Pose normalization of 3D models via reflective symmetry on panoramic views

A novel pose normalization method, based on reflective symmetry computed on panoramic views, is presented. Qualitative and experimental investigation in 3D data-sets has led us to the observation that most objects possess a single plane of symmetry. Our approach is thus guided by this observation. Initially, through an iterative procedure, the symmetry plane of a 3D model is estimated, thus computing the first axis of the model. This is achieved by rotating the 3D model and computing reflective symmetry scores on panoramic view images. The other principal axes of the 3D model are estimated by computing the variance of the 3D model’s panoramic views. The proposed method is incorporated in a hybrid scheme, that serves as the pose normalization method in a state-of-the-art 3D object retrieval system. The effectiveness of this system, using the hybrid pose normalization scheme, is evaluated in terms of retrieval accuracy and the results clearly show improved performance against current approaches.     

Surface deformation models for nonrigid 3D shape recovery

Three-dimensional detection and shape recovery of a nonrigid surface from video sequences require deformation models to effectively take advantage of potentially noisy image data. Here, we introduce an approach to creating such models for deformable 3D surfaces. We exploit the fact that the shape of an inextensible triangulated mesh can be parameterized in terms of a small subset of the angles between its facets. We use this set of angles to create a representative set of potential shapes, which we feed to a simple dimensionality reduction technique to produce low-dimensional 3D deformation models. We show that these models can be used to accurately model a wide range of deforming 3D surfaces from video sequences acquired under realistic conditions.     

Retrieving articulated 3-D models using medial surfaces

We consider the use of medial surfaces to represent symmetries of 3-D objects. This allows for a qualitative abstraction based on a directed acyclic graph of components and also a degree of invariance to a variety of transformations including the articulation of parts. We demonstrate the use of this representation for 3-D object model retrieval. Our formulation uses the geometric information associated with each node along with an eigenvalue labeling of the adjacency matrix of the subgraph rooted at that node. We present comparative retrieval results against the techniques of shape distributions (Osada et al.) and harmonic spheres (Kazhdan et al.) on 425 models from the McGill Shape Benchmark, representing 19 object classes. For objects with articulating parts, the precision vs recall curves using our method are consistently above and to the right of those of the other two techniques, demonstrating superior retrieval performance. For objects that are rigid, our method gives results that compare favorably with these methods. A preliminary version of this article was published in EMMCVPR 2005. In this extended version we have included results on the significantly larger McGill Shape Benchmark, making a stronger case for the advantages of our method for models with articulating parts. We have also included expanded introduction, medial surface computation, matching, indexing, experimental results, and discussion sections, along with several new figures.     

Robust algorithm for tunnel closing in 3D volumetric objects based on topological characteristics of points

In this letter, we propose a robust, linear in time modification of Aktouf, Bertrand and Perroton’s algorithm for tunnel (3D hole) closing in 3D volumetric objects. Our algorithm is insensitive to small distortions and branches. The algorithm has been tested on various 3D images including very complicated 3D crack propagation images. The results of the tests, discussion of the algorithm properties and future research plans are also included in the paper.     

Automatic construction of 2D shape models

A procedure for automated 2D shape model design is presented. The system is given a set of training example shapes defined by contour point coordinates. The shapes are automatically aligned using Procrustes analysis and clustered to obtain cluster prototypes (typical objects) and statistical information about intracluster shape variation. One difference from previous methods is that the training set is first automatically clustered and shapes considered to be outliers are discarded. In this way, cluster prototypes are not distorted by outliers. A second difference is in the manner in which registered sets of points are extracted from each shape contour. We propose a flexible point matching technique that takes into account both pose/scale differences and nonlinear shape differences. The matching method is independent of the objects' initial relative position/scale and does not require any manually tuned parameters. Our shape model design method was used to learn 11 different shapes from contours that were manually traced in MR brain images. The resulting model was then employed to segment several MR brain images that were not included in the shape-training set. A quantitative analysis of our shape registration approach, within the main cluster of each structure, demonstrated results that compare very well to those achieved by manual registration; achieving an average registration error of about 1 pixel. Our approach can serve as a fully automated substitute to the tedious and time-consuming manual 2D shape registration and analysis     

3D anatomical shape atlas construction using mesh quality preserved deformable models

