We present a semantics-driven approach for stroke-based painterly rendering, based on recent image parsing techniques [Tu et al. 2005; Tu and Zhu 2006] in computer vision. Image parsing integrates segmentation for regions, sketching for curves, and recognition for object categories. In an interactive manner, we decompose an input image into a hierarchy of its constituent components in a parse tree representation with occlusion relations among the nodes in the tree. To paint the image, we build a brush dictionary containing a large set (760) of brush examples of four shape/appearance categories, which are collected from professional artists, then we select appropriate brushes from the dictionary and place them on the canvas guided by the image semantics included in the parse tree, with each image component and layer painted in various styles. During this process, the scene and object categories also determine the color blending and shading strategies for inhomogeneous synthesis of image details. Compared with previous methods, this approach benefits from richer meaningful image semantic information, which leads to better simulation of painting techniques of artists using the high-quality brush dictionary. We have tested our approach on a large number (hundreds) of images and it produced satisfactory painterly effects.

Abstract. This paper addresses a new problem, that of multiscale activity recognition. Our goal is to detect and localize a wide range of activities, including individual actions and group activities, which may simultaneously co-occur in highresolution video. The video resolution allows for digital zoom-in (or zoom-out) for examining fine details (or coarser scales), as needed for recognition. The key challenge is how to avoid running a multitude of detectors at all spatiotemporal scales, and yet arrive at a holistically consistent video interpretation. To this end, we use a three-layered AND-OR graph to jointly model group activities, individual actions, and participating objects. The AND-OR graph allows a principled formulation of efficient, cost-sensitive inference via an explore-exploit strategy. Our inference optimally schedules the following computational processes: 1) direct application of activity detectors -called α process; 2) bottom-up inference based on detecting activity parts -called β process; and 3) top-down inference based on detecting activity context -called γ process. The scheduling iteratively maximizes the log-posteriors of the resulting parse graphs. For evaluation, we have compiled and benchmarked a new dataset of high-resolution videos of group and individual activities co-occurring in a courtyard of the UCLA campus.

We present an interactive abstract painting system named Sisley. Sisley works upon the psychological principle [Berlyne 1971] that abstract arts are often characterized by their greater perceptual ambiguities than photographs, which tend to invoke moderate mental efforts of the audience for interpretation, accompanied with subtle aesthetic pleasures. Given an input photograph, Sisley decomposes it into a hierarchy/tree of its constituent image components (e.g., regions, objects of different categories) with interactive guidance from the user, then automatically generates corresponding abstract painting images, with increased ambiguities of both the scene and individual objects at desired levels. Sisley consists of three major working parts: (1) an interactive image parser executing the tasks of segmentation, labeling, and hierarchical organization, (2) a painterly rendering engine with abstract operators for transferring the image appearance, and (3) a numerical ambiguity computation and control module of servomechanism. With the help of Sisley, even an amateur user can create abstract paintings from photographs easily in minutes. We have evaluated the rendering results of Sisley using human experiments, and verified that they have similar abstract effects to original abstract paintings by artists.

a) (b) (c) Figure 1: Three portrait paintings rendered with different templates using our method. Their corresponding source photograph is in Fig.5. Notice: all painting images in this paper are best viewed on a color display at 400% zoom unless annotated otherwise. AbstractPortraiture plays a substantial role in traditional painting, yet it has not been studied in depth in painterly rendering research. The difficulty in rendering human portraits is due to our acute visual perception to the structure of human face. To achieve satisfactory results, a portrait rendering algorithm should account for facial structure.In this paper, we present an example-based method to render portrait paintings from photographs, by transferring brush strokes from previously painted portrait templates by artists. These strokes carry rich information about not only the facial structure but also how artists depict the structure with large and decisive brush strokes and vibrant colors. With a dictionary of portrait painting templates for different types of faces, we show that this method can produce satisfactory results.