Search For:

Displaying 1-50 out of 69 total
Binary-Space-Partitioned Images for Resolving Image-Based Visibility
Found in: IEEE Transactions on Visualization and Computer Graphics
By Chi-Wing Fu, Tien-Tsin Wong, Wai-Shun Tong, Chi-Keung Tang, Andrew J. Hanson
Issue Date:January 2004
pp. 58-71
<p><b>Abstract</b>-We propose a novel 2D representation for 3D visibility sorting, the <it>Binary-Space-Partitioned Image (BSPI)</it>, to accelerate real-time image-based rendering. BSPI is an efficient 2D realization of a 3D ...
 
ROD-TV: Reconstruction on Demand by Tensor Voting
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Wai-Shun Tong, Chi-Keung Tang
Issue Date:June 2003
pp. 391
A
 
Limits of Learning-Based Superresolution Algorithms
Found in: Computer Vision, IEEE International Conference on
By Zhouchen Lin, Junfeng He, Xiaoou Tang, Chi-Keung Tang
Issue Date:October 2007
pp. 1-8
Learning-based superresolution (SR) are popular SR techniques that use application dependent priors to infer the missing details in low resolution images (LRIs). However, their performance still deteriorates quickly when the magnification factor is moderat...
 
Dense Photometric Stereo Using Tensorial Belief Propagation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Kam-Lun Tang, Chi-Keung Tang, Tien-Tsin Wong
Issue Date:June 2005
pp. 132-139
We address the normal reconstruction problem by photometric stereo using a uniform and dense set of photometric images captured at fixed viewpoint. Our method is robust to spurious noises caused by highlight and shadows and non-Lambertian reflections. To s...
 
A Markov Random Field Approach for Dense Photometric Stereo
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Kam-Lun Tang, Chi-Keung Tang, Tien-Tsin Wong
Issue Date:June 2005
pp. 1197
We present a surprisingly simple system that allows for robust normal reconstruction by photometric stereo using a uniform and dense set of photometric images captured at fixed viewpoint, in the presense of spurious noises caused by highlight, shadows and ...
   
Two-Class Weather Classification
Found in: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Cewu Lu,Di Lin,Jiaya Jia,Chi-Keung Tang
Issue Date:June 2014
pp. 3718-3725
Given a single outdoor image, this paper proposes a collaborative learning approach for labeling it as either sunny or cloudy. Never adequately addressed, this twoclass classification problem is by no means trivial given the great variety of outdoor images...
 
Shadow Removal from Single RGB-D Images
Found in: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Yao Xiao,Efstratios Tsougenis,Chi-keung Tang
Issue Date:June 2014
pp. 3011-3018
We present the first automatic method to remove shadows from single RGB-D images. Using normal cues directly derived from depth, we can remove hard and soft shadows while preserving surface texture and shading. Our key assumption is: pixels with similar no...
 
Range-Sample Depth Feature for Action Recognition
Found in: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Cewu Lu,Jiaya Jia,Chi-Keung Tang
Issue Date:June 2014
pp. 772-779
We propose binary range-sample feature in depth. It is based on &amp;tau; tests and achieves reasonable invariance with respect to possible change in scale, viewpoint, and background. It is robust to occlusion and data corruption as well. The descripto...
 
Motion-Aware KNN Laplacian for Video Matting
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Dingzeyu Li,Qifeng Chen,Chi-Keung Tang
Issue Date:December 2013
pp. 3599-3606
This paper demonstrates how the nonlocal principle benefits video matting via the KNN Laplacian, which comes with a straightforward implementation using motion-aware K nearest neighbors. In hindsight, the fundamental problem to solve in video matting is to...
 
KNN Matting
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Qifeng Chen, Dingzeyu Li, Chi-Keung Tang
Issue Date:September 2013
pp. 2175-2188
This paper proposes to apply the nonlocal principle to general alpha matting for the simultaneous extraction of multiple image layers; each layer may have disjoint as well as coherent segments typical of foreground mattes in natural image matting. The esti...
 
