Search For:

Displaying 1-50 out of 69 total
Accurate and Scalable Surface Representation and Reconstruction from Images
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Gang Zeng, Sylvain Paris, Long Quan, François Sillion
Issue Date:January 2007
pp. 141-158
We introduce a new surface representation method, called patchwork, to extend three-dimensional surface reconstruction capabilities from multiple images. A patchwork is the combination of several patches that are built one by one. This design potentially a...
 
Interactive Shape from Shading
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Gang Zeng, Yasuyuki Matsushita, Long Quan, Heung-Yeung Shum
Issue Date:June 2005
pp. 343-350
Shape from shading (SfS) has always been difficult for real applications due to its intrinsic ill-posedness. In this paper, we propose an interactive SfS method which efficiently uses human knowledge in order to resolve ambiguity. We propose a global solut...
 
Image-based street-side city modeling
Found in: ACM Transactions on Graphics (TOG)
By Jianxiong Xiao, Long Quan, Maxime Lhuillier, Peng Zhao, Tian Fang, Jianxiong Xiao, Long Quan, Maxime Lhuillier, Peng Zhao, Tian Fang
Issue Date:December 2009
pp. 1-2
We propose an automatic approach to generate street-side 3D photo-realistic models from images captured along the streets at ground level. We first develop a multi-view semantic segmentation method that recognizes and segments each image at pixel level int...
     
Filtering and Rendering of Resolution-Dependent Reflectance Models
Found in: IEEE Transactions on Visualization and Computer Graphics
By Ping Tan, Stephen Lin, Long Quan, Baining Guo, Harry Shum
Issue Date:March 2008
pp. 412-425
The apparent reflectance of a surface depends upon the resolution at which it is imaged. Conventional reflectance models represent reflection at a single predetermined resolution; however, a low-resolution pixel that views a greater surface area often exhi...
 
Progressive Surface Reconstruction from Images Using a Local Prior
Found in: Computer Vision, IEEE International Conference on
By Gang Zeng, Sylvain Paris, Long Quan, François Sillion
Issue Date:October 2005
pp. 1230-1237
This paper introduces a new method for surface reconstruction from multiple calibrated images. The primary contribution of this work is the notion of local prior to combine the flexibility of the carving approach with the accuracy of graph-cut optimization...
 
Outward-Looking Circular Motion Analysis of Large Image Sequences
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Guang Jiang, Yichen Wei, Long Quan, Hung-tat Tsui, Heung Yeung Shum
Issue Date:February 2005
pp. 271-277
This paper presents a novel and simple method of analyzing the motion of a large image sequence captured by a calibrated outward-looking video camera moving on a circular trajectory for large-scale environment applications. Previous circular motion algorit...
 
Learning CRFs for Image Parsing with Adaptive Subgradient Descent
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Honghui Zhang,Jingdong Wang,Ping Tan,Jinglu Wang,Long Quan
Issue Date:December 2013
pp. 3080-3087
We propose an adaptive sub gradient descent method to efficiently learn the parameters of CRF models for image parsing. To balance the learning efficiency and performance of the learned CRF models, the parameter learning is iteratively carried out by solvi...
 
Image-Based Modeling of Unwrappable Façades
Found in: IEEE Transactions on Visualization and Computer Graphics
By Tian Fang, Zhexi Wang, Honghui Zhang, Long Quan
Issue Date:October 2013
pp. 1720-1731
In this paper, we propose an unwrappable representation for image-based façade modeling from multiple registered images. An unwrappable façade is represented by the mutually orthogonal baseline and profile. We first reconstruct semidense 3D points from ima...
 
Parsing façade with rank-one approximation
Found in: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Chao Yang, Tian Han, Long Quan, Chiew-Lan Tai
Issue Date:June 2012
pp. 1720-1727
The binary split grammar is powerful to parse façade in a broad range of types, whose structure is characterized by repetitive patterns with different layouts. We notice that, as far as two labels are concerned, BSG parsing is equivalent to approximating a...
 
