Optimal correspondences from pairwise constraints

Enqvist, Olof; Josephson, Klas; Kahl, Fredrik

doi:10.1109/iccv.2009.5459319

Cited by 106 publications

(77 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We will not discuss it in detail here but note that it is an NP-hard problem and that it can always be solved for example using a branch and bound. A more thorough discussion on using pairwise constraints to remove outliers can be found in [4].…”

Section: Handling Outliersmentioning

confidence: 99%

Two View Geometry Estimation with Outliers

Enqvist¹,

Kahl²

2009

Procedings of the British Machine Vision Conference 2009

Self Cite

View full text Add to dashboard Cite

We study the relative orientation problem for two calibrated cameras with outliers from the feature matching. In recent years there has been a growing interest in optimal algorithms for computer vision. Most people agree that to get accurate solutions to multiview geometry problems, an appropriate norm of the reprojection errors should be minimized. To this end local as well as global optimization methods have been employed.To handle outliers though, heuristic methods still dominate the field. In this paper we address the problem of estimating relative orientation from uncertain feature correspondences. We formulate this task as an optimization problem and propose a branchand-bound algorithm to find the optimal set of correspondences as well as the optimal relative orientation. The approach is based on geometric constraints for pairs of correspondences. The experimental results are promising, especially for omnidirectional cameras. An implementation of the algorithm is also made publicly available to facilitate further research.

show abstract

Section: Handling Outliersmentioning

confidence: 99%

Two View Geometry Estimation with Outliers

Enqvist¹,

Kahl²

2009

Procedings of the British Machine Vision Conference 2009

Self Cite

View full text Add to dashboard Cite

show abstract

“…All data with camera calibration and rotation information were obtained from the web. 3 The Dino data are relatively clean, so we randomly perturbed 15% of the original data by up to 5 pixels to create a more realistic test setting. Other data were pre-cleaned by RANSAC, and only contain around 1% outliers.…”

Section: Sfm With Known Camera Rotationmentioning

confidence: 99%

“…Ideally, one would aim for the largest I, and there exists work [3,10] that targets this goal. However, these methods are either computationally intractable for high dimensional w (with a worst-case exponential complexity), or only tailored for a very specific class of applications.…”

Section: Introductionmentioning

confidence: 99%

An Adversarial Optimization Approach to Efficient Outlier Removal

Eriksson

Chin

et al. 2013

J Math Imaging Vis

View full text Add to dashboard Cite

This paper proposes a novel adversarial optimization approach to efficient outlier removal in computer vision. We characterize the outlier removal problem as a game that involves two players of conflicting interests, namely, optimizer and outlier. Such an adversarial view not only brings new insights into various existing methods, but also gives rise to a general optimization framework that provably unifies them. Under the proposed framework, we develop a new outlier removal approach that is able to offer a much needed control over the trade-off between reliability and speed, which is otherwise not available in previous methods. The proposed approach is driven by a mixed-integer minmax (convex-concave) optimization process. Although a minmax problem is generally not amenable to efficient optimization, we show that for some commonly used vision objective functions, an equivalent Linear Program reformulation exists. We demonstrate our method on two representative multiview geometry problems. Experiments on real image data illustrate superior practical performance of our method over recent techniques.

show abstract

“…It performs just as well as SoftPosit in a similar amount of time except in large amounts of clutter, where SoftPosit is outperformed by it. Also, [Enqvist et al, 2009] solved the SPC problem by determining which pairs of correspondences are infeasible and sought to maximise the number of correspondences that are feasible. This is done using an heuristic branch and bound technique and the authors achieve results comparable to state of the art.…”

Section: Related Workmentioning

confidence: 99%

A Saliency-based Framework for 2D-3D Registration

Brown

Guillemaut

Windridge

2014

Proceedings of the 9th International Conference on Computer Vision Theory and Applications

View full text Add to dashboard Cite

Abstract:Here we propose a saliency-based filtering approach to the problem of registering an untextured 3D object to a single monocular image. The principle of saliency can be applied to a range of modalities and domains to find intrinsically descriptive entities from amongst detected entities, making it a rigorous approach to multi-modal registration. We build on the Kadir-Brady saliency framework due to its principled information-theoretic approach which enables us to naturally extend it to the 3D domain. The salient points from each domain are initially aligned using the SoftPosit algorithm. This is subsequently refined by aligning the silhouette with contours extracted from the image. Whereas other point based registration algorithms focus on corners or straight lines, our saliency-based approach is more general as it is more widely applicable e.g. to curved surfaces where a corner detector would fail. We compare our salient point detector to the Harris corner and SIFT keypoint detectors and show it generally achieves superior registration accuracy.

show abstract

Optimal correspondences from pairwise constraints

Cited by 106 publications

References 23 publications

Two View Geometry Estimation with Outliers

Two View Geometry Estimation with Outliers

An Adversarial Optimization Approach to Efficient Outlier Removal

A Saliency-based Framework for 2D-3D Registration

Contact Info

Product

Resources

About