Accelerating Outlier-robust Rotation Estimation by Stereographic Projection

• URL: http://arxiv.org/abs/2502.06337v1
• Date: Mon, 10 Feb 2025 10:37:36 GMT
• Title: Accelerating Outlier-robust Rotation Estimation by Stereographic Projection
• Authors: Taosi Xu, Yinlong Liu, Xianbo Wang, Zhi-Xin Yang,
• Abstract summary: We propose an efficient and robust rotation estimation method.<n>Our method can solve large-scale ($106$ points) and severely corrupted (90% outlier rate) rotation estimation problems within 0.07 seconds.
• Score: 11.031734331985975
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Rotation estimation plays a fundamental role in many computer vision and robot tasks. However, efficiently estimating rotation in large inputs containing numerous outliers (i.e., mismatches) and noise is a recognized challenge. Many robust rotation estimation methods have been designed to address this challenge. Unfortunately, existing methods are often inapplicable due to their long computation time and the risk of local optima. In this paper, we propose an efficient and robust rotation estimation method. Specifically, our method first investigates geometric constraints involving only the rotation axis. Then, it uses stereographic projection and spatial voting techniques to identify the rotation axis and angle. Furthermore, our method efficiently obtains the optimal rotation estimation and can estimate multiple rotations simultaneously. To verify the feasibility of our method, we conduct comparative experiments using both synthetic and real-world data. The results show that, with GPU assistance, our method can solve large-scale ($10^6$ points) and severely corrupted (90\% outlier rate) rotation estimation problems within 0.07 seconds, with an angular error of only 0.01 degrees, which is superior to existing methods in terms of accuracy and efficiency.

Related papers

• Linearly Solving Robust Rotation Estimation [11.8260722786548]
  We propose an easily understandable-based method to solve rotation estimation problems.<n>The proposed method exhibits exceptional robustness to noise and outliers and can be computed in parallel with graphics processing units.<n>We conduct controlled experiments and demonstrate the superiority of our proposed method.
  arXiv  Detail & Related papers  (2025-06-13T08:00:03Z)
• Irrational Complex Rotations Empower Low-bit Optimizers [102.56966165088963]
  We propose a novel state compression algorithm, namely $pi$-Quant, for memory-efficient training.<n>We show that it can reduce the bit-width of parameters to 3.32-bit, achieving a 75% reduction in parameter scale and a 40% decrease in GPU memory usage.
  arXiv  Detail & Related papers  (2025-01-22T14:17:57Z)
• Multiple Rotation Averaging with Constrained Reweighting Deep Matrix Factorization [22.487393413405954]
  Multiple rotation averaging plays a crucial role in computer vision and robotics domains. This paper proposes an effective rotation averaging method for mining data patterns in a learning manner.
  arXiv  Detail & Related papers  (2024-09-15T16:50:27Z)
• Robust Single Rotation Averaging Revisited [14.533304890042361]
  We propose a novel method for robust single rotation averaging that can efficiently handle an extremely large fraction of outliers. Our method is robust against up to 99% outliers given a sufficient number of accurate inliers, outperforming the current state of the art.
  arXiv  Detail & Related papers  (2023-09-11T11:35:17Z)
• Vanishing Point Estimation in Uncalibrated Images with Prior Gravity Direction [82.72686460985297]
  We tackle the problem of estimating a Manhattan frame. We derive two new 2-line solvers, one of which does not suffer from singularities affecting existing solvers. We also design a new non-minimal method, running on an arbitrary number of lines, to boost the performance in local optimization.
  arXiv  Detail & Related papers  (2023-08-21T13:03:25Z)
• Revisiting Rotation Averaging: Uncertainties and Robust Losses [51.64986160468128]
  We argue that the main problem of current methods is the minimized cost function that is only weakly connected with the input data via the estimated epipolar. We propose to better model the underlying noise distributions by directly propagating the uncertainty from the point correspondences into the rotation averaging.
  arXiv  Detail & Related papers  (2023-03-09T11:51:20Z)
• RAGO: Recurrent Graph Optimizer For Multiple Rotation Averaging [62.315673415889314]
  This paper proposes a deep recurrent Rotation Averaging Graph (RAGO) for Multiple Rotation Averaging (MRA) Our framework is a real-time learning-to-optimize rotation averaging graph with a tiny size deployed for real-world applications.
  arXiv  Detail & Related papers  (2022-12-14T13:19:40Z)
• ART-Point: Improving Rotation Robustness of Point Cloud Classifiers via Adversarial Rotation [89.47574181669903]
  In this study, we show that the rotation robustness of point cloud classifiers can also be acquired via adversarial training. Specifically, our proposed framework named ART-Point regards the rotation of the point cloud as an attack. We propose a fast one-step optimization to efficiently reach the final robust model.
  arXiv  Detail & Related papers  (2022-03-08T07:20:16Z)
• RSDet++: Point-based Modulated Loss for More Accurate Rotated Object Detection [53.57176614020894]
  We classify the discontinuity of loss in both five-param and eight-param rotated object detection methods as rotation sensitivity error (RSE) We introduce a novel modulated rotation loss to alleviate the problem and propose a rotation sensitivity detection network (RSDet) To further improve the accuracy of our method on objects smaller than 10 pixels, we introduce a novel RSDet++.
  arXiv  Detail & Related papers  (2021-09-24T11:57:53Z)
• Efficient Algorithms for Rotation Averaging Problems [17.101725065752486]
  The averaging problem is a fundamental task in computer applications. We propose a block-based averaging algorithm with guaranteed convergence to stationary points. We also propose an alternative averaging algorithm by applying upper-bound minimization.
  arXiv  Detail & Related papers  (2021-03-18T05:22:45Z)

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.