Per-pixel translational symmetry detection, optimization, and segmentation
Found in: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Peng Zhao, Lei Yang, Honghui Zhang, Long Quan
Issue Date:June 2012
pp. 526-533
We present a novel method for translational symmetry detection, optimization, and symmetry object segmentation in façade images. Unlike most previous methods, our detection algorithm accumulates pixel-level correspondence in translation space. Thus it does...
 
Translation symmetry detection in a fronto-parallel view
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Peng Zhao, Long Quan
Issue Date:June 2011
pp. 1009-1016
In this paper, we present a method of detecting translation symmetries from a fronto-parallel image. The proposed method automatically detects unknown multiple repetitive patterns of arbitrary shapes, which are characterized by translation symmetries on a ...
 
Partial similarity based nonparametric scene parsing in certain environment
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Honghui Zhang, Tian Fang, Xiaowu Chen, Qinping Zhao, Long Quan
Issue Date:June 2011
pp. 2241-2248
In this paper we propose a novel nonparametric image parsing method for the image parsing problem in certain environment. A novel and efficient nearest neighbor matching scheme, the ANN bilateral matching scheme, is proposed. Based on the proposed matching...
 
The Geometry of Reflectance Symmetries
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Ping Tan,Long Quan,Todd Zickler
Issue Date:December 2011
pp. 2506-2520
Different materials reflect light in different ways, and this reflectance interacts with shape, lighting, and viewpoint to determine an object's image. Common materials exhibit diverse reflectance effects, and this is a significant source of difficulty for...
 
Camera Calibration Using Lengths of Corresponding Line Segments
Found in: Image and Video Technology, Pacific-Rim Symposium on
By Ruiyan Wang, Guang Jiang, Long Quan, Chengke Wu
Issue Date:November 2010
pp. 162-167
Camera calibration using patterns is widely used in computer vision and industry. The accuracy of calibration depends on the accuracy of the pattern. A high accuracy pattern is usually difficult to manufacture in labs. In this paper, we propose to use two ...
 
A Linear Interpolation Fuzzy Controller with NN Compensator for an Electro-hydraulic Servo System
Found in: Computational Aspects of Social Networks, International Conference on
By Yanhong Bai, Zhiyi Sun, Long Quan, Shaojuan Yu
Issue Date:September 2010
pp. 565-568
A linear interpolation fuzzy controller with NN compensator is proposed for an electro-hydraulic position servo system. First, to overcome the conventional fuzzy controller’s disadvantage of lower precision caused by discretization, bilinear interpolation ...
 
Rectilinear parsing of architecture in urban environment
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Peng Zhao, Tian Fang, Jianxiong Xiao, Honghui Zhang, Qinping Zhao, Long Quan
Issue Date:June 2010
pp. 342-349
We propose an approach that parses registered images captured at ground level into architectural units for large-scale city modeling. Each parsed unit has a regularized shape, which can be used for further modeling purposes. In our approach, we first parse...
 
Invited Talk: Image-Based Modeling of Plants and Trees
Found in: Plant Growth Modeling and Applications, International Symposium on
By Long Quan
Issue Date:November 2009
pp. 351
We present a semi-automatic technique for modeling trees and plants directly from images. Our image-based approach has the distinct advantage that the resulting model inherits the realistic shape and complexity of a real tree or plant. This is possible bec...
 
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...
 
Normalized tree partitioning for image segmentation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Jingdong Wang, Yangqing Jia, Xian-Sheng Hua, Changshui Zhang, Long Quan
Issue Date:June 2008
pp. 1-8
In this paper, we propose a novel graph based clustering approach with satisfactory clustering performance and low computational cost. It consists of two main steps: tree fitting and partitioning. We first introduce a probabilistic method to fit a tree to ...
 
Blurred/Non-Blurred Image Alignment using Sparseness Prior
Found in: Computer Vision, IEEE International Conference on
By Lu Yuan, Jian Sun, Long Quan, Heung-Yeung Shum
Issue Date:October 2007
pp. 1-8
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 b...
 
