In this paper, we present and investigate an approach to fast multilabel color image segmentation using convex optimization techniques. The presented model is in some ways related to the well-known Mumford-Shah model, but deviates in certain important aspects. The optimization problem has been designed with two goals in mind. The objective function should represent fundamental concepts of image segmentation, such as incorporation of weighted curve length and variation of intensity in the segmented regions, while allowing transformation into a convex concave saddle point problem that is computationally inexpensive to solve. This paper introduces such a model, the nontrivial transformation of this model into a convex-concave saddle point problem, and the numerical treatment of the problem. We evaluate our approach by applying our algorithm to various images and show that our results are competitive in terms of quality at unprecedentedly low computation times. Our algorithm allows high-quality segmentation of megapixel images in a few seconds and achieves interactive performance for low resolution images.

Display resolution is frequently exceeded by available image resolution. Recently, apparent display resolution enhancement (ADRE) techniques show how characteristics of the human visual system can be exploited to provide super-resolution on high refresh rate displays. In this paper, we address the problem of generalizing the ADRE technique to conventional videos of arbitrary content. We propose an optimization-based approach to continuously translate the video frames in such a way that the added motion enables apparent resolution enhancement for the salient image region. The optimization considers the optimal velocity, smoothness, and similarity to compute an appropriate trajectory. In addition, we provide an intuitive user interface that allows to guide the algorithm interactively and preserves important compositions within the video. We present a user study evaluating apparent rendering quality and show versatility of our method on a variety of general test scenes.

High quality dense image correspondence estimation between two images is an essential pre-requisite for view interpolation in visual media production. Due to the ill-posed nature of the problem, automated estimation approaches are prone to erroneous correspondences and subsequent quality degradation, e.g. in the presence of ambiguous movements that require human scene understanding to resolve. Where visually convincing results are essential, artifacts resulting from estimation errors must be repaired by hand with image editing tools. In this paper, we propose a new workflow alternative by fixing the correspondences instead of fixing the interpolated images. We combine realtime interactive correspondence display, multi-level user guidance and algorithmic subpixel precision to counteract failure cases of automated estimation algorithms. Our results show that already few interactions improve the visual quality considerably.

Currently no standardised gesture annotation systems are available. As a contribution towards solving this problem, CoGesT, a machine processable and human usable computational model for the annotation of a subset of conversational gestures is presented, its empirical and formal properties are detailed, and application areas are discussed. 1. A gesture representation strategy There is as yet no standard generic transcription scheme for gestures, and researchers in the field tend to develop their own systems, based on rather specific research and development goals. Various classification schemes have been proposed (cf. [1, 2, 3, 4, 5, 6]), but none of these is particularly suitable for generalisation into a standard. We provide an initial solution to this problem by selecting a subset of gestures as a starting point,

The extraction of lexical information for machine readable lexica from multilevel annotations is addressed in this paper. Relations between these levels of annotation are used for subclassification of lexical entries. A method for relating annotation units is presented, based on a temporal calculus. Relating the annotation units manually is errorprone, time consuming and tends to be inconsistent, and a method is presented for automatically accomplishing this task, and evaluated using German, Japanese and Anyi (W. Africa) corpora.