A Certifiably Globally Optimal Solution to Generalized Essential Matrix Estimation

Zhao, Ji; Xu, Wanting; Kneip, Laurent

doi:10.1109/cvpr42600.2020.01205

Cited by 27 publications

(15 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, relative pose estimation methods can be applied for single cameras [5], [6], [7], [8], [9], [10], multi-camera systems or generalized cameras [11], [12], [13], [14]. Moreover, the cameras include fully calibrated cameras and partially calibrated cameras with unknown focal length and/or radial distortion.…”

Section: Related Workmentioning

confidence: 99%

“…Third, a relative pose estimation method can be classified as a minimal solver [5], [11], a non-minimal solver [13], [14], [31], [32] or a linear solver [12], [33]. Minimal solvers use the minimum required number of geometric primitives to estimate relative pose.…”

Section: Related Workmentioning

confidence: 99%

“…For multi-camera systems, the development of minimal solvers for relative pose estimation ranges back to the six-point method [11]. Later, many other works have been subsequently proposed, such as the 17-point linear solvers [12], an efficient solver based on iterative optimization [13], and a solver based on global optimization [14].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

On Relative Pose Recovery for Multi-Camera Systems

Zhao¹,

Guan²

2021

Preprint

Self Cite

View full text Add to dashboard Cite

The point correspondence (PC) and affine correspondence (AC) are widely used for relative pose estimation. An AC consists of a PC across two views and an affine transformation between the small patches around this PC. Previous work demonstrates that one AC generally provides three independent constraints for relative pose estimation. For multi-camera systems, there is still not any AC-based minimal solver for general relative pose estimation. To deal with this problem, we propose a complete solution to relative pose estimation from two ACs for multi-camera systems, consisting of a series of minimal solvers. The solver generation in our solution is based on Cayley or quaternion parameterization for rotation and hidden variable technique to eliminate translation. This solver generation method is also naturally applied to relative pose estimation from PCs, resulting in a new six-point method for multi-camera systems. A few extensions are made, including relative pose estimation with known rotation angle and/or with unknown focal lengths. Extensive experiments demonstrate that the proposed AC-based solvers and PC-based solvers are effective and efficient on synthetic and real-world datasets.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

On Relative Pose Recovery for Multi-Camera Systems

Zhao¹,

Guan²

2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…These could be classified into algebra-based minimal/nonminimal solvers [34,37,19,32,29] and optimization-based nonlinear methods [28,67,5,12]. In addition, some methods are specially tailored to specific types of camera setup or motion prior [71,21,76,16,53,15,14]. Our framework does not require the geometric methods to be differentiable, and in principle could work with any approaches.…”

Section: Related Workmentioning

confidence: 99%

Fusing the Old with the New: Learning Relative Camera Pose with Geometry-Guided Uncertainty

Zhuang¹,

Chandraker²

2021

Preprint

View full text Add to dashboard Cite

Learning methods for relative camera pose estimation have been developed largely in isolation from classical geometric approaches. The question of how to integrate predictions from deep neural networks (DNNs) and solutions from geometric solvers, such as the 5-point algorithm [37], has as yet remained under-explored. In this paper, we present a novel framework that involves probabilistic fusion between the two families of predictions during network training, with a view to leveraging their complementary benefits in a learnable way. The fusion is achieved by learning the DNN uncertainty under explicit guidance by the geometric uncertainty, thereby learning to take into account the geometric solution in relation to the DNN prediction. Our network features a self-attention graph neural network, which drives the learning by enforcing strong interactions between different correspondences and potentially modeling complex relationships between points. We propose motion parmeterizations suitable for learning and show that our method achieves state-of-the-art performance on the challenging DeMoN [61] and ScanNet [8] datasets. While we focus on relative pose, we envision that our pipeline is broadly applicable for fusing classical geometry and deep learning.

show abstract

“…Relative pose estimation from two views of a camera, or a multi-camera system is regarded as a fundamental problem in computer vision [22,10,45,46,51], which plays an important role in simultaneous localization and mapping (SLAM) and structure-from-motion (SfM). Thus, improving the accuracy, efficiency and robustness of relative pose estimation algorithms is always an important research topic [30,50,1,16,6,12,31].…”

Section: Introductionmentioning

confidence: 99%

Minimal Cases for Computing the Generalized Relative Pose using Affine Correspondences

Guan

Zhao

Baráth³

et al. 2021

2021 IEEE/CVF International Conference on Computer Vision (ICCV)

Self Cite

View full text Add to dashboard Cite

We propose three novel solvers for estimating the relative pose of a multi-camera system from affine correspondences (ACs). A new constraint is derived interpreting the relationship of ACs and the generalized camera model. Using the constraint, we demonstrate efficient solvers for two types of motions assumed. Considering that the cameras undergo planar motion, we propose a minimal solution using a single AC and a solver with two ACs to overcome the degenerate case. Also, we propose a minimal solution using two ACs with known vertical direction, e.g., from an IMU. Since the proposed methods require significantly fewer correspondences than state-of-the-art algorithms, they can be efficiently used within RANSAC for outlier removal and initial motion estimation. The solvers are tested both on synthetic data and on real-world scenes from the KITTI odometry benchmark. It is shown that the accuracy of the estimated poses is superior to the state-of-the-art techniques.

show abstract

A Certifiably Globally Optimal Solution to Generalized Essential Matrix Estimation

Cited by 27 publications

References 32 publications

On Relative Pose Recovery for Multi-Camera Systems

On Relative Pose Recovery for Multi-Camera Systems

Fusing the Old with the New: Learning Relative Camera Pose with Geometry-Guided Uncertainty

Minimal Cases for Computing the Generalized Relative Pose using Affine Correspondences

Contact Info

Product

Resources

About