Joint Affinity Propagation for Multiple View Segmentation
Found in: Computer Vision, IEEE International Conference on
By Jianxiong Xiao, Jingdong Wang, Ping Tan, Long Quan
Issue Date:October 2007
pp. 1-7
A joint segmentation is a simultaneous segmentation of registered 2D images and 3D points reconstructed from the multiple view images. It is fundamental in structuring the data for subsequent modeling applications. In this paper, we treat this joint segmen...
 
Subpixel Photometric Stereo
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Ping Tan, Stephen Lin, Long Quan
Issue Date:August 2008
pp. 1460-1471
Conventional photometric stereo recovers one normal direction per pixel of the input image. This fundamentally limits the scale of recovered geometry to the resolution of the input image, and cannot model surfaces with subpixel geometric structures. In thi...
 
Picture Collage
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Jingdong Wang, Long Quan, Jian Sun, Xiaoou Tang, Heung-Yeung Shum
Issue Date:June 2006
pp. 347-354
In this paper, we address a novel problem of automatically creating a picture collage from a group of images. Picture collage is a kind of visual image summary - to arrange all input images on a given canvas, allowing overlay, to maximize visible visual in...
 
Separation of Highlight Reflections on Textured Surfaces
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Ping Tan, Long Quan, Stephen Lin
Issue Date:June 2006
pp. 1855-1860
We present a method for separating highlight reflections on textured surfaces. In contrast to previous techniques that use diffuse color information from outside the highlight area to constrain the solution, the proposed method further capitalizes on the s...
 
Detection of Concentric Circles for Camera Calibration
Found in: Computer Vision, IEEE International Conference on
By Guang Jiang, Long Quan
Issue Date:October 2005
pp. 333-340
The geometry of plane-based calibration methods is well understood, but some user interaction is often needed in practice for feature detection. This paper presents a fully automatic calibration system that uses patterns of pairs of concentric circles. The...
 
Asymmetrical Occlusion Handling Using Graph Cut for Multi-View Stereo
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yichen Wei, Long Quan
Issue Date:June 2005
pp. 902-909
Occlusion is usually modelled in two images symmetrically in previous stereo algorithms which cannot work for multi-view stereo efficiently. In this paper, we present a novel formulation that handles occlusion using only one depth map in an asymmetrical wa...
 
Robust Carving for Non-Lambertian Objects
Found in: Pattern Recognition, International Conference on
By Gang Zeng, Sylvain Paris, Long Quan
Issue Date:August 2004
pp. 119-122
This paper presents a new surface reconstruction method that extends previous carving methods for non-Lambertian objects by integrating the smoothness and image information of different aspects. We introduce a robust multi-view photo-consistency function a...
 
Depth vs. Intensity: Which is More Important for Face Recognition?
Found in: Pattern Recognition, International Conference on
By Chenghua Xu, Yunhong Wang, Tieniu Tan, Long Quan
Issue Date:August 2004
pp. 342-345
Both depth and intensity are important information for face recognition. In this paper, based on 3D face modelling, we extract depth features and intensity features respectively, and further compare their capacity to characterize the individuals in our dat...
 
Circular Motion Geometry Using Minimal Data
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Guang Jiang, Long Quan, Hung-Tat Tsui
Issue Date:June 2004
pp. 721-731
<p><b>Abstract</b>—Circular motion or single axis motion is widely used in computer vision and graphics for 3D model acquisition. This paper describes a new and simple method for recovering the geometry of uncalibrated circular motion fro...
 
Region-Based Progressive Stereo Matching
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yichen Wei, Long Quan
Issue Date:July 2004
pp. 106-113
A novel region-based progressive stereo matching algorithm is presented. It combines the strengthes of previous region-based and progressive approaches. The progressive framework avoids the time consuming global optimization, while the inherent problem, th...
 