A Closed-Form Solution to Tensor Voting: Theory and Applications
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Tai-Pang Wu, Sai-Kit Yeung, Jiaya Jia, Chi-Keung Tang,G. Medioni
Issue Date:August 2012
pp. 1482-1495
We prove a closed-form solution to tensor voting (CFTV): Given a point set in any dimensions, our closed-form solution provides an exact, continuous, and efficient algorithm for computing a structure-aware tensor that simultaneously achieves salient struct...
 
KNN matting
Found in: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Qifeng Chen, Dingzeyu Li, Chi-Keung Tang
Issue Date:June 2012
pp. 869-876
We are interested in a general alpha matting approach for the simultaneous extraction of multiple image layers; each layer may have disjoint segments for material matting not limited to foreground mattes typical of natural image matting. The estimated alph...
 
Adequate reconstruction of transparent objects on a shoestring budget
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Sai-Kit Yeung, Tai-Pang Wu, Chi-Keung Tang,T. F. Chan,S. Osher
Issue Date:June 2011
pp. 2513-2520
Reconstructing transparent objects is a challenging problem. While producing reasonable results for quite complex objects, existing approaches require custom calibration or somewhat expensive labor to achieve high precision. On the other hand, when an over...
 
Quasi-dense 3D reconstruction using tensor-based multiview stereo
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Tai-Pang Wu, Sai-Kit Yeung, Jiaya Jia, Chi-Keung Tang
Issue Date:June 2010
pp. 1482-1489
We propose tensor-based multiview stereo (TMVS) for quasi-dense 3D reconstruction from uncalibrated images. Our work is inspired by the patch-based multiview stereo (PMVS), a state-of-the-art technique in multiview stereo reconstruction. The effectiveness ...
 
Surface-from-Gradients without Discrete Integrability Enforcement: A Gaussian Kernel Approach
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Heung-Sun Ng, Tai-Pang Wu, Chi-Keung Tang
Issue Date:November 2010
pp. 2085-2099
Representative surface reconstruction algorithms taking a gradient field as input enforce the integrability constraint in a discrete manner. While enforcing integrability allows the subsequent integration to produce surface heights, existing algorithms hav...
 
Photometric Stereo via Expectation Maximization
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Tai-Pang Wu, Chi-Keung Tang
Issue Date:March 2010
pp. 546-560
This paper presents a robust and automatic approach to photometric stereo, where the two main components, namely surface normals and visible surfaces, are respectively optimized by Expectation Maximization (EM). A dense set of input images is conveniently ...
 
Robust dual motion deblurring
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Jia Chen, Lu Yuan, Chi-Keung Tang, Long Quan
Issue Date:June 2008
pp. 1-8
This paper presents a robust algorithm to deblur two consecutively captured blurred photos from camera shaking. Previous dual motion deblurring algorithms succeeded in small and simple motion blur and are very sensitive to noise. We develop a robust feedba...
 
Enforcing stochastic inverse consistency in non-rigid image registration and matching
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Sai-Kit Yeung, Chi-Keung Tang, Pengcheng Shi, Josien P.W. Pluim, Max A. Viergever, Albert C.S. Chung, Helen C. Shen
Issue Date:June 2008
pp. 1-8
This paper presents a new method to enforce inverse consistency in nonrigid image registration and matching. Conventional approaches assume diffeomorphic transformation, implicitly or explicitly. However, the inherent smoothness constraint discourages disc...
 
Extracting smooth and transparent layers from a single image
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Sai-Kit Yeung, Tai-Pang Wu, Chi-Keung Tang
Issue Date:June 2008
pp. 1-7
Layer decomposition from a single image is an under-constrained problem, because there are more unknowns than equations. This paper studies a slightly easier but very useful alternative where only the background layer has substantial image gradients and st...
 
Example-Based Cosmetic Transfer
Found in: Computer Graphics and Applications, Pacific Conference on
By Wai-Shun Tong, Chi-Keung Tang, Michael S. Brown, Ying-Qing Xu
Issue Date:November 2007
pp. 211-218
<p>Cosmetic makeup is used worldwide as a means to enhance beauty and express moods. An art form in its own right, cosmetic styles continuously change and evolve to reflect cultural and societal trends. While countless magazines and books are dedicat...
 
