Results 1 - 10
of
14
Progressive surface reconstruction from images using a local prior
- In ICCV
, 2005
"... 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. A progressive refinement scheme is used to ..."
Abstract
-
Cited by 11 (2 self)
- Add to MetaCart
(Show Context)
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. A progressive refinement scheme is used to recover the topology and reason the visibility of the object. Within each voxel, a detailed surface patch is optimally reconstructed using a graph-cut method. The advantage of this technique is its ability to handle complex shape similarly to level sets while enjoying a higher precision. Compared to carving techniques, the addressed problem is well-posed, and the produced surface does not suffer from aliasing. In addition, our approach seamlessly handles complete and partial reconstructions: If the scene is only partially visible, the process naturally produces an open surface; otherwise, if the scene is fully visible, it creates a complete shape. These properties are demonstrated on real image sequences.
A.: Visibility constrained surface evolution
- In: Computer Vision and Pattern Recognition 2005
, 2005
"... The problem of feature-based surface reconstruction is considered in this paper. Our main contribution is the ability to handle visibility constraints, obtained from the projections of points, curves and silhouettes, in the surface fitting process. While traditional methods often ignore such informa ..."
Abstract
-
Cited by 7 (1 self)
- Add to MetaCart
(Show Context)
The problem of feature-based surface reconstruction is considered in this paper. Our main contribution is the ability to handle visibility constraints, obtained from the projections of points, curves and silhouettes, in the surface fitting process. While traditional methods often ignore such information, we show that visibility constraints not only give better initial surface estimates and faster convergence, but also provide an important cue for determining surface topology. The problem is cast as a variational problem with constraints within the level set framework. It is shown how to evolve the surface without violating the visibility constraints using methods from variational calculus. Applications of the theory are detailed for a number of important cases of geometric primitives: points, curves and visual hulls. Several experiments on real image sequences are given to demonstrate the performance of the approach. 1.
Surface reconstruction from the projection of points, curves and contours
- In 2nd Int. Symposium on 3D Data Processing, Visualization and Transmission
, 2004
"... In this paper the problem of building and reconstructing geometrical surface models from multiple calibrated images is considered. We build an appropriate statistical 3D model from the images alone and show how this a priori model can be used to automatically reconstruct new instances of the object ..."
Abstract
-
Cited by 6 (4 self)
- Add to MetaCart
(Show Context)
In this paper the problem of building and reconstructing geometrical surface models from multiple calibrated images is considered. We build an appropriate statistical 3D model from the images alone and show how this a priori model can be used to automatically reconstruct new instances of the object category from one or several images. The surface reconstruction method is based on a level set representation and one of the main novel contributions lie within the level set framework. Standard methods use either image-correlation or point correspondences to achieve this goal. We show how this framework can be extended to incorporate image curves and apparent contours (i.e. the projections of silhouettes). In order to automatically obtain feature correspondences, we use a statistical shape model for the object category of interest. The model is based on the Active Shape Model using Probabilistic PCA. The scheme is applied to build and automatically reconstruct 3D surface models of faces. The resulting system is demonstrated on a database of real face images. 1.
Methodological and Applied Contributions to the Deformable Models Framework
, 2005
"... Deformable models constitute a flexible framework to address various shape reconstruction problems in image processing. They have been initially proposed for the purpose of image segmentation, but they have also proven successful in many other contexts in computer vision and in medical imaging, incl ..."
Abstract
-
Cited by 3 (0 self)
- Add to MetaCart
Deformable models constitute a flexible framework to address various shape reconstruction problems in image processing. They have been initially proposed for the purpose of image segmentation, but they have also proven successful in many other contexts in computer vision and in medical imaging, including region tracking, stereovision, shape from shading and shape from unstructured point sets. The key elements of this framework are the design of an energy functional, the choice of a minimization procedure and of a geometric representation. In this
Surface reconstruction using learned shape models
- In Advances in Neural Information Processing Systems 17. Lawrence K. Saul, Yair Weiss, and Léon Bottou, (Eds
"... We consider the problem of geometrical surface reconstruction from one or several images using learned shape models. While humans can effortlessly retrieve 3D shape information, this inverse problem has turned out to be difficult to perform automatically. We introduce a framework based on level set ..."
