缪永伟,肖春霞, 著. 三维点采样模型的几何处理和形状造型. 北京:科学出版社, 2014.9.

Yongwei Miao, Chunxia Xiao. Geometric Processing and Shape Modeling for Point-Sampled Models. Beijing: Science Press, 2014.9.

内容简介: 本书是介绍三维点采样模型数字几何处理的一本专著。全书对三维点采样模型几何处理和形状造型的一些核心领域进行了详细介绍,包括点采样模型几何处理中的基本问题、点采样模型的参数化方法、点采样模型的分片方法、点采样模型的光顺去噪方法、点采样模型的简化重采样方法、点采样模型的形状修复和纹理合成方法、点采样模型的形状造型方法、点采样模型的形状变形方法等,这些内容构成了一个较完整的点采样模型数字几何处理框架,书中所提出算法下实现的大量应用实例验证了算法的有效性、实用性和通用性。


Selected Papers

Repetitions Detection based 3D Reconstruction of Detailed Architectures

Abstract: In the literature of computer graphics and computer vision, the single-image based 3d architecture modeling is a hot research topic. Due to the repetitions detection for the inputting urban architecture images, a novel algorithm for reconstructing 3d detailed architectures is presented for interactively generating the large number of repetitive structures in an effective and convenient manner. Our approach consists of three steps. Firstly, according to the parallel or vertical relations of sketch lines interactively drawn by the user, the coarse architectural model can be reconstructed using an energy function optimization. Upon the texture information of the inputting single image, the horizontal and vertical repetitions on each architectural face can then be detected and classified based on their bounding boxes.According to the user inputted sketch lines of typical detailed structure, the 3d information of detailed concave or convex structures can be calculated based on the projective relations between detailed structures and basic body of architecture. Finally, the other same type of repetitive structures can be reconstructed automatically and 3d detailed architectures can be generated. Experimental results show that our proposed method can conveniently and effectively reconstruct 3d detailed architectures from single image with high visual quality.

Yongwei Miao, Xiaohong Feng , Lijie Yu, Jiazhou Chen, Yong-Tsui Lee

Journal of Software , 2016, 27(10): 2557-2573. (in Chinese)

Single-Image based Interactively Progressive Modeling for 3D Architectures

Abstract: Based on the input single architecture image, a novel 3d reconstruction approach for urban architecture is presented in this paper, which can create real-world buildings in an interactively progressive manner. Upon the sketching plane defined by the input image, the users firstly mark two main faces of the target architecture for image rectification. Due to the fact that the parallel lines under perspective projection always intersect at a vanishing point, the perspective distortions can be removed and the parallel relations among sketch lines can be restored by a special projection transformation. Then, the users interactively sketch the visible primary profiles of target object on the rectified image, and the system automatically identifies different kinds of parallel or vertical relations of the sketch lines. All of these relations and co-plane properties can be regarded as the geometric constrains for calculating the z-depths of sketch lines. Owing to the property of symmetry, the coarse model can thus be generated by completing the geometric structures of architecture scene. Furthermore, by incorporating the geometrical relations between urban details and the primary structure into the z-depth computation of architectural details, a real fine 3d architecture can finally be reconstructed by synthesizing the surface texture derived from visible texture information of the input image. Experimental results show that our proposed method can conveniently and effectively reconstruct 3d architecture model from single image with high visual quality.

Yongwei Miao, Xiaohong Feng , Lijie Yu, Jiazhou Chen, Yong-Tsui Lee

Journal of Computer-Aided Design & Computer Graphics, 2016, 28(9) :1410-1419. (in Chinese)

Pattern Analysis and Digitization Modeling of Papercutting Textures

Abstract:To support efficient editing, reuse and individual design of papercutting textures, we propose a novel approach of pattern analysis and hierarchical modeling for texture patterns on papercutting works. First a vectorization process is applied to decompose the image of a papercutting work into individual texture shapes, these textures are then categorized based on their shape similarities using an improved shape context descriptor, finally the spatial distribution mode of each categorized texture pattern is identified, therefore converting the initial papercutting image into a hierarchical tree structure composed of a primitive layer, a similarity elements layer, a decorative pattern layer and a root node. Our modeling method corresponds closely to the characteristics of conventional papercutting texture including pattern repetition and modularization, and facilitates fast examination of geometric connection of the entire textures. Experiments show that our method can greatly reduce the difficulty for individual papercutting design while increase the editing efficiency.

