CONSAC: Robust Multi-Model Fitting by Conditional Sample Consensus

Kluger, Florian; Brachmann, Eric; Ackermann, Hanno; Rother, Carsten; Yang, Michael Ying; Rosenhahn, Bodo

doi:10.1109/cvpr42600.2020.00469

Cited by 44 publications

(78 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We conduct experiments on both synthetic and realworld datasets by comparing our method with three stateof-the-art multi-model fitting methods: T-linkage(2014) [32], Progressive-X(2019) [10], and CONSAC(2020) [29]. Other multi-model fitting methods: RPA [33] and RansaCov [34] are extremely slow (need months) to run our experiments, hence we do not include them.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Multi-instance Point Cloud Registration by Efficient Correspondence Clustering

Tang¹,

Zou²

2021

Preprint

View full text Add to dashboard Cite

We address the problem of estimating the poses of multiple instances of the source point cloud within a target point cloud. Existing solutions require sampling a lot of hypotheses to detect possible instances and reject the outliers, whose robustness and efficiency degrade notably when the number of instances and outliers increase. We propose to directly group the set of noisy correspondences into different clusters based on a distance invariance matrix. The instances and outliers are automatically identified through clustering. Our method is robust and fast. We evaluated our method on both synthetic and real-world datasets. The results show that our approach can correctly register up to 20 instances with an F1 score of 90.46% in the presence of 70% outliers, which performs significantly better and at least 10× faster than existing methods.

show abstract

Section: Methodsmentioning

confidence: 99%

“…They change the sampling weight of each point in each iteration to get different model parameters. CONSAC [29] is a learning-based method that learns to weigh each point for sampling. Both clustering-based and RANSAC-based methods rely on sampling valid hypotheses.…”

Section: Related Workmentioning

confidence: 99%

Multi-instance Point Cloud Registration by Efficient Correspondence Clustering

Tang¹,

Zou²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…In NG-RANSAC [33], Brachmann and Rother have introduced the idea of guiding. Meanwhile, Kluger et al have added the idea of multiple parametric model fitting in CONSAC [34].…”

Section: Deep Learning-based Outlier Rejectionmentioning

confidence: 99%

Learning Two-View Correspondences and Geometry via Local Neighborhood Correlation

Dai

Liu

Wang

et al. 2021

Entropy

View full text Add to dashboard Cite

Seeking quality feature correspondences (also known as matches) is a foundational step in computer vision. In our work, a novel and effective network with a stable local constraint, named the Local Neighborhood Correlation Network (LNCNet), is proposed to capture abundant contextual information of each correspondence in the local region, followed by calculating the essential matrix and camera pose estimation. Firstly, the k-Nearest Neighbor (KNN) algorithm is used to divide the local neighborhood roughly. Then, we calculate the local neighborhood correlation matrix (LNC) between the selected correspondence and other correspondences in the local region, which is used to filter outliers to obtain more accurate local neighborhood information. We cluster the filtered information into feature vectors containing richer neighborhood contextual information so that they can be used to more accurately determine the probability of correspondences as inliers. Extensive experiments have demonstrated that our proposed LNCNet performs better than some state-of-the-art networks to accomplish outlier rejection and camera pose estimation tasks in complex outdoor and indoor scenes.

show abstract

“…Robust model fitting algorithms such as RANSAC [15] and its many derivatives [2,10,54] have been used to fit low-dimensional parametric models, such as plane homographies, fundamental matrices or geometric primitives, to real-world noisy data. Trainable variants of RANSAC [7,8,34] use a neural network to predict sampling weights from data. They require fewer samples and are more accurate.…”

Section: Introductionmentioning

confidence: 99%

“…A trainable RANSAC estimator fits these primitives to 3D features, such as a depth map. We build upon the estimator proposed in [34], and extend it by predicting multiple sets of RANSAC sampling weights concurrently. This enables our method to distinguish between different structures in a scene more easily.…”

Section: Introductionmentioning

confidence: 99%

Cuboids Revisited: Learning Robust 3D Shape Fitting to Single RGB Images

Kluger¹,

Ackermann²,

Brachmann³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Humans perceive and construct the surrounding world as an arrangement of simple parametric models. In particular, man-made environments commonly consist of volumetric primitives such as cuboids or cylinders. Inferring these primitives is an important step to attain high-level, abstract scene descriptions. Previous approaches directly estimate shape parameters from a 2D or 3D input, and are only able to reproduce simple objects, yet unable to accurately parse more complex 3D scenes. In contrast, we propose a robust estimator for primitive fitting, which can meaningfully abstract real-world environments using cuboids. A RANSAC estimator guided by a neural network fits these primitives to 3D features, such as a depth map. We condition the network on previously detected parts of the scene, thus parsing it one-by-one. To obtain 3D features from a single RGB image, we additionally optimise a feature extraction CNN in an end-to-end manner. However, naively minimising pointto-primitive distances leads to large or spurious cuboids occluding parts of the scene behind. We thus propose an occlusion-aware distance metric correctly handling opaque scenes. The proposed algorithm does not require labourintensive labels, such as cuboid annotations, for training. Results on the challenging NYU Depth v2 dataset demonstrate that the proposed algorithm successfully abstracts cluttered real-world 3D scene layouts.

show abstract

CONSAC: Robust Multi-Model Fitting by Conditional Sample Consensus

Cited by 44 publications

References 64 publications

Multi-instance Point Cloud Registration by Efficient Correspondence Clustering

Multi-instance Point Cloud Registration by Efficient Correspondence Clustering

Learning Two-View Correspondences and Geometry via Local Neighborhood Correlation

Cuboids Revisited: Learning Robust 3D Shape Fitting to Single RGB Images

Contact Info

Product

Resources

About