| 1. |
- Bernard, Florian, et al.
(författare)
-
HiPPI : Higher-order projected power iterations for scalable multi-matching
- 2019
-
Ingår i: IEEE International Conference on (ICCV) Computer Vision. - New York : Institute of Electrical and Electronics Engineers (IEEE). - 1550-5499. ; 2019-October, s. 10283-10292
-
Tidskriftsartikel (refereegranskat)abstract
- The matching of multiple objects (e.g. shapes or images) is a fundamental problem in vision and graphics. In order to robustly handle ambiguities, noise and repetitive patterns in challenging real-world settings, it is essential to take geometric consistency between points into account. Computationally, the multi-matching problem is difficult. It can be phrased as simultaneously solving multiple (NP-hard) quadratic assignment problems (QAPs) that are coupled via cycle-consistency constraints. The main limitations of existing multi-matching methods are that they either ignore geometric consistency and thus have limited robustness, or they are restricted to small-scale problems due to their (relatively) high computational cost. We address these shortcomings by introducing a Higher-order Projected Power Iteration method, which is (i) efficient and scales to tens of thousands of points, (ii) straightforward to implement, (iii) able to incorporate geometric consistency, (iv) guarantees cycle-consistent multi-matchings, and (iv) comes with theoretical convergence guarantees. Experimentally we show that our approach is superior to existing methods. © 2019 IEEE.
|
|
| 2. |
- Byröd, Martin, et al.
(författare)
-
Improving numerical accuracy of Grobner basis polynomial equation solvers
- 2007
-
Ingår i: Proceedings of the IEEE 11th International Conference on Computer Vision. - 1550-5499. - 9781424416318 ; , s. 449-456
-
Konferensbidrag (refereegranskat)abstract
- This paper presents techniques for improving the numerical stability of Grobner basis solvers for polynomial equations. Recently Grobner basis methods have been used succesfully to solve polynomial equations arising in global optimization e.g. three view triangulation and in many important minimal cases of structure from motion. Such methods work extremely well for problems of reasonably low degree, involving a few variables. Currently, the limiting factor in using these methods for larger and more demanding problems is numerical difficulties. In the paper we (i) show how to change basis in the quotient space R[x]/I and propose a strategy for selecting a basis which improves the conditioning of a crucial elimination step, (ii) use this technique to devise a Grobner basis with improved precision and (iii) show how solving for the eigenvalues instead of eigenvectors can be used to improve precision further while retaining the same speed. We study these methods on some of the latest reported uses of Grobner basis methods and demonstrate dramatically improved numerical precision using these new techniques making it possible to solve a larger class of problems than previously.
|
|
| 3. |
- Enqvist, Olof, et al.
(författare)
-
Optimal Correspondences from Pairwise Constraints
- 2009
-
Ingår i: IEEE International Conference on Computer Vision. - 1550-5499. - 9781424444199 ; , s. 1295-1302
-
Konferensbidrag (refereegranskat)abstract
- Correspondence problems are of great importance in computer vision. They appear as subtasks in many applications such as object recognition, merging partial 3D reconstructions and image alignment. Automatically matching features from appearance only is difficult and errors are frequent. Thus, it is necessary to use geometric consistency to remove incorrect correspondences. Typically heuristic methods like RANSAC or EM-like algorithms are used, but they risk getting trapped in local optima and are in no way guaranteed to find the best solution. This paper illustrates how pairwise constraints in combination with graph methods can be used to efficiently find optimal correspondences. These ideas are implemented on two basic geometric problems, 3D-3D registration and 2D-3D registration. The developed scheme can handle large rates of outliers and cope with multiple hypotheses. Despite the combinatorial explosion, the resulting algorithm which has been extensively evaluated on real data, yields competitive running times compared to state of the art
|
|
| 4. |
- Iglesias, José Pedro Lopes, 1994, et al.
