Transformation Decoupling Strategy based on Screw Theory for Deterministic Point Cloud Registration with Gravity Prior

• URL: http://arxiv.org/abs/2311.01432v1
• Date: Thu, 2 Nov 2023 17:46:25 GMT
• Title: Transformation Decoupling Strategy based on Screw Theory for Deterministic Point Cloud Registration with Gravity Prior
• Abstract summary: This paper focuses on addressing the robust correspondence-based registration problem with gravity prior. We propose a novel transformation decoupling strategy by leveraging screw theory. Our method is more efficient and robust than state-of-the-art methods, even when dealing with outlier rates exceeding 99%.
• Score: 18.2236540834986
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Point cloud registration is challenging in the presence of heavy outlier correspondences. This paper focuses on addressing the robust correspondence-based registration problem with gravity prior that often arises in practice. The gravity directions are typically obtained by inertial measurement units (IMUs) and can reduce the degree of freedom (DOF) of rotation from 3 to 1. We propose a novel transformation decoupling strategy by leveraging screw theory. This strategy decomposes the original 4-DOF problem into three sub-problems with 1-DOF, 2-DOF, and 1-DOF, respectively, thereby enhancing the computation efficiency. Specifically, the first 1-DOF represents the translation along the rotation axis and we propose an interval stabbing-based method to solve it. The second 2-DOF represents the pole which is an auxiliary variable in screw theory and we utilize a branch-and-bound method to solve it. The last 1-DOF represents the rotation angle and we propose a global voting method for its estimation. The proposed method sequentially solves three consensus maximization sub-problems, leading to efficient and deterministic registration. In particular, it can even handle the correspondence-free registration problem due to its significant robustness. Extensive experiments on both synthetic and real-world datasets demonstrate that our method is more efficient and robust than state-of-the-art methods, even when dealing with outlier rates exceeding 99%.