Surface-from-Gradients with Incomplete Data for Single View Modeling
Found in: Computer Vision, IEEE International Conference on
By Heung-Sun Ng, Tai-Pang Wu, Chi-Keung Tang
Issue Date:October 2007
pp. 1-8
Surface gradients are useful to surface reconstruction in single view modeling, shape-from-shading, and photometric stereo. Previous algorithms minimize a complex, nonlinear energy functional, or require dense surface gradients to perform integration to ge...
 
Soft Color Segmentation and Its Applications
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Yu-Wing Tai, Jiaya Jia, Chi-Keung Tang
Issue Date:September 2007
pp. 1520-1537
We propose an automatic approach to soft color segmentation, which produces soft color segments with appropriate amount of overlapping and transparency essential to synthesizing natural images for a wide range of image-based applications. While many state-...
 
Image Stitching Using Structure Deformation
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Jiaya Jia, Chi-Keung Tang
Issue Date:April 2008
pp. 617-631
The aim of this paper is to achieve seamless imagestitching without producing visual artifact caused by severeintensity discrepancy and structure misalignment, given that theinput images are roughly aligned or globally registered. Our newapproach is based ...
 
Spatio-Temporal Markov Random Field for Video Denoising
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Jia Chen, Chi-Keung Tang
Issue Date:June 2007
pp. 1-8
This paper presents a novel spatio-temporalMarkov random field (MRF) for video denoising. Two main issues are addressed in this paper, namely, the estimation of noise model and the proper use of motion estimation in the denoising process. Unlike previous a...
 
Robust Estimation of Texture Flow via Dense Feature Sampling
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yu-Wing Tai, Michael S. Brown, Chi-Keung Tang
Issue Date:June 2007
pp. 1-8
Texture flow estimation is a valuable step in a variety of vision related tasks, including texture analysis, image segmentation, shape-from-texture and texture remapping. This paper describes a novel and effective technique to estimate texture flow in an i...
 
Multiresolution Mesh Reconstruction from Noisy 3D Point Sets
Found in: Pattern Recognition, International Conference on
By Wai-Shun Tong, Chi-Keung Tang
Issue Date:August 2006
pp. 5-8
We augment the tensor voting framework with a datadriven multiscale scheme for reconstructing a multiresolution mesh from a noisy 3D point set. The augmentations are effective, automatic but very simple, consisting of surface saliency inference, scale segm...
 
Separating Subsurface Scattering from Photometric Image
Found in: Pattern Recognition, International Conference on
By Tai-Pang Wu, Chi-Keung Tang
Issue Date:August 2006
pp. 207-210
While subsurface scattering is common in many real objects, almost all separation algorithms focus on extracting specular and diffuse components from real images. In this paper, we present a model-less approach derived from the bi-directional surface scatt...
 
Simultaneous Image Denoising and Compression by Multiscale 2D Tensor Voting
Found in: Pattern Recognition, International Conference on
By Yu-Wing Tai, Wai-Shun Tong, Chi-Keung Tang
Issue Date:August 2006
pp. 818-821
In this paper we propose a method that simultaneously performs image denoising and compression by using multiscale tensor voting. Given a real color image, the pixels are first converted into a set of tokens to be grouped by tensor voting, where optimal sc...
 
Perceptually-Inspired and Edge-Directed Color Image Super-Resolution
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yu-Wing Tai, Wai-Shun Tong, Chi-Keung Tang
Issue Date:June 2006
pp. 1948-1955
Inspired by multi-scale tensor voting, a computational framework for perceptual grouping and segmentation, we propose an edge-directed technique for color image superresolution given a single low-resolution color image. Our multi-scale technique combines t...
 
Visible Surface Reconstruction from Normals with Discontinuity Consideration
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Tai-Pang Wu, Chi-Keung Tang
Issue Date:June 2006
pp. 1793-1800
Given a dense set of imperfect normals obtained by photometric stereo or shape from shading, this paper presents an optimization algorithm which alternately optimizes until convergence the surface integrabilities and discontinuities inherent in the normal ...
 