(författare)
-
Radial Distortion Invariant Factorization for Structure from Motion
- 2021
-
Ingår i: Proceedings of the IEEE International Conference on Computer Vision. - 1550-5499. ; , s. 5886-5895
-
Konferensbidrag (refereegranskat)abstract
- Factorization methods are frequently used for structure from motion problems (SfM). In the presence of noise they are able to jointly estimate camera matrices and scene points in overdetermined settings, without the need for accurate initial solutions. While the early formulations were restricted to affine models, recent approaches have been show to work with pinhole cameras by minimizing object space errors. In this paper we propose a factorization approach using the so called radial camera, which is invariant to radial distortion and changes in focal length. Assuming a known principal point our approach can reconstruct the 3D scene in settings with unknown and varying radial distortion and focal length. We show on both real and synthetic data that our approach outperforms state-of-the-art factorization methods under these conditions.
|
|
| 5. |
- Jafarzadeh, Ara, et al.
(författare)
-
CrowdDriven: A New Challenging Dataset for Outdoor Visual Localization
- 2021
-
Ingår i: Proceedings of the IEEE International Conference on Computer Vision. - 1550-5499. ; , s. 9825-9835
-
Konferensbidrag (refereegranskat)abstract
- Visual localization is the problem of estimating the position and orientation from which a given image (or a sequence of images) is taken in a known scene. It is an important part of a wide range of computer vision and robotics applications, from self-driving cars to augmented/virtual reality systems. Visual localization techniques should work reliably and robustly under a wide range of conditions, including seasonal, weather, illumination and man-made changes. Recent benchmarking efforts model this by providing images under different conditions, and the community has made rapid progress on these datasets since their inception. However, they are limited to a few geographical regions and often recorded with a single device. We propose a new benchmark for visual localization in outdoor scenes, using crowd-sourced data to cover a wide range of geographical regions and camera devices with a focus on the failure cases of current algorithms. Experiments with state-of-the-art localization approaches show that our dataset is very challenging, with all evaluated methods failing on its hardest parts. As part of the dataset release, we provide the tooling used to generate it, enabling efficient and effective 2D correspondence annotation to obtain reference poses.
|
|
| 6. |
- Larsson, Måns, 1989, et al.
(författare)
-
Fine-Grained Segmentation Networks: Self-Supervised Segmentation for Improved Long-Term Visual Localization
- 2019
-
Ingår i: Proceedings of the IEEE International Conference on Computer Vision. - 1550-5499. ; :October, s. 31-41
-
Konferensbidrag (refereegranskat)abstract
- Long-term visual localization is the problem of estimating the camera pose of a given query image in a scene whose appearance changes over time. It is an important problem in practice, for example, encountered in autonomous driving. In order to gain robustness to such changes, long-term localization approaches often use segmantic segmentations as an invariant scene representation, as the semantic meaning of each scene part should not be affected by seasonal and other changes. However, these representations are typically not very discriminative due to the limited number of available classes. In this paper, we propose a new neural network, the Fine-Grained Segmentation Network (FGSN), that can be used to provide image segmentations with a larger number of labels and can be trained in a self-supervised fashion. In addition, we show how FGSNs can be trained to output consistent labels across seasonal changes. We demonstrate through extensive experiments that integrating the fine-grained segmentations produced by our FGSNs into existing localization algorithms leads to substantial improvements in localization performance.
|
|
| 7. |
- Larsson, Viktor, et al.