Jiazhou Chen , Wenwen Hu, Yongwei Miao, Minyan Chen, Qunsheng Peng

Journal of Computer-Aided Design & Computer Graphics, 2016, 28(9) :1465-1475. (in Chinese)

Image Saliency Detection using Regional Covariance Analysis

Abstract: Objective: The purpose of image saliency detection is to obtain high quality saliency maps which can reflect the significance degree of different image areas. Owing to the saliency map, the visual salient regions of the input images can be processed efficiently, which are benefit to various applications, such as image segmentation, object detection and recognition, etc. Method: According to the theoretical analysis of regional covariance, the intrinsic properties of the image superpixels will be described by high-dimensional covariance matrix, and the dissimilarity degree between two image superpixels can thus be determined by the regional covariance distance. Using the regional covariance analysis, a novel method for image saliency detection is proposed. Firstly, the input image is preprocessed by super pixel segmentation. The saliency of superpixels can then be calculated using the regional covariance distance. Finally, the saliency of superpixels can be up-sampled to determine the saliency of the image pixels. Result: By combining the high-dimensional intrinsic properties of image pixels and superpixels, our approach can not only avoid the negative effect of the single noise pixels, but also improve the accuracy of saliency detection. Moreover, by using the covariance matrix of image superpixels, the final saliency map can be robust to the number of feature points, the sequence of image pixels and illumination, etc. Compared with other existing methods, our proposed scheme can obtain the accurate target saliency map with clear salient boundaries which can benefit to the application of image segmentation. Conclusion: In this paper, we test 200 images selected from THUS10000 data set for saliency analysis and compare with four different detection schemes. Experimental results show that our saliency maps are similar to the ground truth manual calibration results. Our method is also effective for estimating the saliency of the input images with complex background or with similar color between front and background. The regional covariance based image saliency map can be applied to salient object extraction and image segmentation.

Xudong Zhang, Yanyan Lyu, Yongwei Miao, Pengyi Hao, Jiazhou Chen

Journal of Image and Graphics, 2016, 21(5): 605-615. (in Chinese)

3D Model Sculpturing Technique based on Drawing Lines

Abstract: Based on the user input drawing lines, a novel sculpturing technique for 3D models is presented which can generate some complex sculptures. The clean centerlines are firstly extracted from the drawing lines by edge shrinkage operation which will be regarded as the contour lines for 3D sculpturing. Then, the given model will be parameterized by global or local parameterization scheme. The extracted contour lines will be mapped as the discrete sculptural lines on the underlying 3D models. The distances to the discrete sculptural lines are computed for each mesh vertex, and the sculpturing vertices can be selected if their distance to the discrete sculptural lines is less than a given threshold. Finally, the shift distance of these sculpturing vertices can be calculated by a specific crease profile and the 3D sculpturing result can be achieved by moving the sculpturing vertices along their normal direction. Experiment results show that our approach can generate some complex sculpture results on different 3D models in a convenient and efficient manner.

Yongwei Miao, Minyan Chen, Xudong Fang, Jiazhou Chen, Zhen Liu

Journal of Computer-Aided Design & Computer Graphics, 2016, 28(1): 50-57.(in Chinese)

SymmSketch: Creating Symmetric 3D Free-form Shapes from 2D Sketches

Abstract: This paper presents SymmSketch — a system for creating symmetric 3D free-form shapes from 2D sketches. The reconstruction task usually separates a 3D symmetric shape into two types of shape components, that is, the self-symmetric shape component and the mutual-symmetric shape components. Each type of them can be created in an intuitive manner. According to a uniform symmetry plane, the user first draws 2D sketch lines for each shape component on a sketching plane. The z-depth information of the hand-drawn input sketches can be calculated using their property of mirror symmetry to generate 3D constructive curves. In order to provide more freedom for controlling the local geometric features of the reconstructed freeform shapes (such as their cross sections will not be limited to be traditional circular), our modeling system will create each shape component from four constructive curves. With one pair of symmetric curves and one pair of general curves, an improved cross-sectional surface blending scheme is applied to generate a parametric surface for each component. The final symmetric freeform shape will be progressively created and be represented as 3D triangular mesh. Experimental results illustrate that our system can generate symmetric complex free-form shapes effectively and conveniently.

Yongwei Miao, Feixia Hu, Xudong Zhang, Jiazhou Chen, Renato Pajarola

Journal of Computational Visual Media, 2015, 1(1): 3-16.