Related papers

• Efficient and Robust Absolute Pose Estimation via Gravity-Prior-Driven Transformation Decoupling and Pose Refinement [41.96293293890405]
  In this paper, we propose a novel transformation strategy that exploits geometric relations derived from the gravity prior.<n>For the 1-DoF rotation angle, we apply a one-dimensional global voting algorithm for optimal estimation.<n>To obtain accurate pose results, we introduce a novel pose refinement algorithm to enhance the accuracy of both rotation and translation.
  arXiv  Detail & Related papers  (2026-09-01T04:43:39Z)
• When Is Rank-1 Steering Cheap? Geometry, Granularity, and Budgeted Search [61.73232505100331]
  Activation steering offers a lightweight way to control LLMs without retraining, but its effectiveness varies sharply across concepts.<n>We formalize rank-1 steering as a budget-constrained optimization over intervention layer and coefficient.<n>We present textitGRACE, a Granularity- and Representation-Aware Concept Engineering framework that uses activation geometry to diagnose the dominant source of steering difficulty.
  arXiv  Detail & Related papers  (2026-05-09T14:26:49Z)
• Test-Time Scaling with Diffusion Language Models via Reward-Guided Stitching [66.39914384073145]
  We propose a self-consistency framework that turns cheap diffusion-sampled reasoning into a reusable pool of step-level candidates.<n>We find that step-level recombination is most beneficial on harder problems.<n>Our training-free framework improves average accuracy by up to 2 across six math and coding tasks.
  arXiv  Detail & Related papers  (2026-02-26T11:08:39Z)
• Fractured Chain-of-Thought Reasoning [61.647243580650446]
  We introduce Fractured Sampling, a unified inference-time strategy that interpolates between full CoT and solution-only sampling.<n>We show that Fractured Sampling consistently achieves superior accuracy-cost trade-offs, yielding steep log-linear scaling gains in Pass@k versus token budget.
  arXiv  Detail & Related papers  (2025-05-19T11:30:41Z)
• Escaping Saddle Points in Heterogeneous Federated Learning via Distributed SGD with Communication Compression [42.85797250438604]
  We propose a novel algorithm Power-EF that only communicates compressed information via a novel error-feedback scheme. Power-EF is the first distributed and compressed SGD algorithm that provably escapes saddle points in heterogeneous FL without any data homogeneity assumptions. Our theory improves/recovers previous results, while extending to much more tolerant settings on the local data.
  arXiv  Detail & Related papers  (2023-10-29T16:24:53Z)
• Momentum Provably Improves Error Feedback! [54.93799845077906]
  When untreated, errors caused by compression propagate exponential training behavior. EF21-SGDM improves the communication and sample complexities of previous error feedback algorithms.
  arXiv  Detail & Related papers  (2023-05-24T13:52:02Z)
• Efficient and Deterministic Search Strategy Based on Residual Projections for Point Cloud Registration with Correspondences [18.509532571594995]
  Current 3D feature matching approaches commonly lead to numerous outlier correspondences, making outlier-robust registration techniques indispensable. We introduce a novel pose decoupling strategy based on residual projections, decomposing the raw registration problem into three sub-problems. Our method can be adapted to address the challenging problem of simultaneous pose and registration.
  arXiv  Detail & Related papers  (2023-05-19T14:52:40Z)
• D4FT: A Deep Learning Approach to Kohn-Sham Density Functional Theory [79.50644650795012]
  We propose a deep learning approach to solve Kohn-Sham Density Functional Theory (KS-DFT) We prove that such an approach has the same expressivity as the SCF method, yet reduces the computational complexity. In addition, we show that our approach enables us to explore more complex neural-based wave functions.
  arXiv  Detail & Related papers  (2023-03-01T10:38:10Z)
• FedDA: Faster Framework of Local Adaptive Gradient Methods via Restarted Dual Averaging [104.41634756395545]
  Federated learning (FL) is an emerging learning paradigm to tackle massively distributed data. We propose textbfFedDA, a novel framework for local adaptive gradient methods. We show that textbfFedDA-MVR is the first adaptive FL algorithm that achieves this rate.
  arXiv  Detail & Related papers  (2023-02-13T05:10:30Z)
• Faster Adaptive Federated Learning [84.38913517122619]
  Federated learning has attracted increasing attention with the emergence of distributed data. In this paper, we propose an efficient adaptive algorithm (i.e., FAFED) based on momentum-based variance reduced technique in cross-silo FL.
  arXiv  Detail & Related papers  (2022-12-02T05:07:50Z)
• Robust Manifold Nonnegative Tucker Factorization for Tensor Data Representation [44.845291873747335]
  Nonnegative Tucker Factorization (NTF) minimizes the euclidean distance or Kullback-Leibler divergence between the original data and its low-rank approximation. NTF suffers from rotational ambiguity, whose solutions with and without rotation transformations are equally in the sense of yielding the maximum likelihood. We propose three Robust Manifold NTF algorithms to handle outliers by incorporating structural knowledge about the outliers.
  arXiv  Detail & Related papers  (2022-11-08T01:16:21Z)
• A dual semismooth Newton based augmented Lagrangian method for large-scale linearly constrained sparse group square-root Lasso problems [0.0]
  This paper focuses on the numerical computation of large-scale linearly constrained sparse group square-root Lasso problems. We propose a dual semismooth Newton (SSN) based augmented Lagrangian method (ALM) for it. Numerical experiments demonstrate the efficiency of the proposed algorithm.
  arXiv  Detail & Related papers  (2021-11-27T12:20:43Z)
• Hybrid Trilinear and Bilinear Programming for Aligning Partially Overlapping Point Sets [85.71360365315128]
  In many applications, we need algorithms which can align partially overlapping point sets are invariant to the corresponding corresponding RPM algorithm. We first show that the objective is a cubic bound function. We then utilize the convex envelopes of trilinear and bilinear monomial transformations to derive its lower bound. We next develop a branch-and-bound (BnB) algorithm which only branches over the transformation variables and runs efficiently.
  arXiv  Detail & Related papers  (2021-01-19T04:24:23Z)
• On the Practicality of Differential Privacy in Federated Learning by Tuning Iteration Times [51.61278695776151]
  Federated Learning (FL) is well known for its privacy protection when training machine learning models among distributed clients collaboratively. Recent studies have pointed out that the naive FL is susceptible to gradient leakage attacks. Differential Privacy (DP) emerges as a promising countermeasure to defend against gradient leakage attacks.
  arXiv  Detail & Related papers  (2021-01-11T19:43:12Z)
• TEASER: Fast and Certifiable Point Cloud Registration [30.19476775410544]
  First fast and robust certifiable algorithm for the registration of 3D points in the presence of large amounts of outliers. Second fast and robust certifiable translation, named TEASER++, uses graduated non-componentity to solve a large subproblem.
  arXiv  Detail & Related papers  (2020-01-21T18:56:00Z)

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.