Abstract
-
Cited by 3 (0 self)
- Add to MetaCart
(Show Context)
We consider the problem of geometrical surface reconstruction from one or several images using learned shape models. While humans can effortlessly retrieve 3D shape information, this inverse problem has turned out to be difficult to perform automatically. We introduce a framework based on level set surface reconstruction and shape models for achieving this goal. Through this merging, we obtain an efficient and robust method for reconstructing surfaces of an object category of interest. The shape model includes surface cues such as point, curve and silhouette features. Based on ideas from Active Shape Models, we show how both the geometry and the appearance of these features can be modelled consistently in a multi-view context. The complete surface is obtained by evolving a level set driven by a PDE, which tries to fit the surface to the inferred 3D features. In addition, an a priori 3D surface model is used to regularize the solution, in particular, where surface features are sparse. Experiments are demonstrated on a database of real face images. 1
A multi-scale Tikhonov regularization scheme for implicit surface modelling
- In Proc. of Conference on Computer Vision and Pattern Recognition (CVPR). IEEE
, 2007
"... Kernel machines have recently been considered as a promising solution for implicit surface modelling. A key challenge of machine learning solutions is how to fit implicit shape models from large-scale sets of point cloud samples efficiently. In this paper, we propose a fast solution for approximatin ..."
Abstract
-
Cited by 3 (0 self)
- Add to MetaCart
(Show Context)
Kernel machines have recently been considered as a promising solution for implicit surface modelling. A key challenge of machine learning solutions is how to fit implicit shape models from large-scale sets of point cloud samples efficiently. In this paper, we propose a fast solution for approximating implicit surfaces based on a multi-scale Tikhonov regularization scheme. The optimization of our scheme is formulated into a sparse linear equation system, which can be efficiently solved by factorization methods. Different from traditional approaches, our scheme does not employ auxiliary off-surface points, which not only saves the computational cost but also avoids the problem of injected noise. To further speedup our solution, we present a multi-scale surface fitting algorithm of coarse to fine modelling. We conduct comprehensive experiments to evaluate the performance of our solution on a number of datasets of different scales. The promising results show that our suggested scheme is considerably more efficient than the stateof-the-art approach. 1.
1001 Acquisition Viewpoints – Efficient and Versatile View- Dependent Modeling of Real-World Scenes
"... path with 3,684 viewpoints ..."
(Show Context)
Visibility Constrained Surface Evolution
"... The problem of feature-based surface reconstruction is con-sidered in this paper. Our main contribution is the ability to handle visibility constraints, obtained from the projections of points, curves and silhouettes, in the surface fitting pro-cess. While traditional methods often ignore such infor ..."
Abstract
- Add to MetaCart
(Show Context)
The problem of feature-based surface reconstruction is con-sidered in this paper. Our main contribution is the ability to handle visibility constraints, obtained from the projections of points, curves and silhouettes, in the surface fitting pro-cess. While traditional methods often ignore such informa-tion, we show that visibility constraints not only give better initial surface estimates and faster convergence, but also provide an important cue for determining surface topology. The problem is cast as a variational problem with con-straints within the level set framework. It is shown how to evolve the surface without violating the visibility constraints using methods from variational calculus. Applications of the theory are detailed for a number of important cases of geometric primitives: points, curves and visual hulls. Several experiments on real image sequences are given to demonstrate the performance of the approach. 1.
Interactive Photorealistic Inside-Looking-Out Automated 3-D Modeling
"... Digital 3-D models of real world scenes are important in many applications in defense and beyond. Constructing 3-D models that faithfully capture the complexity of the real world is a difficult problem. A promising approach is automated 3-D modeling based on directly recording the geometry and color ..."
Abstract
- Add to MetaCart
Digital 3-D models of real world scenes are important in many applications in defense and beyond. Constructing 3-D models that faithfully capture the complexity of the real world is a difficult problem. A promising approach is automated 3-D modeling based on directly recording the geometry and color of the scene. Current systems suffer of important disadvantages such as inadequate scene coverage due to slow acquisition, lack of immediate feedback on the quality of the acquired 3-D model, restriction to small scenes, and unintuitive operation. In this paper we give an overview of the ModelCamera automated indoor 3-D modeling project at Purdue University, and we present novel research results and their implementation. The ModelCamera is designed to handle the challenging “inside-looking-out ” 3-D modeling case of large, room-sized scenes. The system is interactive, it provides immediate feedback to the operator, it is efficient, and the resulting 3-D model supports rendering the 3-D scene photorealistically at interactive rates, as needed by applications such as virtual training. ABOUT THE AUTHORS Voicu Popescu is an associate professor of computer science at Purdue University. His research interests