Automatic 3D Face Recognition Combining Global Geometric Features with Local Shape Variation Information
Found in: Automatic Face and Gesture Recognition, IEEE International Conference on
By Chenghua Xu, Yunhong Wang, Tieniu Tan, Long Quan
Issue Date:May 2004
pp. 308
Face recognition is a focused issue in pattern recognition over the past decades. In this paper, we have proposed a new scheme for face recognition using 3D information. In this scheme, the scattered 3D point cloud is first represented with a regular mesh ...
 
Adaptive Multi-Resolution Fitting and its Application to Realistic Head Modeling
Found in: Geometric Modeling and Processing
By Chenghua Xu, Long Quan, Yunhong Wang, Tieniu Tan, Maxime Lhuillier
Issue Date:April 2004
pp. 345
The general approach for object modeling is to construct the surface from the high-quality range points obtained from laser scanners. In this paper, we face the noise point cloud obtained from image sequences by a common camera and develop a novel algorith...
 
Geometry of Single Axis Motions Using Conic Fitting
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Guang Jiang, Hung-tat Tsui, Long Quan, Andrew Zisserman
Issue Date:October 2003
pp. 1343-1348
<p><b>Abstract</b>—Previous algorithms for recovering 3D geometry from an uncalibrated image sequence of a single axis motion of unknown rotation angles are mainly based on the computation of two-view fundamental matrices and three-view t...
 
Lightweight Face Relighting
Found in: Computer Graphics and Applications, Pacific Conference on
By Sylvain Paris, François X. Sillion, Long Quan
Issue Date:October 2003
pp. 41
In this paper we present a method to relight human faces in real time, using consumer-grade graphics cards even with limited 3D capabilities. We show how to render faces using a combination of a simple, hardware-accelerated parametric model simulating skin...
 
Surface Reconstruction by Integrating 3D and 2D Data of Multiple Views
Found in: Computer Vision, IEEE International Conference on
By Maxime Lhuillier, Long Quan
Issue Date:October 2003
pp. 1313
Surface representation is needed for almost all modeling and visualization applications, but unfortunately, 3D data from a passive vision system are often insufficient for a traditional surface reconstruction technique that is designed for densely scanned ...
 
Circular Motion Geometry by Minimal 2 Points in 4 Images
Found in: Computer Vision, IEEE International Conference on
By Guang Jiang, Long Quan, Hung-tat Tsui
Issue Date:October 2003
pp. 221
This paper describes a new and simple method of recovering the geometry of uncalibrated circular motion or single axis motion using a minimal data set of 2 points in 4 images. This problem has been solved using non-minimal data either by computing the fund...
 
Match Propogation for Image-Based Modeling and Rendering
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Maxime Lhuillier, Long Quan
Issue Date:August 2002
pp. 1140-1146
<p>This paper presents a quasi-dense matching algorithm between images based on the match propagation principle. The algorithm starts from a set of sparse seed matches, then propagates to the neighboring pixels by the best-first strategy, and produce...
 
Concentric Mosaic(s), Planar Motion and 1D Cameras
Found in: Computer Vision, IEEE International Conference on
By Long Quan, Le Lu, Heung-Yeung Shum, Maxime Lhuillier
Issue Date:July 2001
pp. 193
General SFM methods give poor results for images captured by constrained motions such as planar motion of concentric mosaics (CM). In this paper, we propose new SFM algorithms for both images captured by CM and composite mosaic images from CM. We first int...
 
Minimal Projective Reconstruction Including Missing Data
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Fredrik Kahl, Anders Heyden, Long Quan
Issue Date:April 2001
pp. 418-424
<p><b>Abstract</b>—The minimal data necessary for projective reconstruction from image points is well-known when each object point is visible in all images. In this paper, we formulate and propose solutions to a new family of reconstructi...
 
Two-Way Ambiguity in 2D Projective Reconstruction from Three Uncalibrated 1D Images
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Long Quan
Issue Date:February 2001
pp. 212-216
<p><b>Abstract</b>—We show that there is, in general, a two-way ambiguity for 2D projective reconstruction from three uncalibrated 1D views, independent of the number of point correspondences. The two distinct projective reconstructions a...
 