Vectorization of Line Drawing Image based on Junction Analysis

Abstract: Converting a scanned or shot line drawing image into a vector graph can facilitate further edit and reuse, making it a hot research topic in computer animation and image processing. Besides avoiding noise influence, its main challenge is to preserve the topological structures of the original line drawings, such as line junctions, in the procedure of obtaining a smooth vector graph from a rough line drawing. In this paper, we propose a vectorization method of line drawings based on junction analysis, which retains the original structure unlike done by existing methods. We rst combine central line tracking and contour tracking, which allows us to detect the encounter of line junctions when tracing a single path. Then, a junction analysis approach based on intensity polar mapping is proposed to compute the number and orientations of junction branches. Finally, we make use of bending degrees of contour paths to compute the smoothness between adjacent branches, which allows us to obtain the topological structures corresponding to the respective ones in the input image. We also introduce a correction mechanism for line tracking based on a quadratic surface tting, which avoids accumulating errors of traditional line tracking and improves the robustness for vectorizing rough line drawings. We demonstrate the validity of our method through comparisons with existing methods, and a large amount of experiments on both professional and amateurish line drawing images.

Jiazhou Chen, Qi Lei, Yongwei Miao, Qunsheng Peng.

Science China Information Sciences, 2015, 58(7): 1-14. (SCI)

(Proceedings of Chinagraph 2014 Best Paper Award)

Roughness Based Detail-Preserving Mesh Filtering

Abstract: The design of detail-preserving filter is a hot research topic in the area of computer graphics and computer vision. Incorporating the local roughness measurement of 3d meshes into energy minimization scheme, a novel visual perceptual roughness based local detail-preserving filter is presented in this paper. Firstly, the energy function usually contains two correlative items: the smooth item and the detail-preserving item which will be balanced by the local roughness of the underlying model. Then, under the assumption that the vertices of smooth model are linear correlative with the corresponding vertices of original model, the proposed energy can be effectively minimized. The minimization of the energy will lead to the final smooth mesh. Our local detail-preserving filter can be applied to many applications, such as mesh smoothing/denoising, model layered detail enhancement, etc. Experimental results illustrate that the presented filter is effective and universal to many areas of digital geometry processing.

Xudong Zhang, Xudong Fang, Jiazhou Chen, Yongwei Miao

Journal of Computer-Aided Design & Computer Graphics, 2015, 27(12): 2323-2331. (EI) (in Chinese)

Single Image Based 3D Symmetric Free-Form Objects Reconstruction

Abstract: To create real-word objects from the 2D line drawings sketched on a single input image, a novel 3D reconstruction approach for symmetric free-form objects is presented in this paper. Upon the sketching plane defined by the input image, users first assign a symmetry plane for the reconstructed model and draw the sketch curves for each object component interactively. Each shape component can then be created from four sketch curves, that is, a pair of symmetric curves and a pair of non-symmetric general curves. The 3D depth information of the symmetric curves can be determined with respect to the symmetry plane, and the 3D coordinate information of the general curves can also be calculated due to the symmetric curves of the same shape component. According to the recovered 3D constructive curves, each object component can be generated by an improved cross-sectional surface blending scheme and be represented as a triangular mesh. Owing to the provided texture information in the input image, the free-form objects can finally be obtained by synthesizing the model texture. Experimental results illustrate that our proposed method can generate the real-world objects from a single image effectively.

Yongwei Miao, Feixia Hu, Xiaohong Feng, Xudong Zhang, Jing Fan

Journal of Computer-Aided Design & Computer Graphics, 2015, 27(9):1637-1647. (EI) (in Chinese)

Sketch-based Reconstruction of Symmetric 3D Free-form Objects

Yongwei Miao, Feixia Hu, Xudong Zhang, Jiazhou Chen, Renato Pajarola

Proceedings of ACM SIGGRAPH ASIA 2014

ShenZhen, China, December, 2014 . (Poster)

Visual salience guided feature-aware shape simplification

Abstract: In the area of 3D digital engineering and 3D digital geometry processing, shape simplification is an important task to reduce their requirement of large memory and high time complexity. By incorporating the content-aware visual salience measure of a polygonal mesh into simplification operation, a novel feature-aware shape simplification approach is presented in this paper. Owing to the robust extraction of relief heights on 3D highly detailed meshes, our visual salience measure is defined by a center-surround operator on Gaussian-weighted relief heights in a scale-dependent manner. Guided by our visual salience map, the feature-aware shape simplification algorithm can be performed by weighting the high-dimensional feature space quadric error metric of vertex pair contractions with the weight map derived from our visual salience map. The weighted quadric error metric is calculated in a six-dimensional feature space by combining the position and normal information of mesh vertices. Experimental results demonstrate that our visual salience guided shape simplification scheme can adaptively and effectively re-sample the underlying models in a feature-aware manner, which can account for the visually salient features of the complex shapes and thus yield better visual fidelity.

