Hybrid Rotation Averaging: A Fast and Robust Rotation Averaging Approach

• URL: http://arxiv.org/abs/2101.09116v2
• Date: Sun, 31 Jan 2021 11:50:58 GMT
• Title: Hybrid Rotation Averaging: A Fast and Robust Rotation Averaging Approach
• Authors: Yu Chen and Ji Zhao and Laurent Kneip
• Abstract summary: We propose a hybrid rotation averaging approach to incremental Structure from Motion (SfM) Global RAs ensure global optimality in low noise conditions, but they are inefficient and may easily deviate under the influence of outliers or elevated noise levels. We demonstrate high practicality of the proposed method as bad camera poses are effectively corrected and drift is reduced.
• Score: 28.56388668402907
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We address rotation averaging (RA) and its application to real-world 3D reconstruction. Local optimisation based approaches are the defacto choice, though they only guarantee a local optimum. Global optimizers ensure global optimality in low noise conditions, but they are inefficient and may easily deviate under the influence of outliers or elevated noise levels. We push the envelope of rotation averaging by leveraging the advantages of global RA method and local RA method. Combined with a fast view graph filtering as preprocessing, the proposed hybrid approach is robust to outliers. We apply the proposed hybrid rotation averaging approach to incremental Structure from Motion (SfM) by adding the resulting global rotations as regularizers to bundle adjustment. Overall, we demonstrate high practicality of the proposed method as bad camera poses are effectively corrected and drift is reduced.

Related papers

• Efficient Federated Learning via Local Adaptive Amended Optimizer with Linear Speedup [90.26270347459915]
  We propose a novel momentum-based algorithm via utilizing the global descent locally adaptive. textitLADA could greatly reduce the communication rounds and achieves higher accuracy than several baselines.
  arXiv  Detail & Related papers  (2023-07-30T14:53:21Z)
• Dynamic Regularized Sharpness Aware Minimization in Federated Learning: Approaching Global Consistency and Smooth Landscape [59.841889495864386]
  In federated learning (FL), a cluster of local clients are chaired under the coordination of a global server. Clients are prone to overfit into their own optima, which extremely deviates from the global objective. ttfamily FedSMOO adopts a dynamic regularizer to guarantee the local optima towards the global objective. Our theoretical analysis indicates that ttfamily FedSMOO achieves fast $mathcalO (1/T)$ convergence rate with low bound generalization.
  arXiv  Detail & Related papers  (2023-05-19T10:47:44Z)
• 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)
• Scalable Distributional Robustness in a Class of Non Convex Optimization with Guarantees [7.541571634887807]
  Distributionally robust optimization (DRO) has shown robustness in learning as well as sample based problems. We propose a mixed-integer clustering program (MISOCP) which does not scale enough to solve problems with real worldsets.
  arXiv  Detail & Related papers  (2022-05-31T09:07:01Z)
• 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)
• Rotation Coordinate Descent for Fast Globally Optimal Rotation Averaging [47.3713707521106]
  We present a fast algorithm that achieves global optimality called rotation coordinate descent (RCD) Unlike block coordinate descent (BCD) which solves SDP by updating the semidefinite matrix in a row-by-row fashion, RCD directly maintains and updates all valid rotations throughout the iterations. We mathematically prove the convergence of our algorithm and empirically show its superior efficiency over state-of-the-art global methods.
  arXiv  Detail & Related papers  (2021-03-15T11:31:34Z)
• Pushing the Envelope of Rotation Averaging for Visual SLAM [69.7375052440794]
  We propose a novel optimization backbone for visual SLAM systems. We leverage averaging to improve the accuracy, efficiency and robustness of conventional monocular SLAM systems. Our approach can exhibit up to 10x faster with comparable accuracy against the state-art on public benchmarks.
  arXiv  Detail & Related papers  (2020-11-02T18:02:26Z)
• Shonan Rotation Averaging: Global Optimality by Surfing $SO(p)^n$ [26.686173666277725]
  Shonan Rotation Averaging is guaranteed to recover globally optimal solutions under mild assumptions on the measurement noise. Our method employs semidefinite relaxation in order to recover provably globally optimal solutions of the rotation averaging problem.
  arXiv  Detail & Related papers  (2020-08-06T16:08:23Z)

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.