3D anatomical shape atlas construction has been extensively studied in medical image analysis research, owing to its importance in model-based image segmentation, longitudinal studies and populational statistical analysis, etc. Among multiple steps of 3D shape atlas construction, establishing anatomical correspondences across subjects, i.e., surface registration, is probably the most critical but challenging one. Adaptive focus deformable model (AFDM) [1] was proposed to tackle this problem by exploiting cross-scale geometry characteristics of 3D anatomy surfaces. Although the effectiveness of AFDM has been proved in various studies, its performance is highly dependent on the quality of 3D surface meshes, which often degrades along with the iterations of deformable surface registration (the process of correspondence matching). In this paper, we propose a new framework for 3D anatomical shape atlas construction. Our method aims to robustly establish correspondences across different subjects and simultaneously generate high-quality surface meshes without removing shape details. Mathematically, a new energy term is embedded into the original energy function of AFDM to preserve surface mesh qualities during deformable surface matching. More specifically, we employ the Laplacian representation to encode shape details and smoothness constraints. An expectation–maximization style algorithm is designed to optimize multiple energy terms alternatively until convergence. We demonstrate the performance of our method via a set of diverse applications, including a population of sparse cardiac MRI slices with 2D labels, 3D high resolution CT cardiac images and rodent brain MRIs with multiple structures. The constructed shape atlases exhibit good mesh qualities and preserve fine shape details. The constructed shape atlases can further benefit other research topics such as segmentation and statistical analysis.     

Hole filling in 3D volumetric objects

The construction of hole filling (or hole segmentation) method for 3D volumetric images is a new challenging issue in computer science. It needs a geometrical approach since from a topological point of view 3D holes (tunnels) are not well-delimited subsets of three dimensional space. In this paper, the authors propose an original, efficient, flexible algorithm of hole filling for volumetric objects. The algorithm has been tested on artificial objects and very complicated crack propagation tomography images. The qualitative results, quantitative results and features of proposed approach are presented in the paper. According to our knowledge it is the first algorithm of hole filling for volumetric objects.     

Customizing 3D garments based on volumetric deformation

Improving the reusability of design results is very important for garment design industry, since designing an elegant garment is usually labor-intensive and time-consuming. In this paper, we present a new approach for customizing 3D garment models. Our approach can transfer garment models initially dressed on a reference human model onto a target human model. To achieve this goal, firstly a spatial mapping between the two human models is established with the shape constraints of cross-sections. Secondly, the space around the clothed reference human model is tetrahedralized into five tetrahedral meshes each of which either can be worked dependently with its adjacent ones or can be worked independently. The clothed reference human model is parametrically encoded in the tetrahedral meshes. Thirdly, these tetrahedral meshes are deformed by fitting the reference human model onto the target human model by using constrained volumetric graph Laplacian deformation. The updated garment models are finally decoded from the deformed tetrahedral meshes. As a result, the updated garment models are fitted onto the target human model. Experiments show that our approach performs very well and has the potential to be used in the garment design industry.     

3D pose estimation for articulated vehicles using Kalman-filter based tracking

Knowledge about relative poses within a tractor/trailer combination is a vital prerequisite for kinematic modelling and trajectory estimation. In case of autonomous vehicles or driver assistance systems, for example, the monitoring of an attached passive trailer is crucial for operational safety. We propose a camerabased 3D pose estimation system based on a Kalman-filter. It is evaluated against previously published methods for the same problem.     

Robust3D: a robust 3D face reconstruction application

In the process of reconstructing a historical event such as a rock concert only from video, the reconstruction of faces and expressions of the musicians is obviously important. However, in the process of rebuilding appearance, because of the low quality of the video of the recorded concert, the result of the reconstruction may be far from the real appearance. In this paper, a robust 3D face reconstruction application is described that can be applied to a video recording. The application first uses DeblurGAN program to run anti-ambiguity calculation and removes the ambiguity in the concert video. Then, the super-resolution program is used to enlarge every frame of the concert video by four times, thus making every frame of the video clearer. Finally, the 3D faces are obtained after 3D reconstruction of the processed video frames via the 3DMM_CNN program.

