Simultaneous pose, correspondence and non-rigid shape

Sanchez-Riera, Jordi; Östlund, Jonas; Fua, Pascal; Moreno-Noguer, Francesc

doi:10.1109/cvpr.2010.5539831

Cited by 33 publications

(29 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Along these lines we will take advantage of recent descriptors such as [24] or the DaLI [11]. The latter, is specially interesting because it will let us bring our approach from a rigid to a deformable domain, like in [18,20], but without the strong assumption of having to know the camera calibration parameters in advance.…”

Section: Resultsmentioning

confidence: 99%

Simultaneous Pose, Focal Length and 2D-to-3D Correspondences from Noisy Observations

Peñate-Sánchez

Serradell

Andrade‐Cetto

et al. 2013

Procedings of the British Machine Vision Conference 2013

Self Cite

View full text Add to dashboard Cite

Simultaneously recovering the camera pose and correspondences between a set of 2D-image and 3D-model points is a difficult problem, especially when the 2D-3D matches cannot be established based on appearance only. The problem becomes even more challenging when input images are acquired with an uncalibrated camera with varying zoom, which yields strong ambiguities between translation and focal length. We present a solution to this problem using only geometrical information. Our approach owes its robustness to an initial stage in which the joint pose and focal length solution space is split into several Gaussian regions. At runtime, each of these regions is explored using an hypothesize-and-test approach, in which the potential number of 2D-3D matches is progressively reduced using informed search through Kalman updates, iteratively refining the pose and focal length parameters. The technique is exhaustive but efficient, significantly improving previous methods in terms of robustness to outliers and noise.

show abstract

Section: Resultsmentioning

confidence: 99%

Simultaneous Pose, Focal Length and 2D-to-3D Correspondences from Noisy Observations

Peñate-Sánchez

Serradell

Andrade‐Cetto

et al. 2013

Procedings of the British Machine Vision Conference 2013

Self Cite

View full text Add to dashboard Cite

show abstract

“…In contrast, other problems in geometric computer vision, such as Simultaneous Pose and Correspondence [24,28,31], Fundamental matrix computation [2,14] , ellipse fitting [2,13,15,17], do take into account specific models of uncertainty per observed point. In most these approaches, the uncertainty is modeled by a covariance matrix, and Maximum Likelihood strategies are proposed to minimize the Mahalanobis distances between the noisy and the true locations of the point observations.…”

Section: Related Workmentioning

confidence: 99%

Leveraging Feature Uncertainty in the PnP Problem

Ferraz¹,

Binefa²,

Moreno-Noguer³

2014

Proceedings of the British Machine Vision Conference 2014

Self Cite

View full text Add to dashboard Cite

We propose a real-time and accurate solution to the Perspective-n-Point (PnP) problem -estimating the pose of a calibrated camera from n 3D-to-2D point correspondencesthat exploits the fact that in practice the 2D position of not all 2D features is estimated with the same accuracy. Assuming a model of such feature uncertainties is known in advance, we reformulate the PnP problem as a maximum likelihood minimization approximated by an unconstrained Sampson error function, which naturally penalizes the most noisy correspondences. The advantages of this approach are thoroughly demonstrated in synthetic experiments where feature uncertainties are exactly known.Pre-estimating the features uncertainties in real experiments is, though, not easy. In this paper we model feature uncertainty as 2D Gaussian distributions representing the sensitivity of the 2D feature detectors to different camera viewpoints. When using these noise models with our PnP formulation we still obtain promising pose estimation results that outperform the most recent approaches.

show abstract

“…The limitations of the affine-invariant descriptors when solving correspondences between images of objects that have undergone non-rigid deformations are compensated by enforcing global consistency, both spatial and photometric, among all features [4,5,12,13,24,40,41,47], or introducing segmentation information within the descriptor itself [48,49]. In any event, none of these methods specifically handles the non-rigid nature of the problem, and they rely on solving complex optimization functions for establishing matches.…”

Section: Related Workmentioning

confidence: 99%

“…In order to match points of interest under non-rigid image transformations, recent approaches propose optimizing complex objective functions that enforce global consistency in the spatial layout of all matches [12,13,24,40,41,47]. Yet, none of these approaches explicitly builds a descriptor that goes beyond invariance to affine transformations.…”

Section: Introductionmentioning

confidence: 99%

DaLI: Deformation and Light Invariant Descriptor

2015

Self Cite

View full text Add to dashboard Cite

Recent advances in 3D shape analysis and recognition have shown that heat diffusion theory can be effectively used to describe local features of deforming and scaling surfaces. In this paper, we show how this description can be used to characterize 2D image patches, and introduce DaLI, a novel feature point descriptor with high resilience to non-rigid image transformations and illumination changes. In order to build the descriptor, 2D image patches are initially treated as 3D surfaces. Patches are then described in terms of a heat kernel signature, which captures both local and global information, and shows a high degree of invariance to non-linear image warps. In addition, by further applying a logarithmic sampling and a Fourier transform, invariance to photometric changes is achieved. Finally, the descriptor is compacted by mapping it onto a low dimensional subspace computed using Principal Component Analysis, allowing for an efficient matching. A thorough experimental validation demonstrates that DaLI is significantly more discriminative and robust to illuminations changes and image transformations than state of the art descriptors, even those specifically designed to describe non-rigid deformations.

show abstract

Simultaneous pose, correspondence and non-rigid shape

Cited by 33 publications

References 24 publications

Simultaneous Pose, Focal Length and 2D-to-3D Correspondences from Noisy Observations

Simultaneous Pose, Focal Length and 2D-to-3D Correspondences from Noisy Observations

Leveraging Feature Uncertainty in the PnP Problem

DaLI: Deformation and Light Invariant Descriptor

Contact Info

Product

Resources

About