MCMC-Based Multiview Reconstruction of Piecewise Smooth Subdivision Curves with a Variable Number of Control Points

Kaess, Michael; Zboinski, Rafal; Dellaert, Frank

doi:10.1007/978-3-540-24672-5_26

Cited by 10 publications

(6 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Curve detection and tracing have been extensively studied in several areas. For example, active contours (SNAKE) (Kass et al, 1988), road tracing in satellite images (Geman and Jedynak, 1996), medical image analysis (Zimmer et al, 2002), object tracking (Isard and Blake, 1996), curve reconstruction from multiview images (Kaess et al, 2004), and image coding using ridgelets and curvelets (Candes, 1998;Carlsson, 1998). Existing methods have various restrictive assumptions.…”

Section: Relation To the Other Work In Curvementioning

confidence: 99%

Parsing Images into Regions, Curves, and Curve Groups

Zhu

2006

Int J Comput Vision

View full text Add to dashboard Cite

In this paper, we present an algorithm for parsing natural images into middle level vision representations-regions, curves, and curve groups (parallel curves and trees). This algorithm is targeted for an integrated solution to image segmentation and curve grouping through Bayesian inference. The paper makes the following contributions. (1) It adopts a layered (or 2.1D-sketch) representation integrating both region and curve models which compete to explain an input image. The curve layer occludes the region layer and curves observe a partial order occlusion relation. (2) A Markov chain search scheme Metropolized Gibbs Samplers (MGS) is studied. It consists of several pairs of reversible jumps to traverse the complex solution space. An MGS proposes the next state within the jump scope of the current state according to a conditional probability like a Gibbs sampler and then accepts the proposal with a Metropolis-Hastings step. This paper discusses systematic design strategies of devising reversible jumps for a complex inference task. (3) The proposal probability ratios in jumps are factorized into ratios of discriminative probabilities. The latter are computed in a bottom-up process, and they drive the Markov chain dynamics in a data-driven Markov chain Monte Carlo framework. We demonstrate the performance of the algorithm in experiments with a number of natural images.

show abstract

Section: Relation To the Other Work In Curvementioning

confidence: 99%

Parsing Images into Regions, Curves, and Curve Groups

Zhu

2006

Int J Comput Vision

View full text Add to dashboard Cite

show abstract

“…Kahl and August [23] are among the first to show complete, freeform 3D curve reconstruction from registered 2D images. Later works then focus on improving the parametrisation of the 3D curves, presenting sub-division curves [24], nonrational B-splines [16], and implicit representations via 3D probability distributions [25]. These works, however, mostly focus on the reconstruction problem, and do not use the curve measurements in order to refine the camera poses.…”

Section: Related Workmentioning

confidence: 99%

Canny-VO: Visual Odometry With RGB-D Cameras Based on Geometric 3-D–2-D Edge Alignment

Zhou

Kneip

2019

IEEE Trans. Robot.

View full text Add to dashboard Cite

The present paper reviews the classical problem of free-form curve registration and applies it to an efficient RGB-D visual odometry system called Canny-VO, as it efficiently tracks all Canny edge features extracted from the images. Two replacements for the distance transformation commonly used in edge registration are proposed: Approximate Nearest Neighbour Fields and Oriented Nearest Neighbour Fields. 3D-2D edge alignment benefits from these alternative formulations in terms of both efficiency and accuracy. It removes the need for the more computationally demanding paradigms of datato-model registration, bilinear interpolation, and sub-gradient computation. To ensure robustness of the system in the presence of outliers and sensor noise, the registration is formulated as a maximum a posteriori problem, and the resulting weighted least squares objective is solved by the iteratively re-weighted least squares method. A variety of robust weight functions are investigated and the optimal choice is made based on the statistics of the residual errors. Efficiency is furthermore boosted by an adaptively sampled definition of the nearest neighbour fields. Extensive evaluations on public SLAM benchmark sequences demonstrate state-of-the-art performance and an advantage over classical Euclidean distance fields.

show abstract

“…Common drawbacks are strong requirements for precisely calibrated camera [4], [9], [13] and limitations to pairs or triples of views at a time [13]. In [15], Kaess et alfocuses on the subproblem of fitting parametric curves to contours identified in several images, using a Monte Carlo-type search as we do. They do not however consider the reconstruction of entire scenes with several objects and the inevitable uncertainty in the input observations.…”

Section: Introduction and Related Workmentioning

confidence: 99%

Sampling-Based Multiview Reconstruction without Correspondences for 3D Edges

Teney

Piater

2012

2012 Second International Conference on 3D Imaging, Modeling, Processing, Visualization &Amp; Transmission

View full text Add to dashboard Cite

This paper introduces a novel method for featurebased 3D reconstruction using multiple calibrated 2D views. We use a probabilistic formulation of the problem in the 3D, reconstructed space that allows using features that cannot be matched one-to-one, or which cannot be precisely located, such as points along edges. The reconstructed scene, modelled as a probability distribution in the 3D space, is defined as the intersection of all reconstructions compatible with each available view. We introduce a method based on importance sampling to retrieve individual samples from that distribution, as well as an iterative method to identify contiguous regions of high density. This allows the reconstruction of continuous 3D curves compatible with all the given input views, without establishing specific correspondences and without relying on connectivity in the input images, while accounting for uncertainty in the input observations, due e.g. to noisy images and poorly calibrated cameras. The technical formulation is attractive in its flexibility and genericity. The implemented system, evaluated on several very different publicly-available datasets, shows results competitive with existing methods, effectively dealing with arbitrary numbers of views, wide baselines and imprecise camera calibrations.

show abstract

MCMC-Based Multiview Reconstruction of Piecewise Smooth Subdivision Curves with a Variable Number of Control Points

Cited by 10 publications

References 21 publications

Parsing Images into Regions, Curves, and Curve Groups

Parsing Images into Regions, Curves, and Curve Groups

Canny-VO: Visual Odometry With RGB-D Cameras Based on Geometric 3-D–2-D Edge Alignment

Sampling-Based Multiview Reconstruction without Correspondences for 3D Edges

Contact Info

Product

Resources

About