Yongwei Miao, Feixia Hu, Minyan Chen, Zhen Liu, Huahao Shou

Journal of Zhejiang University-SCIENCE C, 2014, 15(9):744-753. (SCI)

Sketch Lines Based Sculpturing Scheme of 3D Models

Abstract:To generate various geometric textures of complex 3D models, a novel 3D sculpturing scheme is presented in this paper. Firstly, the user defined sketch lines are refined and the edge point set that intersect with model edges are determined. The triangles that traversed by these sketch lines are deleted and new subdivided triangles on these regions are inserted to the original model. Then, for each vertex, its distance to the sketch lines is calculated efficiently. The neighboring vertices of the sketch lines can be selected if their distances are less than a given texture width. The shift distances and shift directions of these neighboring vertices can thus be computed according to a user selected crease profile. Finally, the neighboring vertices of the sketch lines are moved along their shift directions for generating the sculpturing result. Experimental results show that the proposed scheme is convenient and efficient for different 3D sculpturing operations.

Yongwei Miao,Hongjun Wang , Xudong Zhang

Journal of Computer-Aided Design & Computer Graphics, 2014, 26(2): 263-271. (EI) (in Chinese)

Mesh Stitching and Fusion Based on Hermite Interpolation Scheme

Abstract: Mesh stitching and fusion is a fundamental operation in a lot of 3D shape editing and modeling applications. For example, it always need to assemble different mechanical apparatuses together in the area of computer-aided industrial design, creating new toys from some existing ones in the area of digital entertainment and reassembling fractured archeological artifacts in the area of cultural relic protection, etc. In general, to blend two under-stitching meshes or fuse several interested sub-parts together, it is widely recognized that the transition surface connecting them should possess the following properties. The transition surface should smoothly combine the underlying meshes in a seamless natural manner for different joining boundaries, whilst the local geometric details should also be preserved as soon as possible in the vicinity of the stitching boundaries. Based on the Hermite interpolation scheme, a novel approach of mesh seamless stitching and fusion is presented in this paper, which can be adapted for blending two meshes with the arbitrary distributed boundary point sets. Firstly, their boundary point sets of two under-joining meshes are automatically selected to form the blending region. The two joining boundary curves can thus be interpolated by two quadratic B-spline curves separately. Then, the transition surface can be constructed by Hermite functional blending scheme under the geometric position and the tangential direction limitations of two boundary curves. Finally, the transition region can be created by triangulating its discretely sampled vertices and applying Laplacian smoothing to form the resultant blending mesh. Compared with the traditional mesh fusion methods, owing to interpolating the two boundary curves of two under-fusion meshes by using B-spine curves, our mesh stitching and fusion scheme can be applied to blend the underlying meshes with different types of boundary curves, that is, it is not only adaptable for the meshes with planar boundary curves but also for the meshes with spatial boundary curves. ...

Yongwei Miao, Haibin Lin, Huahao Shou

Journal of Image and Graphics, 2013, 18(12): 1055-1064. (in Chinese)

Shape Sparse Correspondence for Nearly-Isometric Meshes Base on Green's Function Representation

Abstract: Based on global point signature and Green's function representation, a coarse-to-fine sparse correspondence algorithm for nearly-isometric meshes is presented in this paper. To address the problem of undetermined signs of the corresponding basis vectors, the anchor points are extracted from the source mesh and the nearly-isometric destination mesh respectively based on the Morse theory and a modified hierarchically clustering approach. Their correspondences are then established by minimizing their GPS distances, which can be solved via a combinational searching strategy. Second, to solve the inconsistent problem of high dimensional GPS coordinates caused by different resolutions of meshes, a new Green’s function presentation of point is proposed based on the anchor point pairs obtained. As a result, the sparse representation of nearly-isometric meshes is established incrementally. Experimental results demonstrate the proposed algorithm exhibits better computational efficiency and correspondence accuracy than other shape correspondence algorithms. It can be potentially applied to rigid or non-rigid mesh alignment, 3D morphing, shape matching, etc.