Video Repairing under Variable Illumination Using Cyclic Motions
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Jiaya Jia, Yu-Wing Tai, Tai-Pang Wu, Chi-Keung Tang
Issue Date:May 2006
pp. 832-839
This paper presents a complete system capable of synthesizing a large number of pixels that are missing due to occlusion or damage in an uncalibrated input video. These missing pixels may correspond to the static background or cyclic motions of the capture...
 
Eliminating Structure and Intensity Misalignment in Image Stitching
Found in: Computer Vision, IEEE International Conference on
By Jiaya Jia, Chi-Keung Tang
Issue Date:October 2005
pp. 1651-1658
The aim of this paper is to achieve seamless image stitching for eliminating obvious visual artifact caused by severe intensity discrepancy, image distortion and structure mis-alignment, given that the input images are globally registered. Our approach is ...
 
A Bayesian Approach for Shadow Extraction from a Single Image
Found in: Computer Vision, IEEE International Conference on
By Tai-Pang Wu, Chi-Keung Tang
Issue Date:October 2005
pp. 480-487
This paper addresses the problem of shadow extraction from a single image of a complex natural scene. No simplifying assumption on the camera and the light source other than the Lambertian assumption is used. Our method is unique because it is capable of t...
 
Dense Photometric Stereo Using a Mirror Sphere and Graph Cut
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Tai-Pang Wu, Chi-Keung Tang
Issue Date:June 2005
pp. 140-147
We present a surprisingly simple system that performs robust normal reconstruction by dense photometric stereo, in the presence of large shadows, highlight, transparencies, complex geometry, variable attenuation in light intensity and inaccurate light dire...
 
Local Color Transfer via Probabilistic Segmentation by Expectation-Maximization
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yu-Wing Tai, Jiaya Jia, Chi-Keung Tang
Issue Date:June 2005
pp. 747-754
<p>We address the problem of regional color transfer between two natural images by probabilistic segmentation. We use a new Expectation-Maximization (EM) scheme to impose both spatial and color smoothness to infer natural connectivity among pixels. U...
 
Robust Estimation of Adaptive Tensors of Curvature by Tensor Voting
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Wai-Shun Tong, Chi-Keung Tang
Issue Date:March 2005
pp. 434-449
Although curvature estimation from a given mesh or regularly sampled point set is a well-studied problem, it is still challenging when the input consists of a cloud of unstructured points corrupted by misalignment error and outlier noise. Such input is ubi...
 
Tensor Voting for Image Correction by Global and Local Intensity Alignment
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Jiaya Jia, Chi-Keung Tang
Issue Date:January 2005
pp. 36-50
This paper presents a voting method to perform image correction by global and local intensity alignment. The key to our modeless approach is the estimation of global and local replacement functions by reducing the complex estimation problem to the robust 2...
 
Simultaneous Two-View Epipolar Geometry Estimation and Motion Segmentation by 4D Tensor Voting
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Wai-Shun Tong, Chi-Keung Tang, Gérard Medioni
Issue Date:September 2004
pp. 1167-1184
We address the problem of simultaneous two-view epipolar geometry estimation and motion segmentation from nonstatic scenes. Given a set of noisy image pairs containing matches of n objects, we propose an unconventional, efficient, and robust method, 4D ten...
 
Inference of Segmented Color and Texture Description by Tensor Voting
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Jiaya Jia, Chi-Keung Tang
Issue Date:June 2004
pp. 771-786
<p><b>Abstract</b>—A robust synthesis method is proposed to automatically infer missing color and texture information from a damaged 2D image by <tmath>N\rm D</tmath> tensor voting (<tmath>N > 3</tmath>). The sa...
 
Video Repairing: Inference of Foreground and Background under Severe Occlusion
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Jiaya Jia, Tai-Pang Wu, Yu-Wing Tai, Chi-Keung Tang
Issue Date:July 2004
pp. 364-371
In this paper, we propose a new method, video repairing, to robustly infer missing static background and moving fore-ground due to severe damage or occlusion from a video. To recover background pixels, we extend the image repairing method, where layer segm...
 