Camera Calibration and Relative Pose Estimation from Gravity
Found in: Pattern Recognition, International Conference on
By Peter F. Sturm, Long Quan
Issue Date:September 2000
pp. 1072
We examine the potential use of gravity for camera calibration and pose estimation purposes. Concretely, objects being launched or dropped follow trajectories dictated by the law of gravity. We examine if video sequences of such trajectories give us exploi...
 
Robust Dense Matching Using Local and Global Geometric Constraints
Found in: Pattern Recognition, International Conference on
By Maxime Lhuillier, Long Quan
Issue Date:September 2000
pp. 1968
A new robust dense matching algorithm is introduced in this paper. The algorithm starts from matching the most textured points, and then a match propagation algorithm is developed with the best first strategy to densify the matches. Next, the matching map ...
 
Edge-Constrained Joint View Triangulation for Image Interpolation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Maxime Lhuillier, Long Quan
Issue Date:June 2000
pp. 2218
Image-based-interpolation creates smooth and photorealistic views between two viewpoints. The concept of joint view triangulation (JVT) has been proven an efficient multi-view representation to handle visibility issue. However, the existing JVT, built only...
 
A Unified Linear Algorithm for a Novel View Synthesis and Camera Pose Estimation in Mixed Reality
Found in: Virtual Reality Conference, IEEE
By Toshihiro Kobayashi, Goki Inoue, Yuichi Ohta, Long Quan
Issue Date:March 2000
pp. 263
We propose a linear algorithm that is useful for realizing geometric registration between the view of a real scene and that of a virtual object in an image-based rendering framework. In a unified framework, the novel view synthesis of a virtual object base...
 
Inherent Two-Way Ambiguity in 2D Projective Reconstruction from Three Uncalibrated 1D Images
Found in: Computer Vision, IEEE International Conference on
By Long Quan
Issue Date:September 1999
pp. 344
It is shown that there always exists a two-way ambiguity for 2D projective reconstruction from three uncalibrated 1D views independent of the number of point correspondences. It is also shown that the two distinct projective reconstructions are exactly rel...
 
Linear N-Point Camera Pose Determination
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Long Quan, Zhongdan Lan
Issue Date:August 1999
pp. 774-780
<p><b>Abstract</b>—The determination of camera position and orientation from known correspondences of 3D reference points and their images is known as <it>pose estimation</it> in computer vision and <it>space resection&l...
 
Minimal Projective Reconstruction with Missing Data
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Long Quan, Anders Heyden, Fredrik Kahl
Issue Date:June 1999
pp. 2210
The minimal data necessary for projective reconstruction from point correspondences is well-known when the points are visible in all images. In this paper, we formulate and propose solutions to a new family of reconstruction problems from multiple images w...
 
Image Interpolation by Joint View Triangulation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Maxime Lhuillier, Long Quan
Issue Date:June 1999
pp. 2139
Creating novel views by interpolating prestored images or view morphing has many applications in visual simulation. We present in this paper a new method of automatically interpolating two images which tackles two most difficult problems of morphing due to...
 
Affine Structure from Line Correspondences With Uncalibrated Affine Cameras
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Long Quan, Takeo Kanade
Issue Date:August 1997
pp. 834-845
<p><b>Abstract</b>—This paper presents a linear algorithm for recovering 3D affine shape and motion from line correspondences with uncalibrated affine cameras. The algorithm requires a minimum of seven line correspondences over three view...
 
Uncalibrated 1D projective camera and 3D affine reconstruction of lines
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Long Quan
Issue Date:June 1997
pp. 60
We describe a linear algorithm to recover 3D affine shape/motion from line correspondences over three views with uncalibrated affine cameras. The key idea is the introduction of a one-dimensional projective camera. This converts the 3D affine reconstructio...
 
 1  2 Next >>