Minimal Solutions for Relative Pose With a Single Affine Correspondence

Guan, Banglei; Zhao, Ji; Li, Zhang; Sun, Fuchun; Fraundorfer, Friedrich

doi:10.1109/cvpr42600.2020.00200

Cited by 36 publications

(29 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When the relative pose has a motion prior, there are simple and efficient solvers. For example, there are many customized solvers when the rotation axis is known [21], the motion is under planar motion [21], [22], or the depth of feature points is known [53].…”

Section: Related Workmentioning

confidence: 99%

“…Several minimal solvers using ACs have been developed for different tasks. For single cameras, there are pose estimation methods for general 5 degrees of freedom (DOF) motion [17], 3DOF motion with known rotation axis [21], and 2DOF motion with planar motion [21], [22]. For multi-camera systems, there are pose estimation methods for motion with known rotation axis and planar motion [23].…”

Section: Introductionmentioning

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

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: Introductionmentioning

confidence: 99%

On Relative Pose Recovery for Multi-Camera Systems

Zhao¹,

Guan²

2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Barath et al [16,17] show that two affine correspondences are enough for relative pose estimation when the focal length is fixed and unknown. Recently, it has been shown that the relative pose can be estimated from one affine correspondence with known gravity direction or under the planar motion assumption [18,19]. However, a major drawback of using such features in practice is that obtaining them, e.g., via Affine-SIFT [20] or Harris-Affine [21], is time-consuming.…”

Section: Introductionmentioning

confidence: 99%

Homography-Based Egomotion Estimation Using Gravity and SIFT Features

Ding

Baráth

Kúkelová

2021

Computer Vision – ACCV 2020

View full text Add to dashboard Cite

Camera systems used, e.g., in cars, UAVs, smartphones, and tablets, are typically equipped with IMUs (inertial measurement units) that can measure the gravity vector. Using the information from an IMU, the y-axes of cameras can be aligned with the gravity, reducing their relative orientation to a single DOF (degree of freedom). In this paper, we use the gravity information to derive extremely efficient minimal solvers for homography-based egomotion estimation from orientation-and scalecovariant features. We use the fact that orientation-and scale-covariant features, such as SIFT or ORB, provide additional constraints on the homography. Based on the prior knowledge about the target plane (horizontal/vertical/general plane, w.r.t. the gravity direction) and using the SIFT/ORB constraints, we derive new minimal solvers that require fewer correspondences than traditional approaches and, thus, speed up the robust estimation procedure significantly. The proposed solvers are compared with the state-of-the-art point-based solvers on both synthetic data and real images, showing comparable accuracy and significant improvement in terms of speed.

show abstract

“…Eichhardt et al [14] proposed a method that uses two ACs for relative pose estimation based on general central-projective views. Recently, Hajder et al [19] and Guan et al [18] proposed minimal solutions for relative pose from a single AC when the camera is mounted on a moving vehicle. Homographies can also be estimated from two ACs as it was first shown by Köser [24].…”

Section: Introductionmentioning

confidence: 99%

Relative Pose from Deep Learned Depth and a Single Affine Correspondence

Eichhardt

Baráth

2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

We propose a new approach for combining deep-learned nonmetric monocular depth with affine correspondences (ACs) to estimate the relative pose of two calibrated cameras from a single correspondence. Considering the depth information and affine features, two new constraints on the camera pose are derived. The proposed solver is usable within 1-point RANSAC approaches. Thus, the processing time of the robust estimation is linear in the number of correspondences and, therefore, orders of magnitude faster than by using traditional approaches. The proposed 1AC+D 4 solver is tested both on synthetic data and on 110 395 publicly available real image pairs where we used an off-the-shelf monocular depth network to provide up-to-scale depth per pixel. The proposed 1AC+D leads to similar accuracy as traditional approaches while being significantly faster. When solving large-scale problems, e.g. pose-graph initialization for Structure-from-Motion (SfM) pipelines, the overhead of obtaining ACs and monocular depth is negligible compared to the speed-up gained in the pairwise geometric verification, i.e., relative pose estimation. This is demonstrated on scenes from the 1DSfM dataset using a state-of-the-art global SfM algorithm.

show abstract

Minimal Solutions for Relative Pose With a Single Affine Correspondence

Cited by 36 publications

References 41 publications

On Relative Pose Recovery for Multi-Camera Systems

On Relative Pose Recovery for Multi-Camera Systems

Homography-Based Egomotion Estimation Using Gravity and SIFT Features

Relative Pose from Deep Learned Depth and a Single Affine Correspondence

Contact Info

Product

Resources

About