Fast and Globally Optimal Single View Reconstruction of Curved Objects (CVPR 2012) скачать в хорошем качестве

Fast and Globally Optimal Single View Reconstruction of Curved Objects (CVPR 2012)

This video shows our interactive single-view reconstruction tool in action on several input images. Corresponding publication: Fast and Globally Optimal Single View Reconstruction of Curved Objects. (M.R. Oswald, E. Toeppe, D. Cremers) In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012. https://vision.in.tum.de/_media/spezi... Abstract: We propose a novel algorithmic solution for estimating a three-dimensional model of an object observed in a single image. Based on a minimal user input, the algorithm interactively determines the objects' silhouette and subsequently computes a silhouette-consistent 3D model which is precisely the globally minimal surface with user-specified volume. In contrast to a recently published approach to single view reconstruction, the proposed algorithm does not constrain the resolution in the depth-direction, it assures the global optimum and is faster by about an order of magnitude. Experiments demonstrate that plausible highresolution 3D models can be generated in fractions of a second and compare favorably with other methods. For more information visit: http://vision.in.tum.de