First Order Augmentation to Tensor Voting for Boundary Inference and Multiscale Analysis in 3D
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Wai-Shun Tong, Chi-Keung Tang, Philippos Mordohai, Gérard Medioni
Issue Date:May 2004
pp. 594-611
<p><b>Abstract</b>—Most computer vision applications require the reliable detection of boundaries. In the presence of outliers, missing data, orientation discontinuities, and occlusion, this problem is particularly challenging. We propose...
 
Stereo Reconstruction from Multiperspective Panoramas
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Yin Li, Heung-Yeung Shum, Chi-Keung Tang, Richard Szeliski
Issue Date:January 2004
pp. 45-62
<p><b>Abstract</b>—A new approach to computing a panoramic (360 degrees) depth map is presented in this paper. Our approach uses a large collection of images taken by a camera whose motion has been constrained to planar concentric circles...
 
Image Registration with Global and Local Luminance Alignment
Found in: Computer Vision, IEEE International Conference on
By Jiaya Jia, Chi-Keung Tang
Issue Date:October 2003
pp. 156
Inspired by tensor voting, we present luminance voting, a novel approach for image registration with global and local luminance alignment. The key to our modeless approach is the direct estimation of replacement function, by reducing the complex estimation...
 
Image Repairing: Robust Image Synthesis by Adaptive ND Tensor Voting
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Jiaya Jia, Chi-Keung Tang
Issue Date:June 2003
pp. 643
We present a robust image synthesis method to automatically infer missing information from a damaged 2D image by tensor voting. Our method translates image color and texture information into an adaptive N D tensor, followed by a voting process that infers ...
 
Curvature-Augmented Tensor Voting for Shape Inference from Noisy 3D Data
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Chi-Keung Tang, Geérard Medioni
Issue Date:June 2002
pp. 858-864
<p>We improve the basic tensor voting formalism to infer the sign and direction of principal curvatures at each input site from noisy 3D data. Unlike most previous approaches, no local surface fitting, partial derivative computation, nor oriented nor...
 
First Order Tensor Voting, and Application to 3-D Scale Analysis
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Wai-Shun Tong, Chi-Keung Tang, Gérard Medioni
Issue Date:December 2001
pp. 175
Many computer vision systems depend on reliable detection of 3-D boundaries and regions in order to proceed. In the presence of outliers, missing data, and orientation discontinuities due to occlusion, it is difficult to detect boundaries and interpolate d...
 
Epipolar Geometry Estimation for Non-Static Scenes by 4D Tensor Voting
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Wai-Shun Tong, Chi-Keung Tang, Gérard Medioni
Issue Date:December 2001
pp. 926
In the presence of false matches and moving objects, image registration is challenging, as outlier rejection, matching and registration become interdependent. In this paper, we present an efficient and robust method, 4D tensor voting, to estimate epipolar ...
 
N-Dimensional Tensor Voting and Application to Epipolar Geometry Estimation
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Chi-Keung Tang, Gérard Medioni, Mi-Suen Lee
Issue Date:August 2001
pp. 829-844
<p><b>Abstract</b>—We address the problem of epipolar geometry estimation efficiently and effectively, by formulating it as one of hyperplane inference from a sparse and noisy point set in an 8D space. Given a set of noisy point correspon...
 
Efficient Dense Depth Estimation from Dense Multiperspective Panoramas
Found in: Computer Vision, IEEE International Conference on
By Yin Li, Chi-Keung Tang, Heung-Yeung Shum
Issue Date:July 2001
pp. 119
In this paper we study how to compute a dense depth map with panoramic field of view (e.g., 360 degrees) from multi-perspective panoramas. A dense sequence of multiperspective panoramas is used for better accuracy and reduced ambiguity by taking advantage ...
 
Robust Estimation of Curvature Information from Noisy 3D Data for Shape Description
Found in: Computer Vision, IEEE International Conference on
By Chi-Keung Tang, Gérard Medioni
Issue Date:September 1999
pp. 426
We describe an effective and novel approach to infer sign and direction of principal curvatures at each input site from noisy 3D data. Unlike most previous approaches, no local surface fitting, partial derivative computation of any kind, nor oriented norma...
 
 1  2 Next >>