DANIEL: A Fast and Robust Consensus Maximization Method for Point Cloud Registration with High Outlier Ratios

• URL: http://arxiv.org/abs/2110.05075v2
• Date: Tue, 12 Oct 2021 00:50:49 GMT
• Title: DANIEL: A Fast and Robust Consensus Maximization Method for Point Cloud Registration with High Outlier Ratios
• Authors: Lei Sun
• Abstract summary: 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.
• Score: 6.8858952804978335
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Correspondence-based point cloud registration is a cornerstone in geometric computer vision, robotics perception, photogrammetry and remote sensing, which seeks to estimate the best rigid transformation between two point clouds from the correspondences established over 3D keypoints. However, due to limited robustness and accuracy, current 3D keypoint matching techniques are very prone to yield outliers, probably even in very large numbers, making robust estimation for point cloud registration of great importance. Unfortunately, existing robust methods may suffer from high computational cost or insufficient robustness when encountering high (or even extreme) outlier ratios, hardly ideal enough for practical use. In this paper, we present a novel time-efficient RANSAC-type consensus maximization solver, named DANIEL (Double-layered sAmpliNg with consensus maximization based on stratIfied Element-wise compatibiLity), for robust registration. DANIEL is designed with two layers of random sampling, in order to find inlier subsets with the lowest computational cost possible. Specifically, we: (i) apply the rigidity constraint to prune raw outliers in the first layer of one-point sampling, (ii) introduce a series of stratified element-wise compatibility tests to conduct rapid compatibility checking between minimal models so as to realize more efficient consensus maximization in the second layer of two-point sampling, and (iii) probabilistic termination conditions are employed to ensure the timely return of the final inlier set. Based on a variety of experiments over multiple real datasets, we show that DANIEL is robust against over 99% outliers and also significantly faster than existing state-of-the-art robust solvers (e.g. RANSAC, FGR, GORE).

Related papers

• SEED: A Simple and Effective 3D DETR in Point Clouds [72.74016394325675]
  We argue that the main challenges are challenging due to the high sparsity and uneven distribution of point clouds. We propose a simple and effective 3D DETR method (SEED) for detecting 3D objects from point clouds.
  arXiv  Detail & Related papers  (2024-07-15T14:21:07Z)
• KECOR: Kernel Coding Rate Maximization for Active 3D Object Detection [48.66703222700795]
  We resort to a novel kernel strategy to identify the most informative point clouds to acquire labels. To accommodate both one-stage (i.e., SECOND) and two-stage detectors, we incorporate the classification entropy tangent and well trade-off between detection performance and the total number of bounding boxes selected for annotation. Our results show that approximately 44% box-level annotation costs and 26% computational time are reduced compared to the state-of-the-art method.
  arXiv  Detail & Related papers  (2023-07-16T04:27:03Z)
• Reliability-Adaptive Consistency Regularization for Weakly-Supervised Point Cloud Segmentation [80.07161039753043]
  Weakly-supervised point cloud segmentation with extremely limited labels is desirable to alleviate the expensive costs of collecting densely annotated 3D points. This paper explores applying the consistency regularization that is commonly used in weakly-supervised learning, for its point cloud counterpart with multiple data-specific augmentations. We propose a novel Reliability-Adaptive Consistency Network (RAC-Net) to use both prediction confidence and model uncertainty to measure the reliability of pseudo labels.
  arXiv  Detail & Related papers  (2023-03-09T10:41:57Z)
• 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)
• Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling [52.464516118826765]
  We introduce RandLA-Net, an efficient and lightweight neural architecture to infer per-point semantics for large-scale point clouds. The key to our approach is to use random point sampling instead of more complex point selection approaches. Our RandLA-Net can process 1 million points in a single pass up to 200x faster than existing approaches.
  arXiv  Detail & Related papers  (2021-07-06T05:08:34Z)
• 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)
• RANSIC: Fast and Highly Robust Estimation for Rotation Search and Point Cloud Registration using Invariant Compatibility [6.8858952804978335]
  Correspondence-based rotation search and point cloud registration are fundamental problems in robotics and computer vision. We present RANSIC, a fast and highly robust method applicable to both problems based on a new paradigm combining random sampling with invariance and compatibility. In multiple synthetic and real experiments, we demonstrate that RANSIC is fast for use, robust against over 95% outliers, and also able to recall approximately 100% inliers, outperforming other state-of-the-art solvers for both the rotation search and the point cloud registration problems.
  arXiv  Detail & Related papers  (2021-04-19T08:29:34Z)
• IRON: Invariant-based Highly Robust Point Cloud Registration [6.8858952804978335]
  In this paper, we present a non-minimal and highly robust solution for point cloud registration with a great number of outliers. We show that IRON is efficient, highly accurate and robust against as many as 99% outliers whether the scale is known or unknown.
  arXiv  Detail & Related papers  (2021-03-07T13:46:56Z)
• 3DSSD: Point-based 3D Single Stage Object Detector [61.67928229961813]
  We present a point-based 3D single stage object detector, named 3DSSD, achieving a good balance between accuracy and efficiency. Our method outperforms all state-of-the-art voxel-based single stage methods by a large margin, and has comparable performance to two stage point-based methods as well.
  arXiv  Detail & Related papers  (2020-02-24T12:01:58Z)
• 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.