Using generic interpolation machinery based on solving Poisson equations, a variety of novel tools are introduced for seamless editing of image regions. The first set of tools permits the seamless importation of both opaque and transparent source image regions into a destination region. The second set is based on similar mathematical ideas and allows the user to modify the appearance of the image seamlessly, within a selected region. These changes can be arranged to affect the texture, the illumination, and the color of objects lying in the region, or to make tileable a rectangular selection.

This paper presents a strategy for rapid summarisation and browsing of video sequences. The input video is first transformed into a sequence of representative feature vectors. Using this representation a utility function is designed that assigns high reward to subsequences of keyframes that are maximally distinct and individually carry the most information. For a specified level of detail and endpoints the keyframe sequence that maximises this utility function can be obtained by a non-iterative Dynamic Programming procedure, thus allowing the user to efficiently zoom in on any part or all of the video sequence. For the sake of compactness and clarity the working of the algorithm is illustrated on a television commercial. 1

The problem of extracting continuous structures from noisy or cluttered images is a difficult one. Successful extraction depends critically on the ability to balance prior constraints on continuity and smoothness against evidence garnered from image analysis. Exact, deterministic optimisation algorithms, based on discretized functionals, suffer from severe limitations on the form of prior constraint that can be imposed tractably. This paper proposes a sequential Monte-Carlo technique, termed JetStream, that enables constraints on curvature, corners, and contour parallelism. To be mobilized, all of which are infeasible under exact optimization. The power of JetStream is demonstrated in two contexts: (1) interactive cut-out in photo-editing applications, and (2) the recovery of roads in aerial photographs.

Compared to traditional media, computer illustration software offers superior editing power at the cost of reduced freedom in the picture construction process. To reduce this discrepancy, we propose an extension to the classical paradigm of 2D layered drawing, the map paradigm, that is conducive to a more natural drawing technique. We present the key concepts on which the new paradigm is based: a) graphical objects, called planar maps, that describe shapes with multiple colors and contours; b) a drawing technique, called map sketching, that allows the iterative construction of arbitrarily complex objects. We also discuss user interface design issues in map based illustration software.

A planar map is a figure formed by a set of intersecting lines and curves. Such an object captures both the geometrical and the topological information implicitly defined by the data. In the context of 2D drawing it provides a new interaction paradigm, map sketching, for editing graphic shapes.To build a planar map, one must compute curve intersections and deduce from them the map they define. The computed topology must be consistent with the underlying geometry. Robustness of geometric computations is a key issue in this process. We present a robust solution to Bézier curve intersection that uses exact forward differencing and bounded rational arithmetic. Then, we describe data structure and algorithms to support incremental insertion of Bézier curves in a planar map. A prototype illustration tool using this method is also discussed.

In this paper we present the first version of a new algorithm for hidden-surface and hidden-line elimination which applies primarily to the generation of indoor perspective views of simple building models. The algorithm is very efficient and though being an object space algorithm its run-time depends only on the complexity of the generated picture. The algorithm is recursive and uses extensively the coherence given by the adjacencies of the rooms within a building. Extensions to more complex models are considered.