Surface reconstruction using deformable models with interior and boundary constraints

Wang, Y.F.; Wang, J.-F.

doi:10.1109/34.134061

Cited by 37 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As with the methods employing 2k-dimensional representations, those employing 3-D representations have used a variety of single image cues for reconstruction, such as silhouettes and image features [3,24,25,27], range data [28], stereo [9], and motion [20]. Liedtke [14] first uses silhouettes to derive an initial estimate of the surface, and then uses a multi-image stereo algorithm to improve on the result.…”

Section: Related Work and Contributionsmentioning

confidence: 99%

<title>Combining stereo, shading, and geometric constraints for surface reconstruction from multiple views</title>

Fua

Leclerc

1993

SPIE Proceedings

View full text Add to dashboard Cite

Our goal is to reconstruct both the shape and reflectance properties of surfaces from multiple images. We argue that an object-centered representation is most appropriate for this purpose because it naturally accomodates multiple sources of data, multiple images (including motion sequences of a rigid object), self-occlusions arid geometric constraints. We then present a specific object-centered reconstruction method. It begins with an initial estimate of surface shape that is iteratively adjusted to minimize an objective function that combines information from multiple input images. The objective function is a weighted sum of "stereo," shading, and smoothness components, where the weight varies over the surface. For example, the stereo component is weighted more strongly where the surface projects onto highly textured areas in the images, and less strongly otherwise. Thus, each component has its greatest influence where its accuracy is likely to be greatest. Experimental results on both synthetic and real images are presented.

show abstract

Section: Related Work and Contributionsmentioning

confidence: 99%

<title>Combining stereo, shading, and geometric constraints for surface reconstruction from multiple views</title>

Fua

Leclerc

1993

SPIE Proceedings

View full text Add to dashboard Cite

show abstract

“…The governing equation for nodal point relationships is nonlinear and hence, numerical methods are used to solve this equation. There are many applications that use this approach to minimize the energy needed to reconstruct the surface [1,2,4,5,6,7,8]. The most popular technique is the finite element method (FEM).…”

Section: Introductionmentioning

confidence: 99%

<title>Sampling and surface reconstruction with adaptive-size meshes</title>

Huang

Goldgof

1992

Applications of Artificial Intelligence X: Machine Vision and Robotics

View full text Add to dashboard Cite

show abstract

“…Incorporating dynamics into shape modeling enables the creation of realistic animation in computer graphics applications and for tracking moving objects in computer vision. Following the advent of the dynamic shape modeling paradigm, considerable research followed, with numerous application specific modifications to the modeling primitives, and external forces derived from data constraints [10,12,34,35,37]. However, the final surface shape in the aforementioned schemes depends on the initial guess made to start the numerical reconstruction procedure.…”

Section: Introductionmentioning

confidence: 99%

A fast level set based algorithm for topology-independent shape modeling

1996

View full text Add to dashboard Cite

Shape modeling is an important constituent of computer vision as well as computer graphics research. Shape models aid the tasks of object representation and recognition. This paper presents a new approach to shape modeling which retains some of the attractive features of existing methods, and overcomes some of their limitations. Our technique can be applied to model arbitrarily complex shapes, which include shapes with significant protrusions, and to situations where no apriori assumption about the object's topology is made. A single instance of our model, when presented with an image having more than one object of interest, has the ability to split freely to represent each object. This method is based on the ideas developed by Osher and Sethian to model propagating solid/liquid interfaces with curvature-dependent speeds. The interface (front) is a closed, nonintersecting, hypersurface flowing along its gradient field with constant speed or a speed that depends on the curvature. It is moved by solving a "Hamilton-Jacobi" type equation written for a function in which the interface is a particular level set. A speed term synthesized from the image is used to stop the interface in the vicinity of object boundaries. The resulting equation of motion is solved by employing entropy-satisfying upwind finite difference schemes. We also introduce a new algorithm for rapid advancement of the front using what we call a narrow-band update scheme. The efficacy of the scheme is demonstrated with numerical experiments on low contrast medical images.

show abstract

Surface reconstruction using deformable models with interior and boundary constraints

Cited by 37 publications

References 7 publications

<title>Combining stereo, shading, and geometric constraints for surface reconstruction from multiple views</title>

<title>Combining stereo, shading, and geometric constraints for surface reconstruction from multiple views</title>

<title>Sampling and surface reconstruction with adaptive-size meshes</title>

A fast level set based algorithm for topology-independent shape modeling

Contact Info

Product

Resources

About