Learn More
Markov random fields (MRFs) are popular and generic probabilistic models of prior knowledge in low-level vision. Yet their generative properties are rarely examined, while application-specific models and non-probabilistic learning are gaining increased attention. In this paper we revisit the generative aspects of MRFs, and analyze the quality of common(More)
Many state-of-the-art image restoration approaches do not scale well to larger images, such as megapixel images common in the consumer segment. Computationally expensive optimization is often the culprit. While efficient alternatives exist, they have not reached the same level of image quality. The goal of this paper is to develop an effective approach to(More)
Identifying suitable image features is a central challenge in computer vision, ranging from representations for low-level to high-level vision. Due to the difficulty of this task, techniques for learning features directly from example data have recently gained attention. Despite significant benefits, these learned features often have many fewer of the(More)
Conventional non-blind image deblurring algorithms involve natural image priors and maximum a-posteriori (MAP) estimation. As a consequence of MAP estimation, separate pre-processing steps such as noise estimation and training of the regularization parameter are necessary to avoid user interaction. Moreover, MAP estimates involving standard natural image(More)
The beneficial effects of bone marrow-derived mesenchymal stromal cell (MSC) administration following experimental stroke have already been described. Despite several promising characteristics, placenta-derived MSC have not been used in models of focal ischemia. The aim of the current study is to investigate the impact of intravenously transplanted(More)
Non-blind deblurring is an integral component of blind approaches for removing image blur due to camera shake. Even though learning-based deblurring methods exist, they have been limited to the generative case and are computationally expensive. To this date, manually-defined models are thus most widely used, though limiting the attained restoration quality.(More)
Conditional random fields (CRFs) are popular discriminative models for computer vision and have been successfully applied in the domain of image restoration, especially to image denoising. For image deblurring, however, discriminative approaches have been mostly lacking. We posit two reasons for this: First, the blur kernel is often only known at test time,(More)
Motivated by aiding human operators in the detection of dangerous objects in passenger luggage, such as in airports, we develop an automatic object detection approach for multi-view X-ray image data. We make three main contributions: First, we systematically analyze the appearance variations of objects in X-ray images from inspection systems. We then(More)
1 PRO3ECT OVERVIEW The compiler system described in this paper may be regarded as a specialization of the classical UNCOL-problem [Con58]. It has been developed at the University of Kiel and is currently being used by Norsk-Data-Oietz Computer Systems, M0I-helm, FRG. The system results from the need to lower maintenance costs and to achieve a high degree of(More)