Computing similarity transformations from only image correspondences

Sweeney, Chris; Kneip, Laurent; Höllerer, Tobias; Turk, Matthew

doi:10.1109/cvpr.2015.7298951

Cited by 19 publications

(11 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We believe that the distributed camera model is a useful way to parameterize cameras and can provide great benefits for SfM. For future work, we plan to explore the use of distributed cameras for global SfM, as well as structure-less SfM by merging distributed cameras from 2D-2D ray correspondences without the need for 3D points [13,22].…”

Section: Resultsmentioning

confidence: 99%

Large Scale SfM with the Distributed Camera Model

Sweeney

Fragoso

Höllerer

et al. 2016

2016 Fourth International Conference on 3D Vision (3DV)

Self Cite

View full text Add to dashboard Cite

We introduce the distributed camera model, a novel model for Structure-from-Motion (SfM). This model describes image observations in terms of light rays with ray origins and directions rather than pixels. As such, the proposed model is capable of describing a single camera or multiple cameras simultaneously as the collection of all light rays observed. We show how the distributed camera model is a generalization of the standard camera model and we describe a general formulation and solution to the absolute camera pose problem that works for standard or distributed cameras. The proposed method computes a solution that is up to 8 times more efficient and robust to rotation singularities in comparison with gDLS [21]. Finally, this method is used in an novel large-scale incremental SfM pipeline where distributed cameras are accurately and robustly merged together. This pipeline is a direct generalization of traditional incremental SfM; however, instead of incrementally adding one camera at a time to grow the reconstruction the reconstruction is grown by adding a distributed camera. Our pipeline produces highly accurate reconstructions efficiently by avoiding the need for many bundle adjustment iterations and is capable of computing a 3D model of Rome from over 15,000 images in just 22 minutes.

show abstract

Section: Resultsmentioning

confidence: 99%

Large Scale SfM with the Distributed Camera Model

Sweeney

Fragoso

Höllerer

et al. 2016

2016 Fourth International Conference on 3D Vision (3DV)

Self Cite

View full text Add to dashboard Cite

show abstract

“…1). As we can observe, this line of research may become computationally infeasible when n > 5 [6,50]. For example, in the case of n = 6, we may have up to 288 solutions and there is no easy way to build the solver.…”

Section: -Cycle Registrationmentioning

confidence: 99%

Minimal Solvers for Mini-Loop Closures in 3D Multi-Scan Alignment

Miraldo

Saha

Ramalingam

2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

3D scan registration is a classical, yet a highly useful problem in the context of 3D sensors such as Kinect and Velodyne. While there are several existing methods, the techniques are usually incremental where adjacent scans are registered first to obtain the initial poses, followed by motion averaging and bundle-adjustment refinement. In this paper, we take a different approach and develop minimal solvers for jointly computing the initial poses of cameras in small loops such as 3-, 4-, and 5-cycles 1 . Note that the classical registration of 2 scans can be done using a minimum of 3 point matches to compute 6 degrees of relative motion. On the other hand, to jointly compute the 3D registrations in n-cycles, we take 2 point matches between the first n − 1 consecutive pairs (i.e., Scan 1 & Scan 2, . . . , and Scan n − 1 & Scan n) and 1 or 2 point matches between Scan 1 and Scan n. Overall, we use 5, 7, and 10 point matches for 3-, 4-, and 5-cycles, and recover 12, 18, and 24 degrees of transformation variables, respectively. Using simulations and real-data we show that the 3D registration using mini n-cycles are computationally efficient, and can provide alternate and better initial poses compared to standard pairwise methods.

show abstract

“…bundle adjustment), but we restrict outselves to pure and efficient globally optimal solutions that can be employed many times within a RANSAC scheme, and over small sets of correspondences. We also omit the method presented in [18], as we only consider fully general approaches that do not require any information other than the raw correspondences. As such, the only competing methods are 2D-3D and 3D-3D alignment alternatives.…”

Section: Outline Of the Experimentsmentioning

confidence: 99%

“…The generalized relative pose and scale problem was first introduced and solved for known vertical direction in [18]. In this work, we drop the assumption of known vertical direction, and solve for a full Euclidean transformation.…”

Section: Introductionmentioning

confidence: 99%

The generalized relative pose and scale problem: View-graph fusion via 2D-2D registration

Kneip

Sweeney

Hartley

2016

2016 IEEE Winter Conference on Applications of Computer Vision (WACV)

Self Cite

View full text Add to dashboard Cite

It is well-known that the relative pose problem can be generalized to non-central cameras. We present a further generalization, denoted the generalized relative pose and scale problem. It has surprising importance for classical problems such as solving similarity transformations for view-graph concatenation in hierarchical structure from motion and loop-closure in visual SLAM, both posed as a 2D-2D registration problem. The relative pose problem and all its generalizations constitute a family of similar symmetric eigenvalue problems, which allow us to compress data and find a geometrically meaningful solution by an efficient search in the space of rotations. While the derivation of a completely general closed-form solver appears intractable, we make use of a simple heuristic global energy minimization scheme based on local minimum suppression, returning outstanding performance in practically relevant scenarios. Efficiency and reliability of our algorithm are demonstrated on both simulated and real data, supporting our claim of superior performance with respect to both generalized 2D-3D and 3D-3D registration approaches. By directly employing image information, we avoid the common noise in point clouds occuring especially along the depth direction.

show abstract

Computing similarity transformations from only image correspondences

Cited by 19 publications

References 29 publications

Large Scale SfM with the Distributed Camera Model

Large Scale SfM with the Distributed Camera Model

Minimal Solvers for Mini-Loop Closures in 3D Multi-Scan Alignment

The generalized relative pose and scale problem: View-graph fusion via 2D-2D registration

Contact Info

Product

Resources

About