On Efficient and Robust Metrics for RANSAC Hypotheses and 3D Rigid Registration

• URL: http://arxiv.org/abs/2011.04862v1
• Date: Tue, 10 Nov 2020 02:22:45 GMT
• Title: On Efficient and Robust Metrics for RANSAC Hypotheses and 3D Rigid Registration
• Authors: Jiaqi Yang, Zhiqiang Huang, Siwen Quan, Qian Zhang, Yanning Zhang, Zhiguo Cao
• Abstract summary: This paper focuses on developing efficient and robust evaluation metrics for RANSAC hypotheses to achieve accurate 3D rigid registration. We analyze the contributions of inliers and outliers, and then proposing several efficient and robust metrics with different designing motivations for RANSAC hypotheses.
• Score: 51.64236850960365
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper focuses on developing efficient and robust evaluation metrics for RANSAC hypotheses to achieve accurate 3D rigid registration. Estimating six-degree-of-freedom (6-DoF) pose from feature correspondences remains a popular approach to 3D rigid registration, where random sample consensus (RANSAC) is a de-facto choice to this problem. However, existing metrics for RANSAC hypotheses are either time-consuming or sensitive to common nuisances, parameter variations, and different application scenarios, resulting in performance deterioration in overall registration accuracy and speed. We alleviate this problem by first analyzing the contributions of inliers and outliers, and then proposing several efficient and robust metrics with different designing motivations for RANSAC hypotheses. Comparative experiments on four standard datasets with different nuisances and application scenarios verify that the proposed metrics can significantly improve the registration performance and are more robust than several state-of-the-art competitors, making them good gifts to practical applications. This work also draws an interesting conclusion, i.e., not all inliers are equal while all outliers should be equal, which may shed new light on this research problem.

Related papers

• Self-Training with Pseudo-Label Scorer for Aspect Sentiment Quad Prediction [54.23208041792073]
  Aspect Sentiment Quad Prediction (ASQP) aims to predict all quads (aspect term, aspect category, opinion term, sentiment polarity) for a given review. A key challenge in the ASQP task is the scarcity of labeled data, which limits the performance of existing methods. We propose a self-training framework with a pseudo-label scorer, wherein a scorer assesses the match between reviews and their pseudo-labels.
  arXiv  Detail & Related papers  (2024-06-26T05:30:21Z)
• Towards Evaluating Transfer-based Attacks Systematically, Practically, and Fairly [79.07074710460012]
  adversarial vulnerability of deep neural networks (DNNs) has drawn great attention. An increasing number of transfer-based methods have been developed to fool black-box DNN models. We establish a transfer-based attack benchmark (TA-Bench) which implements 30+ methods.
  arXiv  Detail & Related papers  (2023-11-02T15:35:58Z)
• Robust Outlier Rejection for 3D Registration with Variational Bayes [70.98659381852787]
  We develop a novel variational non-local network-based outlier rejection framework for robust alignment. We propose a voting-based inlier searching strategy to cluster the high-quality hypothetical inliers for transformation estimation.
  arXiv  Detail & Related papers  (2023-04-04T03:48:56Z)
• Practical, Fast and Robust Point Cloud Registration for 3D Scene Stitching and Object Localization [6.8858952804978335]
  3D point cloud registration is a fundamental problem in remote sensing, photogrammetry, robotics and geometric computer vision. We propose a novel, fast and highly robust solution, named VOCRA, for the point cloud registration problem with extreme outlier rates. We show that our solver VOCRA is robust against over 99% outliers and more time-efficient than the state-of-the-art competitors.
  arXiv  Detail & Related papers  (2021-11-08T01:49:04Z)
• TriVoC: Efficient Voting-based Consensus Maximization for Robust Point Cloud Registration with Extreme Outlier Ratios [6.8858952804978335]
  We present a novel, fast, deterministic and guaranteed robust solver, named TriVoC, for the robust registration problem. We show that TriVoC is robust against up to 99% outliers, highly accurate, time-efficient even with extreme outlier ratios, and also practical for real-world applications.
  arXiv  Detail & Related papers  (2021-11-01T02:03:40Z)
• A recursive robust filtering approach for 3D registration [3.5270468102327004]
  The proposed method has four advantages that have not yet occurred altogether in any previous solution. It is able to deal with inherent noise contaminating sensory data. It is robust to uncertainties caused by noisy feature localisation.
  arXiv  Detail & Related papers  (2021-10-28T07:50:02Z)
• DANIEL: A Fast and Robust Consensus Maximization Method for Point Cloud Registration with High Outlier Ratios [6.8858952804978335]
  Correspondence-based point cloud registration is a cornerstone in computer vision, robotics perception, photogrammetry and remote sensing. Current 3D keypoint matching techniques are very prone to yield outliers, probably even in very large numbers. We present a novel time-efficient RANSAC-type consensus solver, named DANIEL, for robust registration.
  arXiv  Detail & Related papers  (2021-10-11T08:27:00Z)
• ICOS: Efficient and Highly Robust Point Cloud Registration with Correspondences [6.8858952804978335]
  Point Cloud Registration is a fundamental problem in robotics and computer vision. In this paper, we present ICOS, a novel, efficient and highly robust solution for the correspondence-based point cloud registration problem.
  arXiv  Detail & Related papers  (2021-04-30T05:41:53Z)
• Hidden Cost of Randomized Smoothing [72.93630656906599]
  In this paper, we point out the side effects of current randomized smoothing. Specifically, we articulate and prove two major points: 1) the decision boundaries of smoothed classifiers will shrink, resulting in disparity in class-wise accuracy; 2) applying noise augmentation in the training process does not necessarily resolve the shrinking issue due to the inconsistent learning objectives.
  arXiv  Detail & Related papers  (2020-03-02T23:37:42Z)
• Triple Wins: Boosting Accuracy, Robustness and Efficiency Together by Enabling Input-Adaptive Inference [119.19779637025444]
  Deep networks were recently suggested to face the odds between accuracy (on clean natural images) and robustness (on adversarially perturbed images) This paper studies multi-exit networks associated with input-adaptive inference, showing their strong promise in achieving a "sweet point" in cooptimizing model accuracy, robustness and efficiency.
  arXiv  Detail & Related papers  (2020-02-24T00:40:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.