Jinrong Wang, Jieqing Feng , Yongwei Miao

Journal of Computer-Aided Design & Computer Graphics, 2013, 25(5): 714-723. (EI) (in Chinese)


Salience-based Feature Preserving Resizing for 3D Models

Yongwei Miao, Haibin Lin

Proceedings of ACM SIGGRAPH ASIA 2013

HongKong, China, November, 2013 . (Poster)



3D Reconstruction of Complex Geometric Solids from 2D Line Drawings

Yongwei Miao, Haibin Lin

Proceedings of ACM SIGGRAPH ASIA 2013

HongKong, China, November, 2013 . (Poster)



Visual Saliency Guided Global and Local Resizing for 3D Models 

Abstract: In the literature of industrial designing and digital entertainment, the resizing of 3D complex models is a popular and useful operation. One of the key issues in model resizing is that some visually salient features of the underlying model should be preserved as much as possible. Based on the surface
deformation scheme, a novel visual saliency guided content-aware model resizing approach is presented in this paper. Firstly, the edge sensitivity measure is determined by edge saliency measure and slippage value. Owing to the edge sensitivity, a quadratic energy function can thus be constructed to guide salient feature-preserving model resizing. Finally, the original model can be non-homogeneously scaled according to the per-edge scales solved by iteratively minimizing the quadratic energy function. Our visual saliency guided model resizing scheme can be benefit not only for the global resizing procedure but also for the local resizing operation. The experimental results demonstrate that our proposed model resizing scheme can effectively preserve the visually salient features of the underlying model in a content-aware manner.

Yongwei Miao, Haibin Lin

 International Conference on Computer-Aided Design and Computer Graphics (CAD/Graphics 2013)

HongKong, China, November, 2013.

Feature Sensitive Re-sampling of Point Set Surface with Gaussian Spheres

Abstract: Feature sensitive simplification and re-sampling of point set surfaces is an important and challenging issue for many computer graphics and geometric modeling applications. Based on the regular sampling of the Gaussian sphere and the surface normals mapping onto the Gaussian sphere, an adaptive re-sampling framework for point set surfaces is presented in this paper, which includes a naive sampling step by index propagation and a novel cluster optimization step by normalized rectification. Our proposed re-sampling scheme can generate non-uniformly distributed discrete sample points for the underlying point sets in a feature sensitive manner. The intrinsic geometric features of the underlying point set surfaces can be preserved efficiently due to our adaptive re-sampling scheme. A novel splat rendering technique is adopted to illustrate the efficiency of our re-sampling scheme. Moreover, a numerical error statistics and surface reconstruction for simplified models are also given to demonstrate the effectiveness of our algorithm in term of the simplified quality of the point set surfaces.

Yongwei Miao,Jonas Bosch, Renato Pajarola, M.Gopi, Jieqing Feng

Science China Information Sciences, 2012, 55(9): 2075–2089. (SCI)


A Multi-Channel Salience Based Detail Exaggeration Technique for 3D Relief Surfaces

Abstract: Visual saliency can always persuade the viewer's visual attention to fine-scale mesostructure of 3D complex shapes. Owing to the multi-channel salience measure and salience-domain shape modeling technique, a novel visual saliency based shape depiction scheme is presented to exaggerate salient geometric details of the underlying relief surface. Our multi-channel salience measure is calculated by combining three feature maps, i.e., the 0-order feature map of local height distribution, the 1-order feature map of normal difference, and the 2-order feature map of mean curvature variation. The original relief surface is firrstly manipulated by a salience-domain enhancement function, and the detail exaggeration surface can then be obtained by adjusting the surface normals of the original surface as the corresponding final normals of the manipulated surface. The advantage of our detail exaggeration technique is that it can adaptively alter the shading of the original shape to reveal visually salient features whilst keeping the desired appearance unimpaired. The experimental results demonstrate that our non-photorealistic shading scheme can enhance the surface mesostructure effectively and thus improving the shape depiction of the relief surfaces.

