Showing papers by "Jian Sun published in 2007"

Learning to Detect A Salient Object

Abstract: We study visual attention by detecting a salient object in an input image. We formulate salient object detection as an image segmentation problem, where we separate the salient object from the image background. We propose a set of novel features including multi-scale contrast, center-surround histogram, and color spatial distribution to describe a salient object locally, regionally, and globally. A conditional random field is learned to effectively combine these features for salient object detection. We also constructed a large image database containing tens of thousands of carefully labeled images by multiple users. To our knowledge, it is the first large image database for quantitative evaluation of visual attention algorithms. We validate our approach on this image database, which is public available with this paper.

Image deblurring with blurred/noisy image pairs

Abstract: Taking satisfactory photos under dim lighting conditions using a hand-held camera is challenging. If the camera is set to a long exposure time, the image is blurred due to camera shake. On the other hand, the image is dark and noisy if it is taken with a short exposure time but with a high camera gain. By combining information extracted from both blurred and noisy images, however, we show in this paper how to produce a high quality image that cannot be obtained by simply denoising the noisy image, or deblurring the blurred image alone. Our approach is image deblurring with the help of the noisy image. First, both images are used to estimate an accurate blur kernel, which otherwise is difficult to obtain from a single blurred image. Second, and again using both images, a residual deconvolution is proposed to significantly reduce ringing artifacts inherent to image deconvolution. Third, the remaining ringing artifacts in smooth image regions are further suppressed by a gain-controlled deconvolution process. We demonstrate the effectiveness of our approach using a number of indoor and outdoor images taken by off-the-shelf hand-held cameras in poor lighting environments.

Image vectorization using optimized gradient meshes

Abstract: Recently, gradient meshes have been introduced as a powerful vector graphics representation to draw multicolored mesh objects with smooth transitions. Using tools from Abode Illustrator and Corel CorelDraw, a user can manually create gradient meshes even for photo-realistic vector arts, which can be further edited, stylized and animated. In this paper, we present an easy-to-use interactive tool, called optimized gradient mesh, to semi-automatically and quickly create gradient meshes from a raster image. We obtain the optimized gradient mesh by formulating an energy minimization problem. The user can also interactively specify a few vector lines to guide the mesh generation. The resulting optimized gradient mesh is an editable and scalable mesh that otherwise would have taken many hours for a user to manually create.

Flash Cut: Foreground Extraction with Flash and No-flash Image Pairs

Abstract: In this paper, we propose a novel approach for foreground layer extraction using flash/no-flash image pairs, which we call flash cut. Flash cut is based on the simple observation that only the foreground is significantly brightened by the flash and the background appearance change is very small, if the background is distant. Changes due to flash, motion, and color information are fused in an MRF framework to produce high quality segmentation results. Flash cut handles some amount of camera shake, and foreground motion, which makes it practical for anyone with a flash-equipped camera to use. We validate our approach on a variety of indoor and outdoor examples.

Salient Object Detection

Abstract: Methods for detecting a salient object in an input image are described. For this, the salient object in an image may be defined using a set of local, regional, and global features including multi-scale contrast, center-surround histogram, and color spatial distribution. These features are optimally combined through conditional random field learning. The learned conditional random field is then used to locate the salient object in the image. The methods can also use image segmentation, where the salient object is separated from the image background.

Blurred/Non-Blurred Image Alignment using Sparseness Prior

Abstract: Aligning a pair of blurred and non-blurred images is a prerequisite for many image and video restoration and graphics applications. The traditional alignment methods such as direct and feature-based approaches cannot be used due to the presence of motion blur in one image of the pair. In this paper, we present an effective and accurate alignment approach for a blurred/non-blurred image pair. We exploit a statistical characteristic of the real blur kernel - the marginal distribution of kernel value is sparse. Using this sparseness prior, we can search the best alignment which produces the sparsest blur kernel. The search is carried out in scale space with a coarse-to-fine strategy for efficiency. Finally, we demonstrate the effectiveness of our algorithm for image deblurring, video restoration, and image matting.

Interactive Offline Tracking for Color Objects

Abstract: In this paper, we present an interactive offline tracking system for generic color objects. The system achieves 60- 100 fps on a 320 times 240 video. The user can therefore easily refine the tracking result in an interactive way. To fully exploit user input and reduce user interaction, the tracking problem is addressed in a global optimization framework. The optimization is efficiently performed through three steps. First, from user's input we train a fast object detector that locates candidate objects in the video based on proposed features called boosted color bin. Second, we exploit the temporal coherence to generate multiple object trajectories based on a global best-first strategy. Last, an optimal object path is found by dynamic programming.

Picture Collage Systems And Methods

Abstract: Systems and methods provide picture collage systems and methods. In one implementation, a system determines a salient region in each of multiple images and develops a Bayesian model to maximize visibility of the salient regions in a collage that overlaps the images. The Bayesian model can also minimize blank spaces in the collage and normalize the percentage of each salient region that can be visibly displayed in the collage. Images are placed with diversified rotational orientation to provide a natural artistic collage appearance. A Markov Chain Monte Carlo technique is applied to the parameters of the Bayesian model to obtain image placement, orientation, and layering. The MCMC technique can combine optimization proposals that include local, global, and pairwise samplings from a distribution of state variables.

Drag-and-drop pasting for seamless image composition

Abstract: Systems and methods provide drag-and-drop pasting for seamless image composition. In one implementation, a user casually outlines a region of a source image that contains a visual object to be pasted into a target image. An exemplary system automatically calculates a new boundary within this region, such that when pasted at this boundary, visual seams are minimized. The system applies a shortest path calculation to find the optimal pasting boundary. The best path has minimal color variation along its length, thus avoiding structure and visual objects in the target image and providing the best chance for seamlessness. Poisson image editing is applied across this optimized boundary to blend colors. When the visual object being pasted has fine structure at its border that could be truncated by the Poisson editing, the exemplary system integrates the alpha matte of the visual object into the Poisson equations to protect the fine structure.

Strategies for extracting foreground information using flash and no-flash image pairs

Abstract: A flash-based strategy is used to separate foreground information from background information within image information. In this strategy, a first image is taken without the use of flash. A second image is taken of the same subject matter with the use of flash. The foreground information in the flash image is illuminated by the flash to a much greater extent than the background information. Based on this property, the strategy applies processing to extract the foreground information from the background information. The strategy supplements the flash information by also taking into consideration motion information and color information.

Blurred/No-Blurred Image Alignment using Kernel Sparseness Prior

Abstract: Aligning a pair of blurred and non-blurred images is a prerequisite for many image and video restoration and graphics applications. The traditional alignment methods such as direct and feature-based approaches cannot be used due to the presence of motion blur in one image of the pair. In this paper, we present an effective and accurate alignment approach for a blurred/non-blurred image pair. We exploit a statistical characteristic of the real blur kernel – the marginal distribution of kernel value is sparse. Using this sparseness prior, we can search the best alignment which produces the sparsest blur kernel. The search is carried out in scale space with a coarse-to-fine strategy for efficiency. Finally, we demonstrate the effectiveness of our algorithm for image deblurring, video restoration, and image matting.

Creating optimized gradient mesh of a vector-based image from a raster-based image

Abstract: A method for creating an optimized gradient mesh of a vector-based image from a raster-based image. In one implementation, a set of boundaries for an object on a raster-based image may be received. An initial gradient mesh of the object may be created. A residual energy between the object on the raster-based image and a rendered initial gradient mesh may be minimized to generate an optimized gradient mesh.