Minglun Gong -- Research

Publications:
Here are my publications indexed by Google Scholar, Microsoft Academic Search, DBLP Bibliography, and ACM Portal. For full publication list, please check my C.V.
Selected Research Projects:
	Foreground Segmentation for Live Videos An easy to implement and simple to use algorithm is proposed for processing live video in real-time. The algorithm can handle a variety of challenges such as dynamic background, fuzzy object boundaries, camera motion, topology changes, and low color contrast. It has applications in video matting, video conferencing, and automatic background subtraction. Related papers: CVPR 2011 Webpage: Foreground Segmentation
	Real-time Video Matting This project presents the 1st real-time matting algorithm that can handle live videos with natural backgrounds. The algorithm is based on a set of novel Poisson equations that are derived for handling multichannel color vectors, as well as the depth information captured. Quantitative evaluation shows that the presented algorithm is comparable to state-of-the-art offline image matting techniques in terms of accuracy. Related papers: IJCV 2011, GI 2010, CRV 2009 Webpage: Video Matting
	Modeling of Deformable Objects We propose a novel approach to reconstruct complete 3D deformable models over time using a single depth camera. The core of this algorithm is based on the assumption that the deformation is continuous and predictable in a short temporal interval. Our experiment shows that this approach is able to reconstruct visually plausible 3D surface deformation results with a single camera. Related papers: 3DPVT 2010, ICCV 2009
	Similarity-based Image Browsing This project studies how to facilatate users to locate the desired photos. Using extracted feature vectors, the approach maps photos onto a 2D virtual canvas so that similar ones are close to each other. When a user browses the collection, a subset of photos is automatically selected to compose a photo collage. Once having identified photos of interest the user can find more photos with similar features through panning and zooming operations, which dynamically update the photo collage. Related papers: CIVR 2009, ISVC 2008
	Background Subtraction from Dynamic Scenes This project addresses the problem of foreground separation from the background modeling perspective. In particular, we deal with the difficult scenarios where the background texture might change spatially and temporally. Empirical experiments on a variety of datasets show the competitiveness of the proposed approach, which works in real-time on programmable graphics cards. Related papers: TIM 2011, ICCV 2009, ICPR 2008 Source code: ZIP
	Stereoscopic Inpainting We present a novel algorithm for simultaneous color and depth inpainting. The algorithm takes stereo images and estimated disparity maps as input and fills in missing color and depth information introduced by occlusions or object removal. We demonstrate the effectiveness of the proposed algorithm on several challenging data sets. Related papers: CVPR 2008
	Real-time Rendering for Dynamic Scenes This project studies how to render dynamic scenes using only a few sample views and estimated noisy disparity maps. To color a pixel in the novel view, a backward searching process is conducted to find the corresponding pixels from the closest four reference images. Since the computations for different pixels are independent, they can be performed in parallel on the Graphics Processing Units of modern graphics hardware. Related papers: GI 2007, GM 2005
	Light Fall-off Stereo We present light fall-off stereo (LFS) a new method for computing depth from scenes beyond Lambertian reflectance and texture. LFS takes a number of images from a stationary camera as the illumination source moves away from the scene. Based on the inverse square law for light intensity, the ratio images are directly related to scene depth from the perspective of the light source. Related papers: ICIP 2008, CVPR 2007
	Joint Disparity and Disparity Flow Estimation A disparity flow map for a given view depicts the 3D motion observed from this view. An algorithm is developed to compute both disparity and disparity flow in an integrated process. The estimated disparity flow is used to predict the disparity for the next frame. The temporal consistency between the two frames is therefore enforced. All computations are performed in the 2D image space, leading to an efficient implementation. Related papers: CVIU 2008, ECCV 2006, ICPR 2006
	Evaluation of Cost Aggregation Approaches This project studies how well different cost aggregation approaches perform under the real-time constraint. Six recent cost aggregation approaches are implemented and optimized for graphics hardware so that real-time speed can be achieved. The performances of these aggregation approaches in terms of both processing speed and result quality are reported. Related papers: IJCV 2007, 3DPVT 2006 Source code: ZIP
	GPU-based Real-time Stereo Matching Algorithms Real-time stereo estimation has many important applications in robotics, image-based modeling and rendering, etc. This project investigates how to perform stereo matching on the Graphics Processing Units (GPU) of modern programmable graphics cards. Two algorithms are proposed, both are capable of estimating disparity maps for dynamic real scenes in real time. Related papers: 3DPVT 2006, 3DIM 2005
	Orthogonal Reliability-based DP A novel algorithm is presented for estimating reliable stereo matches in real-time. The algorithm performs dynamic programming (DP) along both horizontal and vertical scanlines. Most computations are implemented on programmable graphics hardware, which improves the processing speed and makes real-time estimation possible. If needed, the algorithm can be configured for generating full density disparity maps. Related papers: TIP 2007, CVPR 2005
	Large Motion Estimation Using Reliability-DP Detecting and estimating motions of fast moving objects has many important applications. Here we use reliability-based dynamic programming (DP) technique to solving large motion estimation problem. The resulting algorithm can handle sequences that contain large motions and can produce optical flows with 100% density over the entire image domain. Related papers: IJCV 2006, ICIP 2004
	Unambiguous Stereo Matching Using DP A new reliability measure is proposed. For stereo vision application, the reliability of a proposed match is defined as the cost difference between the globally best disparity assignment that includes the match, and the globally best assignment that does not include the match. A reliability-based algorithm is derived, which selectively assigns disparities to pixels when the corresponding reliabilities exceed a given threshold. Related papers: TPAMI 2005, ICCV 2003
	Multiresolution GA and Its Applications A new algorithm is proposed that incorporates a multi-resolution scheme into the conventional genetic algorithms (GA). The solutions of image-related problems are encoded through encoding the corresponding quadtrees, and hence, the 2D locality within the solutions can be preserved. Several computer vision problems, such as color image segmentation, stereo matching, and motion estimation, can be solved efficiently under the same framework. Related papers: PR 2004, IJCV 2002, ICPR 2002
	Rayset: A Taxonomy for Image-Based Rendering A rayset is a parametric function, which consists of two mapping relations. The first one maps from a parameter space to the ray space, while the second one maps from the parameter space to the attribute space. A taxonomy is proposed based on the rayset concept, using which scene representations and scene reconstruction techniques used in image-based rendering are individually classified. Related papers: IJIG 2006
	Layer-based Morphing The warp functions used in most image morphing algorithms are one-to-one. Hence, when some features are visible in only one of the reference images, "ghosting" problems will appear. In addition, since the control features have global effects, there is no way to control different objects in the scene separately. To address these problems, a layer-based morphing approach is porposed. Multiple layers are created and are used to solve the visibility problem. Related papers: GM 2001
	A GA for Minimum Weight Triangulation In this project, a new method for the minimum weight triangulation of points on a plane is presented based on the rationale of genetic algorithms (GA). Polygon crossover and its algorithm for triangulations are proposed. New adaptive crossover and mutation operators are introduced. It is shown that the new method for the minimum weight triangulation can obtain more optimal results of triangulations than the greedy algorithm. Related papers: ICEC 1997
	Fast Ray-NURBS Intersection Calculation A new algorithm with extrapolation process for computing the ray-NURBS intersection is presented. In the preprocessing step, the NURBS surfaces are subdivided adaptively into rational Bezier patches. The parallelepipeds are used to enclose the respective patches as tightly as possible. The improved Newton iteration with extrapolation process saves CPU time by reducing the iteration steps. The intersection scheme is faster than previous methods. Related papers: C&G 1997