Due to distortion, noise, segmentation errors, overlap, and occlusion of objects in digital images, it is usually impossible to extract complete object contours or to segment the ...
In order to store, and retrieve images from large databases, we propose a framework, based on multiple description coding paradigm, that disseminates images over distributed serve...
We present an approach to low-level vision that combines two main ideas: the use of convolutional networks as an image processing architecture and an unsupervised learning procedu...
Given the image of a real-world scene and a polygonal 3-D model of a depicted object, its apparent size, image coordinates, and 3-D orientation are autonomously detected. Based on...
Interactive visualization of complex, real-world light sources has so far not been feasible. In this paper, we present an hardware accelerated direct lighting algorithm based on a...
Xavier Granier, Michael Goesele, Wolfgang Heidrich...