We present Easy Mesh Cutting, an intuitive and easy-to-use mesh cutout tool. Users can cut meaningful components from meshes by simply drawing freehand sketches on the mesh. Our system provides instant visual feedback to obtain the cutting results based on an improved region growing algorithm using a feature sensitive metric. The cutting boundary can be automatically optimized or easily edited by users. Extensive experimentation shows that our approach produces good cutting results while requiring little skill or effort from the user and provides a good user experience. Based on the easy mesh cutting framework, we introduce two applications including sketch-based mesh editing and mesh merging for geometry processing. Categories and Subject Descriptors (according to ACM CCS): I.3.5 [Computer Graphics]: Geometric algorithms, languages, and systems 1.

In this paper we propose an iterative graph cuts based active contours approach to segment an object boundary out of background. Given an initial boundary nearby the object, the graph cuts based active contour can iteratively deform to the object boundary even if there are large discontinuities and noise. In each iteration, the area of interest is a certain neighborhood of the previously estimated boundary. The problem is formulated as a multi-source multisink s − t minimum cut problem in that neighborhood and solved using node identification. The result of each step is globally optimal within the area of interest. On one hand, this area of interest enables the active contour to break away from the constraints of previously estimated boundary and isolated noise points in the image. On the other hand, our method generates multiple sources such that the result boundary should be long enough and hence overcomes the well-known shortcoming of the cost function of min-cut. It is shown that the proposed approach will converge to a final boundary. If this final boundary is not satisfactory, our approach is inherently suitable for interactive correction. As an advantage of using graph cuts, the proposed approach can be easily and seamlessly used to segment two dimensional(2D), three dimensional(3D) and possibly higher dimensional objects.

New Models and Methods for Matting and Compositing by Yung-Yu Chuang Co-Chairs of Supervisory Committee: Professor Brian Curless Computer Science & Engineering Professor David H. Salesin Computer Science & Engineering Matting and compositing are fundamental operations in graphics and visual effects. Despite having enjoyed wide usage for many years, traditional matting and compositing have limitations. Traditional matting methods either require special setups or cannot handle objects with complex silhouettes. Furthermore, the traditional compositing model is effective in modeling color blending effects but not reflection, refraction, and shadows. In this dissertation, we address these limitations and present a set of new compositing models and matting methods. To pull mattes of complex silhouettes from natural images, we introduce a principled statistical approach called Bayesian image matting. We also extend this algorithm to handle video sequences with the help of optical flow computation and background estimation. On the compositing side, previous work on environment matting has been shown to handle refraction and reflection, but the resulting mattes are not very accurate. We propose a more accurate environment matting model and method that requires using more images. For shadows, we develop a physically-motivated shadow compositing equation. Based on this equation, we introduce a shadow matting method for extracting shadow mattes from videos with natural backgrounds, and we demonstrate a novel process for acquiring the photometric and geometric properties of the background to enable creation of realistic shadow composites. Finally, we present a novel application of Bayesian image matting for animating still pictures.

In this paper, we explore the problem of deleting objects in still pictures. We present an interactive system based on an intuitive user-friendly interface for removing undesirable objects in digital pictures. To erase an object in an image, a user indicates which object is to be removed by simply pinpointing it with the mouse cursor. As the mouse cursor rolls over the image, the current implicit selected object’s border is highlighted, providing a visual feedback. In case where the computer-segmented area does not match the users ’ perception of the object, users can further provide a few inside/outside object cues by clicking on a small number of object or nonobject pixels. A small number of such cues is generally enough to reach a correct matching, even for complex textured images. Afterwards, the user removes the object by clicking the left mouse button, and a hole-filling technique is initiated to generate a seamless background portion. Our image manipulation system consists of two components: (i) fully automatic or partially user-steered image segmentation based on an improved fast statistical regiongrowing segmentation, and (ii) texture synthesis or image inpainting of irregular shaped hole regions. Experiments on a variety of photographs display the ability of the system to handle complex scenes with highly textured objects.

We present an algorithm for computing a representation of image structure, or image segmentation, and use it for selecting objects in the image with freehand sketches drawn by the user over the image. The sketches are mapped onto image segments whose union forms the intended object. The mapping operation is performed with the aid of a simplicial decomposition of the image segmentation- a triangulation formed with vertices chosen to lie along the medial axes of the segments. Each edge of a triangle lies entirely inside the two segments that contains its vertices. This decomposition captures the adjacency information about the segments as well as the shape of the segment boundaries. Any object boundary is completely contained in a set of triangles. The triangles are also used to formulate the problem of estimating gradual photometric transition across an object boundary, called alpha channel estimation, as a set of local, intratriangle alpha channel estimation problems

this paper we propose the use of a construct we call faceted models to represent an appearance set. The key distinguishing feature of faceted appearance models from existing representations is that the adjacency information in the sample set is explicitly encoded, and used to enforce a topological constraint that improves representational accuracy without incurring excessive costs in terms of computation time and storage space

This paper proposes a new framework for video editing in gradient domain. The spatio-temporal gradient fields of target videos are modified and/or mixed to generate a new gradient field which is usually not integrable. We compare two methods to solve this "mixed gradient problem", i.e. the variational method and loopy belief propagation. We propose a 3D video integration algorithm, which uses the variational method to find the potential function whose gradient field is closest to the mixed gradient field in the sense of least squares. The video is reconstructed by solving a 3D Poisson equation. The main contributions of our framework lie in three aspects: firstly, we derive a straightforward extension of current 2D gradient technique to 3D space, thus resulting in a novel video editing framework, which is very different from all current video editing software; secondly, we propose using a fast and accurate 3D discrete Poisson solver which uses diagonal multigrids to solve the 3D Poisson equation, which is up to twice as fast as a simple conventional multigrid algorithm; finally, we introduce a set of new applications, such as face replacement and painting, high dynamic range video compression and graphcut based video compositing.