Graph-Cut RANSAC: Local Optimization on Spatially Coherent Structures

Baráth, Dániel; Matas, Jiřı́

doi:10.1109/tpami.2021.3071812

Cited by 36 publications

(18 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We computed the average processing times of the solvers over 1,000 random problem instances. The solvers were implemented in C++ within the GC-RANSAC [5] framework using the Eigen library for performing matrix operations. We used the 5pt [38] and P3P [44] methods implemented in GC-RANSAC for composing the discussed solvers.…”

Section: Mean-point Strategymentioning

confidence: 99%

See 1 more Smart Citation

Efficient solutions to the relative pose of three calibrated cameras from four points using virtual correspondences

Tzamos¹,

Baráth²,

Sattler³

et al. 2023

Preprint

View full text Add to dashboard Cite

We study the challenging problem of estimating the relative pose of three calibrated cameras. We propose two novel solutions to the notoriously difficult configuration of four points in three views, known as the 4p3v problem. Our solutions are based on the simple idea of generating one additional virtual point correspondence in two views by using the information from the locations of the four input correspondences in the three views. For the first solver, we train a network to predict this point correspondence. The second solver uses a much simpler and more efficient strategy based on the mean points of three corresponding input points. The new solvers are efficient and easy to implement since they are based on the existing efficient minimal solvers, i.e., the well-known 5-point relative pose and the P3P solvers. The solvers achieve state-of-the-art results on real data. The idea of solving minimal problems using virtual correspondences is general and can be applied to other problems, e.g., the 5-point relative pose problem. In this way, minimal problems can be solved using simpler non-minimal solvers or even using sub-minimal samples inside RANSAC.In addition, we compare different variants of 4p3v solvers with the baseline solver for the minimal configuration consisting of three triplets of points and two points visible in two views. We discuss which configuration of points is potentially the most practical in real applications.

show abstract

Section: Mean-point Strategymentioning

confidence: 99%

“…To estimate the relative poses between the images of each triplet, we apply the Graph-Cut RANSAC [5] robust estimator. The point-to-model residual function is chosen to be the Sampson error of a triplet correspondence average over image pairs 1-2 and 1-3.…”

Section: Mean-point Strategymentioning

confidence: 99%

Efficient solutions to the relative pose of three calibrated cameras from four points using virtual correspondences

Tzamos¹,

Baráth²,

Sattler³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The authors test its adequacy to several computer vision problems with synthetic and real data and claim it to be more geometrically accurate and at the same time easy to implement. Additional improvements have been presented in [ 43 , 44 ], where USAC [ 45 ] and MAGSAC++ [ 46 ] robust estimators are included in the algorithm.…”

Section: Ransac Variantsmentioning

confidence: 99%

RANSAC for Robotic Applications: A Survey

Martínez-Otzeta

Rodríguez-Moreno

Mendialdua

et al. 2022

Sensors

View full text Add to dashboard Cite

Random Sample Consensus, most commonly abbreviated as RANSAC, is a robust estimation method for the parameters of a model contaminated by a sizable percentage of outliers. In its simplest form, the process starts with a sampling of the minimum data needed to perform an estimation, followed by an evaluation of its adequacy, and further repetitions of this process until some stopping criterion is met. Multiple variants have been proposed in which this workflow is modified, typically tweaking one or several of these steps for improvements in computing time or the quality of the estimation of the parameters. RANSAC is widely applied in the field of robotics, for example, for finding geometric shapes (planes, cylinders, spheres, etc.) in cloud points or for estimating the best transformation between different camera views. In this paper, we present a review of the current state of the art of RANSAC family methods with a special interest in applications in robotics.

show abstract

“…A 3D plane instance is reconstructed by fitting a set of sparse and noisy 3D points triangulated in real-time, which is initialized by the instance planar segmentation using [46] (only on keyframes). However, in order to cope with possible misclassification from the neural network, especially on the unseen dataset of SLAM benchmarks, the reconstruction is conducted as a sequential RANSAC [38] coupled with an inner local optimization of Graph-cut [1]. In this way, we locally optimize the spatial coherent planes in 3D space, as explained by Fig.…”

Section: Pl üCker Coordinates and Orthonormal Representationmentioning

confidence: 99%

Structure PLP-SLAM: Efficient Sparse Mapping and Localization using Point, Line and Plane for Monocular, RGB-D and Stereo Cameras

Shu¹,

Wang²,

Pagani³

et al. 2022

Preprint

View full text Add to dashboard Cite

This paper demonstrates a visual SLAM system that utilizes point and line cloud for robust camera localization, simultaneously, with an embedded piece-wise planar reconstruction (PPR) module which in all provides a structural map. To build a scale consistent map in parallel with tracking, such as employing a single camera brings the challenge of reconstructing geometric primitives with scale ambiguity, and further introduces the difficulty in graph optimization of bundle adjustment (BA). We address these problems by proposing several run-time optimizations on the reconstructed lines and planes. The system is then extended with depth and stereo sensors based on the design of the monocular framework. The results show that our proposed SLAM tightly incorporates the semantic features to boost both frontend tracking as well as backend optimization. We evaluate our system exhaustively on various datasets, and open-source our code for the community (https://github.com/PeterFWS/Structure-PLP-SLAM).

show abstract

Graph-Cut RANSAC: Local Optimization on Spatially Coherent Structures

Cited by 36 publications

References 58 publications

Efficient solutions to the relative pose of three calibrated cameras from four points using virtual correspondences

Efficient solutions to the relative pose of three calibrated cameras from four points using virtual correspondences

RANSAC for Robotic Applications: A Survey

Structure PLP-SLAM: Efficient Sparse Mapping and Localization using Point, Line and Plane for Monocular, RGB-D and Stereo Cameras

Contact Info

Product

Resources

About