     

Bayesian 3D shape from silhouettes

This paper introduces a smooth posterior density function for inferring shapes from silhouettes. Both the likelihood and the prior are modelled using kernel density functions and optimisation is performed using gradient ascent algorithms. Adding a prior allows for the recovery of concave areas of the shape that are usually lost when estimating the visual hull. This framework is also extended to use colour information when it is available in addition to the silhouettes. In these cases, the modelling not only allows for the shape to be recovered but also its colour information. Our new algorithms are assessed by reconstructing 2D shapes from 1D silhouettes and 3D faces from 2D silhouettes. Experimental results show that using the prior can assist in reconstructing concave areas and also illustrate the benefits of using colour information even when only small numbers of silhouettes are available.     

Inverse lagrangian dynamics for animating articulated models

This paper presents the application of inverse Lagrangian dynamics for the purpose of animating articulated models. The method orginates from mechanics and robotics and has been adapted to deal with branched kinematic chains and joints with multiple degrees of freedom. The method is then reformulated to calculate the ground reaction forces that apply to the body. The approach is direct and does not involve guesswork. The formulation has been implemented into a general animation system that is entirely interactive and supports the facility of simulating generic articulated models.     

Multiresolution volumetric 3D object reconstruction for collaborative interactions

Within the framework of collaborative interactions with 3D numerical copies of real objects inserted in virtual environments, this paper tackles the issue of 3D object reconstruction from multiple calibrated cameras. After examining the various constraints related to collaborative systems, we propose comprehensive, state of the art 3D reconstruction techniques. The main families of approaches are here identified, described, and discussed in detail. An analysis of the literature shows that there is a lack of methods that are able to respond to the needs of the collaborative interaction applications, and that perform adequately in terms of computation time and reconstruction accuracy. Accordingly, we propose a new multiresolution volumetric approach that is able to obtain numerical copies of real objects at multiple resolutions. Experimental results demonstrate that the proposed approach provides accurate reconstructions at reasonable, interactive computation times. The use of the proposed approach for progressive insertion of reconstructed objects in the prototype interfaces MOWGLI and Spin-3D developed by FranceTelecom R&D is also illustrated. The text was submitted by the authors in English. Rachid Guerchouche. Was born in Algeria in 1979. He received an Engineer Degree in electronics from the National Polytechnic School of Algiers, Algeria in June 2004, and a research Masters Degree in Virtual Reality and Complex Systems Engineering from Université Evry-Val d’Essonne (France) in June 2005. He is currently a PhD student jointly in the ARTEMIS Department at TELECOM & Management SudParis and in the VIA Project Unit of the IRIS Laboratory at France Télécom R&D. Olivier Bernier. Was born in 1964. He received the diploma of the Ecole Polytech-nique (Palaiseau, France) in 1986 and the diploma of the Ecole Nationale Supérieure des Télécommunications (Paris, France) in 1988. Since this date, he has worked as a Research Engineer at Orange Labs-FT R&D, the research center of France Telecom. His areas of interest are computer vision, statistical learning and pattern recognition, in particular applied to advanced human machine interfaces. Titus Zaharia. Received an Engineer Degree in Electronics and the Masters Degree in Electronics from University POLITEHNICA (Bucharest, Romania) in 1995 and 1996, respectively. In 2001, he obtained a PhD degree in Mathematics and Computer Science from University Paris V—René Descartes (Paris, France). He then joined the ARTEMIS Department at TELECOM & Management SudParis as a research engineer, and became an Associate Professor in 2002. His research interests concern visual content indexing and coding, and include feature extraction, image and video segmentation, motion detection and estimation, 2D/3D reconstruction, virtual character modelling and animation, virtual/augmented reality, digital interactive TV, calibration techniques, and color image processing. Titus Zaharia is a member of SPIE.     

Alignment of 3D models

In this paper we present a new method for alignment of 3D models. This approach is based on two types of symmetries of the models: the reflective symmetry and the local translational symmetry along a direction. Inspired by the work on the principal component analysis (PCA), we select the best optimal alignment axes within the PCA-axes, the plane reflection symmetry being used as a selection criterion. This pre-processing transforms the alignment problem into an indexing scheme based on the number of the retained PCA-axes. In order to capture the local translational symmetry of a shape along a direction, we introduce a new measure we call the local translational invariance cost (LTIC). The mirror planes of a model are also used to reduce the number of candidate coordinate frames when looking for the one which corresponds to the user’s perception. Experimental results show that the proposed method finds the rotation that best aligns a 3D mesh.