to reproduce in the rendering of the 3D model without knowing the material characteristics of the object and the lighting conditions of the acquisition environment; the characteristics of the image background, especially non uniform background, that can degrade the convergence of the registration. To improve the quality of the registration in these cases we propose to compute the MI between the gradient map of the 3D rendering and the gradient map of the image in order to maximize the shared data between them.