Generating Ambiguous Figure-Ground Images.

Ambiguous figure-ground images, mostly represented as binary images, are fascinating as they present viewers a visual phenomena of perceiving multiple interpretations from a single image. In one possible interpretation, the white region is seen as a foreground figure while the black region is treated as shapeless background. Such perception can reverse instantly at any moment. In this paper, we investigate the theory behind this ambiguous perception and present an automatic algorithm to generate such images. We model the problem as a binary image composition using two object contours and approach it through a three-stage pipeline. The algorithm first performs a partial shape matching to find a good partial contour matching between objects. This matching is based on a content-aware shape matching metric, which captures features of ambiguous figure-ground images. Then we combine matched contours into a compound contour using an adaptive contour deformation, followed by computing an optimal cropping window and image binarization for the compound contour that maximize the completeness of object contours in the final composition. We have tested our system using a wide range of input objects and generated a large number of convincing examples with or without user guidance. The efficiency of our system and quality of results are verified through an extensive experimental study.

Morphable Word Clouds for Time-Varying Text Data Visualization.

A word cloud is a visual representation of a collection of text documents that uses various font sizes, colors, and spaces to arrange and depict significant words. The majority of previous studies on time-varying word clouds focuses on layout optimization and temporal trend visualization. However, they do not fully consider the spatial shapes and temporal motions of word clouds, which are important factors for attracting people's attention and are also important cues for human visual systems in capturing information from time-varying text data. This paper presents a novel method that uses rigid body dynamics to arrange multi-temporal word-tags in a specific shape sequence under various constraints. Each word-tag is regarded as a rigid body in dynamics. With the aid of geometric, aesthetic, and temporal coherence constraints, the proposed method can generate a temporally morphable word cloud that not only arranges word-tags in their corresponding shapes but also smoothly transforms the shapes of word clouds over time, thus yielding a pleasing time-varying visualization. Using the proposed frame-by-frame and morphable word clouds, people can observe the overall story of a time-varying text data from the shape transition, and people can also observe the details from the word clouds in frames. Experimental results on various data demonstrate the feasibility and flexibility of the proposed method in morphable word cloud generation. In addition, an application that uses the proposed word clouds in a simulated exhibition demonstrates the usefulness of the proposed method.

Region-based line field design using harmonic functions.

Field design has wide applications in graphics and visualization. One of the main challenges in field design has been how to provide users with both intuitive control over the directions in the field on one hand and robust management of its topology on the other hand. In this paper, we present a design paradigm for line fields that addresses this challenge. Rather than asking users to input all singularities as in most methods that offer topology control, we let the user provide a partitioning of the domain and specify simple flow patterns within the partitions. Represented by a selected set of harmonic functions, the elementary fields within the partitions are then combined to form continuous fields with rich appearances and well-determined topology. Our method allows a user to conveniently design the flow patterns while having precise and robust control over the topological structure. Based on the method, we developed an interactive tool for designing line fields from images, and demonstrated the utility of the fields in image stylization.

Focus+context metro maps.

We introduce a focus+context method to visualize a complicated metro map of a modern city on a small displaying area. The context of our work is with regard the popularity of mobile devices. The best route to the destination, which can be obtained from the arrival time of trains, is highlighted. The stations on the route enjoy larger spaces, whereas the other stations are rendered smaller and closer to fit the whole map into a screen. To simplify the navigation and route planning for visitors, we formulate various map characteristics such as octilinear transportation lines and regular station distances into energy terms. We then solve for the optimal layout in a least squares sense. In addition, we label the names of stations that are on the route of a passenger according to human preferences, occlusions, and consistencies of label positions using the graph cuts method. Our system achieves real-time performance by being able to report instant information because of the carefully designed energy terms. We apply our method to layout a number of metro maps and show the results and timing statistics to demonstrate the feasibility of our technique.

Stylized rendering using samples of a painted image.

We introduce a novel technique to generate painterly art map (PAM) for 3D non-photorealistic rendering. Our technique can automatically transfer brush stroke textures and color changes to 3D models from samples of a painted image. Therefore, the generation of stylized images/animation in the style of a given artwork can be achieved. This new approach works particularly well for a rich variety of brush strokes ranging from simple 1D and 2D line-art strokes to very complicated ones with significant variations in stroke characteristics. During the rendering/animation process, the coherence of brush stroke textures and color changes over 3D surfaces can be well maintained. With PAM, we can also easily generate the illusion of flow animation over a 3D surface to convey the shape of a model.

Stylized and abstract painterly rendering system using a multiscale segmented sphere hierarchy.

This paper presents a novel system framework for interactive, three-dimensional, stylized, abstract painterly rendering. In this framework, the input models are first represented using 3D point sets and then this point-based representation is used to build a multiresolution bounding sphere hierarchy. From the leaf to root nodes, spheres of various sizes are rendered into multiple-size strokes on the canvas. The proposed sphere hierarchy is developed using multiscale region segmentation. This segmentation task assembles spheres with similar attribute regularities into a meaningful region hierarchy. These attributes include colors, positions, and curvatures. This hierarchy is very useful in the following respects: 1) it ensures the screen-space stroke density, 2) controls different input model abstractions, 3) maintains region structures such as the edges/boundaries at different scales, and 4) renders models interactively. By choosing suitable abstractions, brush stroke, and lighting parameters, we can interactively generate various painterly styles. We also propose a novel scheme that reduces the popping effect in animation sequences. Many different stylized images can be generated using the proposed framework.