Yongwei Miao, Jieqing Feng, Jinrong Wang, Renato Pajarola

Journal of Computer Science and Technology, 2012, 27(6): 1100–1109. (SCI) 


A Robust Confirmable Watermarking Algorithm for 3D Mesh based on Manifold Harmonics Analysis

Abstract: Owing to the manifold harmonics analysis, a?robust non-blind spectral watermarking algorithm for a two-manifold mesh is presented, which can be confirmed by a?trusted third party. Derived from the Laplace-Beltrami operator, a set of orthogonal manifold harmonics basis functions is first adopted to span the spectral space of the underlying three-dimensional (3D) mesh. The minimal number of the basis functions required in the proposed algorithm is also determined, which can effectively accelerate the spectrum computations. Then, to assert ownership and resist 3D mesh forging, a?digital signature algorithm is adopted to sign the watermark in the embedding phase and to verify the signature in the extraction phase, which could optimize the robust non-blind spectral watermarking algorithm framework. To improve the robustness of the embedded watermark signature, the input 3D mesh will be segmented into patches. The watermark signature bits are embedded into the low-frequency spectral coefficients of all patches repeatedly and extracted with regard to the corresponding variations of their coefficients. Extensive experimental results demonstrate the efficiency, invisibility, and robustness of the proposed algorithm. Compared with existing watermarking algorithms, our algorithm exhibits better visual quality and is more robust to resist various geometric and connectivity attacks.

Jinrong Wang,Jieqing Feng, Yongwei Miao

The Visual Computer, 2012, 28(11):1049-1062 . (SCI)


Visual Saliency Guided Normal Enhancement Technique for 3D Shape Depiction

Abstract: Visual saliency can Visual saliency can effectively guide the viewer’s visual attention to salient regions of a 3D shape. Incorporating the visual saliency measure of a polygonal mesh into the normal enhancement operation, a novel saliency guided shading scheme for shape depiction is developed in this paper. Due to the visual saliency measure of the 3D shape, our approach will adjust the illumination and shading to enhance the geometric salient features of the underlying model by dynamically perturbing the surface normals. The experimental results demonstrate that our non-photorealistic shading scheme can enhance the depiction of the underlying shape and the visual perception of its salient features for expressive rendering. Compared with previous normal enhancement techniques, our approach can effectively convey surface details to improve shape depiction without impairing the desired appearance.

Yongwei Miao, Jieqing Feng, Renato Pajarola

Computers & Graphics, 2011, 35(3): 706–712. (SCI, EI)  


Best Viewpoint Selection Driven by Relief Saliency Entropy

Abstract: To automatically select the best viewpoint of 3D models, a novel relief saliency entropy driven view descriptor is presented, which is defined by incorporating the relief saliency measure of complex models into the entropy analysis of viewpoint mutual information. The saliency information entropy driven view descriptor is calculated for each pre-sampled viewpoint on the viewing sphere bounding the underlying 3D object. The viewpoint of the highest value of view descriptor is the one that defines the best view. The experimental results demonstrate that the best views selected by our proposed approach can always show the visually salient features of the underlying models.

Yongwei Miao, Hongjun Wang, Huahao Shou

Journal of Computer-Aided Design & Computer Graphics, 2011, 23(12): 2033-2039. (EI) (in Chinese)

Saliency-domain Shape Manipulation for 3D Models

Abstract: Owing to the perceptual-saliency measure and saliency-domain shape modeling techniques, a novel shape manipulation scheme is presented to adjust the visually salient features of 3d models. The perceptual-saliency measure of the 3d models is firstly introduced, which is defined by a center-surround bilateral filter operator on Gaussian-weighted average of local projection height between mesh vertices and their neighbors. The geometric features of the underlying shapes can then be filtered by low-pass, high-pass and enhancement due to the user specified shape manipulation functions defined on the saliency-domain, that is, the low-pass shape manipulation, the high-pass shape manipulation and the enhancement shape manipulation. The experimental results have shown that our proposed technique is easy and efficient to achieve different shape modeling results.

Yongwei Miao, Ruifeng Han, Jinrong Wang, Ronghua Liang

Journal of Image and Graphics, 2011, 16(10): 1926-1936. (in Chinese)

 Perceptual-saliency Extremum Lines for 3D Shape Illustration

Abstract: Owing to its efficiency for conveying perceptual information of the underlying shape and its pleasing perceive in visual aesthetics experience, line drawings are now becoming a widely used technique for illustrating 3D shapes. Using a center-surround bilateral filter operator on Gaussian weighted average of local projection height between mesh vertices and their neighbors, a new perceptual-saliency measure is proposed in this paper, which can depicting surface salient features. Due to the definition of perceptual-saliency measure, our perceptual-saliency extremum lines can be considered as the ridge-valley lines of perceptual-saliency measure along the principal curvature directions on triangular meshes. The experimental results demonstrate that these extremum lines effectively capture and depict 3D shape information visually, especially for archaeological artifacts.