(författare)
-
A Simple Method for Subspace Estimation with Corrupted Columns
- 2016
-
Ingår i: Proceedings of the IEEE International Conference on Computer Vision. - 1550-5499. - 9781467383905 ; 2016-February, s. 841-849
-
Konferensbidrag (refereegranskat)abstract
- This paper presents a simple and effective way of solving the robust subspace estimation problem where the corruptions are column-wise. The method we present can handle a large class of robust loss functions and is simple to implement. It is based on Iteratively Reweighted Least Squares (IRLS) and works in an iterative manner by solving a weighted least-squares rank-constrained problem in every iteration. By considering the special case of column-wise loss functions, we show that each such surrogate problem admits a closed form solution. Unlike many other approaches to subspace estimation, we make no relaxation of the low-rank constraint and our method is guaranteed to produce a subspace estimate with the correct dimension. Subspace estimation is a core problem for several applications in computer vision. We empirically demonstrate the performance of our method and compare it to several other techniques for subspace estimation. Experimental results are given for both synthetic and real image data including the following applications: linear shape basis estimation, plane fitting and non-rigid structure from motion.
|
|
| 8. |
- Larsson, Viktor, et al.
(författare)
-
Orthographic-Perspective Epipolar Geometry
- 2021
-
Ingår i: Proceedings - 2021 IEEE/CVF International Conference on Computer Vision, ICCV 2021. - 1550-5499. - 9781665428125 ; , s. 5550-5558
-
Konferensbidrag (refereegranskat)abstract
- In this paper we consider the epipolar geometry between orthographic and perspective cameras. We generalize many of the classical results for the perspective essential matrix to this setting and derive novel minimal solvers, not only for the calibrated case, but also for partially calibrated and non-central camera setups. While orthographic cameras might seem exotic, they occur naturally in many applications. They can e.g. model 2D maps (such as floor plans), aerial/satellite photography and even approximate narrow field-of-view cameras (e.g. from telephoto lenses). In our experiments we highlight various applications of the developed theory and solvers, including Radar-Camera calibration and aligning Structure-from-Motion models to aerial or satellite images.
|
|
| 9. |
- Larsson, Viktor, et al.
(författare)
-
Revisiting Radial Distortion Absolute Pose
- 2019
-
Ingår i: Proceedings of the IEEE International Conference on Computer Vision. - 1550-5499. - 9781728148038 ; , s. 1062-1071
-
Konferensbidrag (refereegranskat)abstract
- To model radial distortion there are two main approaches; either the image points are undistorted such that they correspond to pinhole projections, or the pinhole projections are distorted such that they align with the image measurements. Depending on the application, either of the two approaches can be more suitable. For example, distortion models are commonly used in Structure-from-Motion since they simplify measuring the reprojection error in images. Surprisingly, all previous minimal solvers for pose estimation with radial distortion use undistortion models. In this paper we aim to fill this gap in the literature by proposing the first minimal solvers which can jointly estimate distortion models together with camera pose. We present a general approach which can handle rational models of arbitrary degree for both distortion and undistortion.
|
|
| 10. |
- Liu, Fanghui, et al.
(författare)
-
Visual Tracking via Nonnegative Regularization Multiple Locality Coding
- 2015
-
Ingår i: Proceedings of the IEEE International Conference on Computer Vision. - 1550-5499. - 9780769557205 ; , s. 912-920
-
Konferensbidrag (refereegranskat)abstract
- This paper presents a novel object tracking method based on approximated Locality-constrained Linear Coding (LLC). Rather than using a non-negativity constraint on encoding coefficients to guarantee these elements nonnegative, in this paper, the non-negativity constraint is substituted for a conventional ℓ2 norm regularization term in approximated LLC to obtain the similar nonnegative effect. And we provide a detailed and adequate explanation in theoretical analysis to clarify the rationality of this replacement. Instead of specifying fixed K nearest neighbors to construct the local dictionary, a series of different dictionaries with pre-defined numbers of nearest neighbors are selected. Weights of these various dictionaries are also learned from approximated LLC in the similar framework. In order to alleviate tracking drifts, we propose a simple and efficient occlusion detection method. The occlusion detection criterion mainly depends on whether negative templates are selected to represent the severe occluded target. Both qualitative and quantitative evaluations on several challenging sequences show that the proposed tracking algorithm achieves favorable performance compared with other state-of-the-art methods.
|
|
