Robust Multiple Structures Estimation with J-Linkage

Toldo, Roberto; Fusiello, Andrea

doi:10.1007/978-3-540-88682-2_41

Cited by 308 publications

(393 citation statements)

References 7 publications

Supporting

Mentioning

390

Contrasting

Unclassified

Order By: Relevance

“…This is done by updating iteratively a collection of κ models with κ new sampled structures using a fusion procedure that enforces explicitly the disjointness of the obtained consensus sets. However, as demonstrated experimentally in [8], this method falls short in the presence of intersecting structures.…”

Section: Consensus Analysismentioning

confidence: 97%

“…Building on this idea, the J-Linkage algorithm [8,13] was the first successful application of a preference-based representation of data. A two steps first-represent-thencluster scheme is implemented: data are represented by the votes they grant to a set of model hypotheses, then a greedy agglomerative clustering is performed to obtain a partition of the data.…”

Section: Preference Analysismentioning

confidence: 99%

“…In this section we investigate the performance of ILPRansaCov with respect to Greedy-RansaCov, which emulates Sequential Ransac, J-Linkage [8] and T-Linkage [15] on synthetic data, using the same sampling and the same inlier threshold for all the methods (or, equivalently, the same P matrix). We obtained the implementations of J-Linkage and T-Linkage from [39].…”

Section: Experiments On Simulated Datamentioning

confidence: 99%

“…The data sets ( Figure 4) consist of segments in several configurations and circles, as in [8]. Each structure consists of 50 inliers points, contaminated by Gaussian noise and outlying points in different percentages (reported in Table 1).…”

Section: Experiments On Simulated Datamentioning

confidence: 99%

“…In all these scenarios we compare ILP-RansaCov with JLinkage [8], T-linkage [15] and RPA [17], whose implementation is taken from [40]. In addition, one reference method have been added to the comparison for each specific scenario, namely: MFIGP [38] in the vanishing point experiments, SSC [41] for video motion segmentation and RCMSA [18] for two-views segmentation.…”

Section: Experimental Comparison On Real Datamentioning

confidence: 99%

See 4 more Smart Citations

Multiple structure recovery with maximum coverage

Magri

Fusiello

2017

Machine Vision and Applications

Self Cite

View full text Add to dashboard Cite

We present a general framework for geometric model fitting based on a set coverage formulation, that caters for intersecting structures and outliers in a simple and principled manner. The multi-model fitting problem is formulated in terms of the optimization of a consensus-based global cost function, which allows to sidestep the pitfalls of preference approaches based on clustering and to avoid the difficult trade-off between data fidelity and complexity of other optimization formulations. Two especially appealing characteristics of this method are the ease with which it can be implemented and its modularity with respect to the solver and to the sampling strategy. Few intelligible parameters need to be set and tuned, namely the inlier threshold and the number of desired models. The summary of the experiments is that our method compares favourably with its competitors overall, and it is always either the best performer or almost on par with the best performer in specific scenarios.

show abstract

Section: Consensus Analysismentioning

confidence: 97%

Section: Preference Analysismentioning

confidence: 99%

Section: Experiments On Simulated Datamentioning

confidence: 99%

Section: Experiments On Simulated Datamentioning

confidence: 99%

Section: Experimental Comparison On Real Datamentioning

confidence: 99%

See 3 more Smart Citations

Multiple structure recovery with maximum coverage

Magri

Fusiello

2017

Machine Vision and Applications

Self Cite

View full text Add to dashboard Cite

show abstract

Recovering 3D Planes from a Single Image via Convolutional Neural Networks

Yang

Zhou

2018

Computer Vision – ECCV 2018

View full text Add to dashboard Cite

Multi-class Model Fitting by Energy Minimization and Mode-Seeking

Baráth

Matas

2018

Computer Vision – ECCV 2018

View full text Add to dashboard Cite

We propose a general formulation, called Multi-X, for multi-class multi-instance model fitting -the problem of interpreting the input data as a mixture of noisy observations originating from multiple instances of multiple classes. We extend the commonly used α-expansion-based technique with a new move in the label space. The move replaces a set of labels with the corresponding density mode in the model parameter domain, thus achieving fast and robust optimization. Key optimization parameters like the bandwidth of the mode seeking are set automatically within the algorithm. Considering that a group of outliers may form spatially coherent structures in the data, we propose a crossvalidation-based technique removing statistically insignificant instances. Multi-X outperforms significantly the stateof-the-art on publicly available datasets for diverse problems: multiple plane and rigid motion detection; motion segmentation; simultaneous plane and cylinder fitting; circle and line fitting.

show abstract

Robust Multiple Structures Estimation with J-Linkage

Cited by 308 publications

References 7 publications

Multiple structure recovery with maximum coverage

Multiple structure recovery with maximum coverage

Recovering 3D Planes from a Single Image via Convolutional Neural Networks

Multi-class Model Fitting by Energy Minimization and Mode-Seeking

Contact Info

Product

Resources

About