Indoor Scene Reconstruction from Sets of Noisy Range Images

Gregor, Jens; Whitaker, Ross T.

doi:10.1006/gmod.2001.0562

Cited by 12 publications

(10 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, we utilize the level set-based Bayesian range map registration and surface reconstruction framework developed by Whitaker and Gregor [17], [19], [18]. This strategy uses maximum likelihood parameter estimation to register the views before combining multiple range images via a level set implementation that can represent any solid object, regardless of shape and topology.…”

Section: Related Workmentioning

confidence: 99%

“…Surface area penalty serves as a simple prior for surface reconstruction [17], [19], [18], and a gradient descent on the surface area energy results in mean curvature flow (MCF). However, in the context of surface reconstruction, MCF suffers from several problems including volume shrinkage and elimination of sharp features (creases).…”

Section: Related Workmentioning

confidence: 99%

“…We will assume that M consists of a set of n registered range images, R ðjÞ È É n j¼1 . For all the examples in this paper, we used the registration methods described in [19], [18]. Then, the posterior probability of S given the data is…”

Section: Surface Reconstructionmentioning

confidence: 99%

“…Using the independence of the range images, the loglikelihood can be expressed as a sum ln P M j S ð Þ¼ À P n j¼1 ln P R ðjÞ j S À Á . Whitaker et al [17], [19], [18] formulate the conditional likelihood of a range image as a volume integral over the object enclosed by S. In this way, the gradient descent for the log-likelihood term is expressed as a function, fðxÞ, where x denotes surface locations in the volume. This function provides a weighted sum of the effects of measurements from different scans on the point x.…”

Section: Surface Reconstructionmentioning

confidence: 99%

“…The gradient descent for the MAP surface estimator (3) is a weighted sum of the refitting term, derived in (19), and a data term. Therefore, the final update rule for is…”

Section: Surface Refittingmentioning

confidence: 99%

See 4 more Smart Citations

Higher-order nonlinear priors for surface reconstruction

Taşdizen

Whitaker

2004

IEEE Trans. Pattern Anal. Machine Intell.

View full text Add to dashboard Cite

Abstract-For surface reconstruction problems with noisy and incomplete range data, a Bayesian estimation approach can improve the overall quality of the surfaces. The Bayesian approach to surface estimation relies on a likelihood term, which ties the surface estimate to the input data, and the prior, which ensures surface smoothness or continuity. This paper introduces a new high-order, nonlinear prior for surface reconstruction. The proposed prior can smooth complex, noisy surfaces, while preserving sharp, geometric features, and it is a natural generalization of edge-preserving methods in image processing, such as anisotropic diffusion. An exact solution would require solving a fourth-order partial differential equation (PDE), which can be difficult with conventional numerical techniques. Our approach is to solve a cascade system of two second-order PDEs, which resembles the original fourth-order system. This strategy is based on the observation that the generalization of image processing to surfaces entails filtering the surface normals. We solve one PDE for processing the normals and one for refitting the surface to the normals. Furthermore, we implement the associated surface deformations using level sets. Hence, the algorithm can accommodate very complex shapes with arbitrary and changing topologies. This paper gives the mathematical formulation and describes the numerical algorithms. We also show results using range and medical data.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Surface Reconstructionmentioning

confidence: 99%

Section: Surface Reconstructionmentioning

confidence: 99%

“…The gradient descent for the MAP surface estimator (3) is a weighted sum of the refitting term, derived in (19), and a data term. Therefore, the final update rule for is…”

Section: Surface Refittingmentioning

confidence: 99%

See 3 more Smart Citations

Higher-order nonlinear priors for surface reconstruction

Taşdizen

Whitaker

2004

IEEE Trans. Pattern Anal. Machine Intell.

View full text Add to dashboard Cite

show abstract

Closed-form solutions for estimating a rigid motion from plane correspondences extracted from point clouds

Khoshelham

2016

ISPRS Journal of Photogrammetry and Remote Sensing

View full text Add to dashboard Cite

3D Surface Modeling and Measuring System for Pneumatic Caisson

Cao

Zhang

et al. 2010

J. Comput. Civ. Eng.

View full text Add to dashboard Cite

In order to build a 3D model environment of a pneumatic caisson for excavator operators and managers, a modeling and measuring 3D surface system of unmanned pneumatic caisson was presented in this paper. The whole system is based on two 3D laser scanners for the pneumatic caisson by acquiring the surface data of pneumatic caisson and successive data processing for surface reconstruction and measurement. Registration and reconstruction are also discussed in this paper. In order to convert two point sets into one common coordinate, Hough transforms were used to extract planes and then by using their parameters to register the two point sets. As for surface reconstruction using triangular meshing, a new method based on curves was presented. When combined with the real-time pose and location of the excavators, the 3D environment can be used as a "virtual reality" operating environment for excavation operators.The whole system has been applied in a pneumatic caisson of an underground project in a Shanghai subway, which proved to be working well, with less than 16-s work cycle ͑period of a single 180°3D laser scan͒, at an estimated resolution of less than 20 mm.

show abstract

Indoor Scene Reconstruction from Sets of Noisy Range Images

Cited by 12 publications

References 55 publications

Higher-order nonlinear priors for surface reconstruction

Higher-order nonlinear priors for surface reconstruction

Closed-form solutions for estimating a rigid motion from plane correspondences extracted from point clouds

3D Surface Modeling and Measuring System for Pneumatic Caisson

Contact Info

Product

Resources

About