Euclidean shape and motion from multiple perspective views by affine iterations

Christy, S.; Horaud, Radu

doi:10.1109/34.544079

Cited by 104 publications

(63 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although the experimental results show that there are little convergence problems, we have been unable to study the convergence of the algorithm from a theoretical point of view. We studied its convergence based on some numerical and practical considerations which allow one to determine in advance the optimal experimental setup under which convergence can be guaranteed [2]. In the future we plan to study more thoroughly the convergence of this type of algorithms.…”

Section: Resultsmentioning

confidence: 99%

Euclidean reconstruction: From paraperspective to perspective

Christy

Horaud

1996

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. In this paper we describe a method to perform Euclidean reconstruction with a perspective camera model. It incrementally performs reconstruction with a paraperspective camera in order to converge towards a perspective model. With respect to other methods that compute shape and motion from a sequence of images with a calibrated perspective camera, this method converges in a few iterations, is computationally efficient, and does not suffer from the non linear nature of the problem. Moreover, the behaviour of the algorithm may be simply explained and analysed, which is an advantage over classical non linear optimization approaches. With respect to 3-D reconstruction using an approximated camera model, our method solves for the sign (reversal) ambiguity in a very simple way and provides much more accurate reconstruction results.

show abstract

Section: Resultsmentioning

confidence: 99%

Euclidean reconstruction: From paraperspective to perspective

Christy

Horaud

1996

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…If the perspective depths λ ij are known, the perspective factorization problem is identical to the affine factorization problem. Christy & Horaud [19] and Fujiki & Kurata [20] suggested a method that consists in incrementally estimating the depth parameters starting with a weak-perspective (or a paraperspective) approximation (λ ij = 1). Each iteration updates the perspective depths and allows to solve for the reversal ambiguity.…”

Section: Previous Workmentioning

confidence: 99%

Multiple Camera Calibration Using Robust Perspective Factorization

Zaharescu

Horaud

Ronfard

et al. 2006

Third International Symposium on 3D Data Processing, Visualization, and Transmission (3DPVT'06)

View full text Add to dashboard Cite

In this paper we address the problem of recovering structure and motion from a large number of intrinsically calibrated perspective cameras. We describe a method that combines (1) weak-perspective reconstruction in the presence of noisy and missing data and (2) an algorithm that updates weakperspective reconstruction to perspective reconstruction by incrementally estimating the projective depths. The method also solves for the reversal ambiguity associated with affine factorization techniques. The method has been successfully applied to the problem of calibrating the external parameters (position and orientation) of several multiple-camera setups. Results obtained with synthetic and experimental data compare favourably with results obtained with nonlinear minimization such as bundle adjustment.

show abstract

“…The factorization algorithm [Tomasi and Kanade, 1992] is a popular approach to the SFM problem, and although initially an orthographic camera was assumed, the approach has been extended to perspective projection as well [Christy and Horaud, 1996].…”

Section: Shape Estimationmentioning

confidence: 99%

Image-based spatio-temporal modeling and view interpolation of dynamic events

Vedula¹,

Baker

Kanade

2005

ACM Trans. Graph.

View full text Add to dashboard Cite

Digital photographs and video are exciting inventions that let us capture the visual experience of events around us in a computer and re-live the experience, although in a restrictive manner. Photographs only capture snapshots of a dynamic event, and while video does capture motion, it is recorded from pre-determined positions and consists of images discretely sampled in time, so the timing cannot be changed.This thesis presents an approach for re-rendering a dynamic event from an arbitrary viewpoint with any timing, using images captured from multiple video cameras. The event is modeled as a non-rigidly varying dynamic scene captured by many images from different viewpoints, at discretely sampled times. First, the spatio-temporal geometric properties (shape and instantaneous motion) are computed. Scene flow is introduced as a measure of non-rigid motion and algorithms to compute it, with the scene shape. The novel view synthesis problem is posed as one of recovering corresponding points in the original images, using the shape and scene flow. A reverse mapping algorithm, ray-casting across space and time, is de-

show abstract

Euclidean shape and motion from multiple perspective views by affine iterations

Cited by 104 publications

References 8 publications

Euclidean reconstruction: From paraperspective to perspective

Euclidean reconstruction: From paraperspective to perspective

Multiple Camera Calibration Using Robust Perspective Factorization

Image-based spatio-temporal modeling and view interpolation of dynamic events

Contact Info

Product

Resources

About