Yongwei Miao, Jieqing Feng

The Visual Computer, 2010, 26(6-8): 433-443. (SCI)  


 Curvature-aware Adaptive Resampling for Point-Sampled Geometry

Abstract: With the emergence of large-scale point-sampled geometry acquired by high-resolution 3D scanning devices, it has become increasingly important to develop efficient algorithms for processing such models which have abundant geometric details and complex topology in general. As a preprocessing step, surface simplification is important and necessary for the subsequent operations and geometric processing. Owing to adaptive mean-shift clustering scheme, a curvature-aware adaptive re-sampling method is proposed for point-sampled geometry simplification. The generated sampling points are non-uniformly distributed and can account for the local geometric feature in a curvature aware manner, i.e., in the simplified model, the sampling points are dense in the high curvature regions, and sparse in the low curvature regions. The proposed method has been implemented and demonstrated on several examples.

Yongwei Miao, Renato Pajarola, Jieqing Feng

Computer-Aided Design, 41(6): 395-403, 2009. (SCI, EI)



 Shape Isophotic Error Metric Controllable Re-Sampling for Point-sampled Surfaces

Abstract: Shape simplification and re-sampling of underlying point-sampled surfaces under userdefined error bounds is an important and challenging issue. Based on the regular triangulation of the Gaussian sphere and the surface normals mapping onto the Gaussian sphere, a Gaussian sphere based re-sampling scheme is presented that generates a non-uniformly curvature-aware simplification of the given point-sampled model. Owing to the theoretical analysis of shape isophotic error metric for did that Gaussian sphere based sampling, the proposed simplification scheme provides a convenient way to control the re-sampling results under a user-specified error metric bound. The novel algorithm has been implemented and demonstrated on several examples.

Yongwei Miao, Pablo Diaz-Gutierrez, Renato Pajarola, M. Gopi, Jieqing Feng

 IEEE International Conference on Shape Modeling and Applications (SMI)

Beijing, June, 2009, pp.28-35. (EI, ISTP)  


High Frequency Geometric Detail Manipulation and Editing for Point-Sampled Surfaces

Abstract: In this paper, based on the new definition of high frequency geometric detail for point-sampled surfaces, a new approach for detail manipulation and a detail-preserving editing framework are proposed. Geometric detail scaling and enhancement can always produce fantastic effects by directly manipulating the geometric details of the underlying geometry. Detail preserving editing is capable of preserving geometric details during the shape deformation of point sampled model. For efficient editing, the point set of the model is first clustered by a mean shift scheme, according to its anisotropic geometric features and each cluster is abstracted as a simplification sample point (SSP). Our editing operation is implemented by manipulating the SSP first and then diffusing the deformation to all sample points on the underlying geometry. As a post processing step, a new up-sampling and relaxation procedure is proposed to refine the deformed model. The effectiveness of the proposed method is demonstrated by several examples. 

Yongwei Miao, Jieqing Feng, Chunxia Xiao, Qunsheng Peng

The Visual Computer, 2008, 24(2): 125-138. (SCI, EI)  


Differentials-based Segmentation and Parameterization for Point-Sampled Surfaces

Abstract: Efficient parameterization of point-sampled surfaces is a fundamental problem in the field of digital geometry processing. In order to parameterize a given point-sampled surface for minimal distance distortion, a differentials-based segmentation and parameterization approach is proposed in this paper. Our approach partitions the point-sampled geometry based on two criteria: variation of Euclidean distance between sample points, and angular difference between surface differential directions. According to the analysis of normal curvatures for some specified directions, a new projection approach is adopted to estimate the local surface differentials. Then a k-means clustering (k-MC) algorithm is used for partitioning the model into a set of charts based on the estimated local surface attributes. Finally, each chart is parameterized with a statistical method ---multidimensional scaling (MDS) approach, and the parameterization results of all charts form an atlas for compact storage.

Yongwei Miao, Jieqing Feng, Chunxia Xiao, Qunsheng Peng, A.R.Forrest

Journal of Computer Science and Technology, 22(5): 749-760, 2007. (SCI, EI)


A Dynamic Balanced Flow for Filtering Point-sampled Geometry

Abstract: 3D point data acquisition has now become a practical approach for generating complex 3D shape. Subsequent smoothing or denoising operations on these raw data sets are then required before performing sophisticated modeling operations. Based on the covariance analysis and the constructed directional curvature, a new approach of anisotropic curvature flow is developed for filtering the point data set. By introducing a forcing term, a balanced flow equation is constructed that allows the anisotropic diffusion flow to be restricted in the flow diffusion band of the original surface. Thus the common problem of shape shrinkage which puzzles most current denoising approaches for point-sampled geometry is avoided. Applying dynamic balance techniques, the equation converges to the solution quickly with appealing physical interpretations. The algorithms operate directly on the discrete sample points, requiring no vertex connectivity information. They are shown computationally efficient, robust with simplicity in implementation.

