Robust Uncertainty-Aware Multiview Triangulation

• URL: http://arxiv.org/abs/2008.01258v2
• Date: Wed, 5 Aug 2020 14:52:00 GMT
• Title: Robust Uncertainty-Aware Multiview Triangulation
• Authors: Seong Hun Lee, Javier Civera
• Abstract summary: We propose a robust and efficient method for multiview triangulation and uncertainty estimation. Our contribution is threefold: First, we propose an outlier rejection scheme using two-view RANSAC with the midpoint method. Second, we compare different local optimization methods for refining the initial solution and the inlier set. Third, we model the uncertainty of a triangulated point as a function of three factors: the number of cameras, the mean reprojection error and the maximum parallax angle.
• Score: 20.02647320786556
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose a robust and efficient method for multiview triangulation and uncertainty estimation. Our contribution is threefold: First, we propose an outlier rejection scheme using two-view RANSAC with the midpoint method. By prescreening the two-view samples prior to triangulation, we achieve the state-of-the-art efficiency. Second, we compare different local optimization methods for refining the initial solution and the inlier set. With an iterative update of the inlier set, we show that the optimization provides significant improvement in accuracy and robustness. Third, we model the uncertainty of a triangulated point as a function of three factors: the number of cameras, the mean reprojection error and the maximum parallax angle. Learning this model allows us to quickly interpolate the uncertainty at test time. We validate our method through an extensive evaluation.

Related papers

• POPoS: Improving Efficient and Robust Facial Landmark Detection with Parallel Optimal Position Search [34.50794776762681]
  This paper introduces the Parallel Optimal Position Search (POPoS), a high-precision encoding-decoding framework. POPoS employs three key innovations: Pseudo-range multilateration is utilized to correct heatmap errors, enhancing the precision of landmark localization. A single-step parallel algorithm is introduced, significantly enhancing computational efficiency and reducing processing time.
  arXiv  Detail & Related papers  (2024-10-12T16:28:40Z)
• Uncertainty-Aware Testing-Time Optimization for 3D Human Pose Estimation [68.75387874066647]
  We propose an Uncertainty-Aware testing-time optimization framework for 3D human pose estimation. Our approach outperforms the previous best result by a large margin of 4.5% on Human3.6M.
  arXiv  Detail & Related papers  (2024-02-04T04:28:02Z)
• 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)
• Efficient first-order predictor-corrector multiple objective optimization for fair misinformation detection [5.139559672771439]
  Multiple-objective optimization (MOO) aims to simultaneously optimize multiple conflicting objectives and has found important applications in machine learning. We propose a Gauss-Newton approximation that only scales linearly, and that requires only first-order inner-product per iteration. The innovations make predictor-corrector possible for large networks.
  arXiv  Detail & Related papers  (2022-09-15T12:32:15Z)
• Dynamic Iterative Refinement for Efficient 3D Hand Pose Estimation [87.54604263202941]
  We propose a tiny deep neural network of which partial layers are iteratively exploited for refining its previous estimations. We employ learned gating criteria to decide whether to exit from the weight-sharing loop, allowing per-sample adaptation in our model. Our method consistently outperforms state-of-the-art 2D/3D hand pose estimation approaches in terms of both accuracy and efficiency for widely used benchmarks.
  arXiv  Detail & Related papers  (2021-11-11T23:31:34Z)
• Boosting RANSAC via Dual Principal Component Pursuit [24.942079487458624]
  We introduce Dual Principal Component Pursuit (DPCP) as a robust subspace learning method with strong theoretical support and efficient algorithms. Experiments on estimating two-view homographies, fundamental and essential matrices, and three-view homographic tensors show that our approach consistently has higher accuracy than state-of-the-art alternatives.
  arXiv  Detail & Related papers  (2021-10-06T17:04:45Z)
• Robust Distributed Optimization With Randomly Corrupted Gradients [24.253191879453784]
  We propose a first-order distributed optimization algorithm that is provably robust to Byzantine failures-arbitrary and potentially adversarial behavior. Our algorithm achieves order normalization and trustworthy statistical error convergence rates.
  arXiv  Detail & Related papers  (2021-06-28T19:45:25Z)
• Robust, Accurate Stochastic Optimization for Variational Inference [68.83746081733464]
  We show that common optimization methods lead to poor variational approximations if the problem is moderately large. Motivated by these findings, we develop a more robust and accurate optimization framework by viewing the underlying algorithm as producing a Markov chain.
  arXiv  Detail & Related papers  (2020-09-01T19:12:11Z)
• Robust 6D Object Pose Estimation by Learning RGB-D Features [59.580366107770764]
  We propose a novel discrete-continuous formulation for rotation regression to resolve this local-optimum problem. We uniformly sample rotation anchors in SO(3), and predict a constrained deviation from each anchor to the target, as well as uncertainty scores for selecting the best prediction. Experiments on two benchmarks: LINEMOD and YCB-Video, show that the proposed method outperforms state-of-the-art approaches.
  arXiv  Detail & Related papers  (2020-02-29T06:24:55Z)
• 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)

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.