Space-Partitioning RANSAC

• URL: http://arxiv.org/abs/2111.12385v1
• Date: Wed, 24 Nov 2021 10:10:04 GMT
• Title: Space-Partitioning RANSAC
• Authors: Daniel Barath, Gabor Valasek
• Abstract summary: A new algorithm is proposed to accelerate RANSAC model quality calculations. The method is based on partitioning the joint correspondence space, e.g., 2D-2D point correspondences, into a pair of regular grids. It reduces the RANSAC run-time by 41% with provably no deterioration in the accuracy.
• Score: 30.255457622022487
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: A new algorithm is proposed to accelerate RANSAC model quality calculations. The method is based on partitioning the joint correspondence space, e.g., 2D-2D point correspondences, into a pair of regular grids. The grid cells are mapped by minimal sample models, estimated within RANSAC, to reject correspondences that are inconsistent with the model parameters early. The proposed technique is general. It works with arbitrary transformations even if a point is mapped to a point set, e.g., as a fundamental matrix maps to epipolar lines. The method is tested on thousands of image pairs from publicly available datasets on fundamental and essential matrix, homography and radially distorted homography estimation. On average, it reduces the RANSAC run-time by 41% with provably no deterioration in the accuracy. It can be straightforwardly plugged into state-of-the-art RANSAC frameworks, e.g. VSAC.

Related papers

• RANSAC Back to SOTA: A Two-stage Consensus Filtering for Real-time 3D Registration [15.81035895734261]
  Correspondence-based point cloud registration (PCR) plays a key role in robotics and computer vision. We propose a two-stage consensus filtering (TCF) that elevates RANSAC to state-of-the-art (SOTA) speed and accuracy.
  arXiv  Detail & Related papers  (2024-10-21T06:46:49Z)
• Disentangled Representation Learning with the Gromov-Monge Gap [65.73194652234848]
  Learning disentangled representations from unlabelled data is a fundamental challenge in machine learning. We introduce a novel approach to disentangled representation learning based on quadratic optimal transport. We demonstrate the effectiveness of our approach for quantifying disentanglement across four standard benchmarks.
  arXiv  Detail & Related papers  (2024-07-10T16:51:32Z)
• Linear Relative Pose Estimation Founded on Pose-only Imaging Geometry [18.270330814061325]
  This paper introduces a linear relative pose estimation algorithm for n $( n geq 6$) point pairs. It is founded on the recent pose-only imaging geometry to filter out outliers by proper reweighting. It achieves relative rotation accuracy improvement of 2 $sim$ 10 times in face of as large as 80% outliers.
  arXiv  Detail & Related papers  (2024-01-24T10:35:34Z)
• $H$-RANSAC, an algorithmic variant for Homography image transform from featureless point sets: application to video-based football analytics [1.1970409518725493]
  We propose a generalized RANSAC algorithm to retrieve homography from sets of transformations without local feature vectors and point pairing. The proposed methodology is tested on a large dataset of images acquired by cameras during real football matches, where radically different views at each 12 timestamp are to be matched.
  arXiv  Detail & Related papers  (2023-10-07T20:56:39Z)
• Learning the Positions in CountSketch [49.57951567374372]
  We consider sketching algorithms which first compress data by multiplication with a random sketch matrix, and then apply the sketch to quickly solve an optimization problem. In this work, we propose the first learning-based algorithms that also optimize the locations of the non-zero entries.
  arXiv  Detail & Related papers  (2023-06-11T07:28:35Z)
• LSG-CPD: Coherent Point Drift with Local Surface Geometry for Point Cloud Registration [1.8876415010297891]
  We propose a novel method called CPD with Local Surface Geometry (LSG-CPD) for rigid point cloud registration. Our method adaptively adds different levels of point-to-plane penalization on top of the point-to-point penalization based on the flatness of the local surface. It is significantly faster than modern implementations of CPD.
  arXiv  Detail & Related papers  (2021-03-28T03:46:41Z)
• Finding Geometric Models by Clustering in the Consensus Space [61.65661010039768]
  We propose a new algorithm for finding an unknown number of geometric models, e.g., homographies. We present a number of applications where the use of multiple geometric models improves accuracy. These include pose estimation from multiple generalized homographies; trajectory estimation of fast-moving objects.
  arXiv  Detail & Related papers  (2021-03-25T14:35:07Z)
• Efficient Initial Pose-graph Generation for Global SfM [56.38930515826556]
  We propose ways to speed up the initial pose-graph generation for global Structure-from-Motion algorithms. The algorithms are tested on 402130 image pairs from the 1DSfM dataset.
  arXiv  Detail & Related papers  (2020-11-24T09:32:03Z)
• Making Affine Correspondences Work in Camera Geometry Computation [62.7633180470428]
  Local features provide region-to-region rather than point-to-point correspondences. We propose guidelines for effective use of region-to-region matches in the course of a full model estimation pipeline. Experiments show that affine solvers can achieve accuracy comparable to point-based solvers at faster run-times.
  arXiv  Detail & Related papers  (2020-07-20T12:07:48Z)
• 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)

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.