Chunxia Xiao, Yongwei Miao, Shu Liu, Qunsheng Peng

The Visual Computer, 2006, 22(3): 210-219. (SCI, EI)


A Unified Method for Appearance and Geometry Completion of Point Set Surfaces

Abstract: This paper presents a novel approach for appearance and geometry completion over point-sampled geometry. Based on the result of surface clustering and a given texture sample, we define a global texture energy function on the point set surface for direct texture synthesis. The color texture completion is performed by minimizing a constrained global energy using the existing surface texture on the surface as the input texture sample. We convert the problem of context-based geometry completion into a task of texture completion on the surface. The geometric detail is then peeled and converted into a piece of signed gray-scale texture on the base surface of the point set surface. We fill the holes on the base surface by smoothed extrapolation and the geometric details over these patches are reconstructed by a process of gray-scale texture completion. Experiments show that our method is flexible, efficient and easy to implement. It provides a practical texture synthesis and geometry completion tool for 3D point set surfaces.

Chunxia Xiao, Wenting Zheng, Yongwei Miao, Yong Zhao, Qunsheng Peng

The Visual Computer, 2007, 23(6): 433-443. (SCI, EI)


 Detail-Preserving Local Editing for Point-Sampled Geometry

Abstract: In digital geometry processing, it is important to preserve the local intrinsic properties of 3D models in geometry editing operations. One of such intrinsic properties can be described as geometric details. For point-sampled geometry, a new Normal Geometric Details (NGDs) based on an implicit surface fitting is proposed, which is invariant under rigid transformations. Combining the normal geometric details and the Position Geometric Details (PGDs), a useful interactive local geometry editing method is developed. The method deforms the sample points in a region of interest by manipulating handle points. To satisfy the anisotropic property of geometric details for point-sampled geometry, a 3D mean shift procedure is adopted to determine the neighbor points adaptively. In the preprocessing step, a non-local denoising algorithm is applied to smooth the input noisy point-sampled model, which is based on a global weight average scheme of all sample points. As a postprocessing step, a new up-sampling and relaxation procedure is proposed to refine the deformed model. The effectiveness of the proposed method is demonstrated by examples, i.e., the editing operation can deform the model while respecting the intrinsic geometric details.

Yongwei Miao, Jieqing Feng, Chunxia Xiao, Hui Li, Qunsheng Peng

 Proceedings of Computer Graphics International (CGI2006)

Hangzhou, June, 2006, T. Nishita, Q. Peng, H.-P. Seidel (Eds.): Lecture Notes in Computer Science 4035, pp. 673-681. (SCI, EI)   



 Curvature estimation of point-sampled surfaces and its applications

Abstract: In this paper, we propose a new approach to estimate curvature information of point-sampled surfaces. We estimate curvatures in terms of the extremal points of a one-dimensional energy function for discrete surfels (points equipped with normals) and a multi-dimensional energy function for discrete unstructured point clouds. Experimental results indicate that our approaches can estimate curvatures faithfully, and reflect the subtle curvature variations. Some applications for curvature information, such as surface simplification and feature extraction for point-sampled surfaces, are given.

Yongwei Miao, Jieqing Feng, Qunsheng Peng

Workshop of Computer Graphics and Geometric Modeling

Singapore, May, 2005, O. Gervasi et al. (Eds.): Lecture Notes in Computer Science 3482, 2005, pp. 1023-1032. (SCI, EI)



 Bezier Surface of Minimal Internal Energy

Abstract: In this paper the variational problems of finding Bezier surfaces that minimize the bending energy functional with prescribed border for both cases of triangular and rectangular are investigated. As a result, two new bending energy masks for finding Bezier surfaces of minimal bending energy for both triangular and rectangular cases are proposed. Experimental comparisons of these two new bending energy masks with existing Dirichlet, Laplacian, harmonic and average masks are performed which show that bending energy masks are among the best.

Yongwei Miao, Huahao Shou, Jieqing Feng, Qunsheng Peng, A.R.Forrest

Conference of Mathematics of Surfaces XI

England, September, 2005, R. Martin, H. Bez, M. Sabin (Eds.): Lecture Notes in Computer Science, 3604, pp. 318-335. (EI)