Spectral Consistency-Guided Multiview Point Cloud Registration for Low-Overlap Scenes

• URL: http://arxiv.org/abs/2609.12417v1
• Date: Fri, 11 Sep 2026 04:11:42 GMT
• Title: Spectral Consistency-Guided Multiview Point Cloud Registration for Low-Overlap Scenes
• Abstract summary: We propose GMPCR, a non-learning-based framework for efficient and robust multiview point cloud registration.<n>It builds a refined second-order compatibility structure from initial correspondences and uses its dominant spectral response to evaluate both correspondence reliability and scan-pair confidence.<n>Experiments on 3DMatch, 3DLoMatch, ScanNet, and ETH demonstrate the effectiveness of GMPCR.
• Score: 10.39937039338342
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multiview point cloud registration is particularly challenging in low-overlap scenes, where reliable correspondences are limited and incorrect pairwise transformations can affect global pose estimation. In addition, registering all scan pairs is computationally expensive because many pairs provide weak geometric information. To address these problems, we propose GMPCR, a non-learning-based spectral consistency-guided framework for efficient and robust multiview point cloud registration. GMPCR builds a refined second-order compatibility structure from initial correspondences and uses its dominant spectral response to evaluate both correspondence reliability and scan-pair confidence. This allows unreliable correspondences to be filtered and informative scan pairs to be selected before relative transformation estimation, leading to a sparse pose graph and reduced pairwise registration cost. For each retained scan pair, maximal-clique-based hypothesis generation is used to estimate reliable relative transformations. The resulting pose graph is further refined by an adaptive history-aware synchronization scheme, in which the effect of residual history is adjusted according to changes in the global rotation residual. A recovery mechanism also allows down-weighted edges to regain confidence when their global consistency improves. Experiments on 3DMatch, 3DLoMatch, ScanNet, and ETH demonstrate the effectiveness of GMPCR. It achieves registration recalls of 97.2% and 89.6% on 3DMatch and 3DLoMatch, respectively, while maintaining competitive performance on ScanNet and ETH. The results show that GMPCR provides a favorable balance among registration accuracy, robustness to low overlap, and computational efficiency. The code is publicly available at https://github.com/swccj/gmpcr.

Related papers

• A Step Towards Robust Unsupervised Domain Adaptation via Fine-Tuning and Reinforcement Learning [2.436631469537453]
  We propose textbfSFT+RL, a two-stage robust UDA framework that integratesSupervised Fine Tuning and Reinforcement Learning.<n>textbfSFT+RL achieves average improvements of textbf10.2% in clean accuracy and textbf15.8% in adversarial robustness across three datasets.
  arXiv  Detail & Related papers  (2026-07-03T20:56:12Z)
• DOC-GS: Dual-Domain Observation and Calibration for Reliable Sparse-View Gaussian Splatting [80.43237927269575]
  In this paper, we revisit sparse-view 3DGS reconstruction from a new perspective.<n>We identify the core challenge as the unobservability of Gaussian primitive reliability.<n>Motivated by this observation, we propose a unified Dual-domain Observation and geometrics in rendered images framework.
  arXiv  Detail & Related papers  (2026-04-08T07:01:24Z)
• DC-Reg: Globally Optimal Point Cloud Registration via Tight Bounding with Difference of Convex Programming [43.06401929828342]
  We develop a new framework to achieve globally optimal point registration interplay.<n>We show that it achieves significantly faster convergence to extreme noise and the outlier-of-the-art global to extreme noise.
  arXiv  Detail & Related papers  (2026-03-26T13:38:45Z)
• FUSER: Feed-Forward MUltiview 3D Registration Transformer and SE(3)$^N$ Diffusion Refinement [39.19949818461193]
  F is the first feed-forward multiview registration transformer that processes all scans in a unified, compact latent space.<n>F predicts global poses without any pairwise estimation.<n>Experiments on 3DMatch, ScanNet and ArkitScenes demonstrate that our approach achieves the superior registration accuracy and outstanding computational efficiency.
  arXiv  Detail & Related papers  (2025-12-10T07:11:22Z)
• Continual Action Quality Assessment via Adaptive Manifold-Aligned Graph Regularization [53.82400605816587]
  Action Quality Assessment (AQA) quantifies human actions in videos, supporting applications in sports scoring, rehabilitation, and skill evaluation.<n>A major challenge lies in the non-stationary nature of quality distributions in real-world scenarios.<n>We introduce Continual AQA (CAQA), which equips with Continual Learning capabilities to handle evolving distributions.
  arXiv  Detail & Related papers  (2025-10-08T10:09:47Z)
• Robust Partial 3D Point Cloud Registration via Confidence Estimation under Global Context [12.216399037814012]
  Partial point cloud registration is essential for autonomous perception and 3D scene understanding.<n>We propose Confidence Estimation under Global Context (CEGC), a unified, confidence-driven framework for robust partial 3D registration.<n>CEGC enables accurate alignment in complex scenes by jointly modeling overlap confidence and correspondence reliability within a shared global context.
  arXiv  Detail & Related papers  (2025-09-29T04:36:55Z)
• Cross3DReg: Towards a Large-scale Real-world Cross-source Point Cloud Registration Benchmark [57.42211080221526]
  Cross-source point cloud registration, which aims to align point cloud data from different sensors, is a fundamental task in 3D vision.<n>The lack of publicly available large-scale real-world datasets for training the deep registration models, and the inherent differences in point clouds captured by multiple sensors pose challenges.<n>We construct Cross3DReg, the currently largest and real-world multi-modal cross-source point cloud registration dataset.<n>A visual-geometric attention guided matching module is proposed to enhance the consistency of cross-source point cloud features.
  arXiv  Detail & Related papers  (2025-09-08T09:01:13Z)
• Robust Multiview Point Cloud Registration with Reliable Pose Graph Initialization and History Reweighting [63.95845583460312]
  We present a new method for the multiview registration of point cloud. Our method achieves 11% higher registration recall on the 3DMatch dataset and 13% lower registration errors on the ScanNet dataset.
  arXiv  Detail & Related papers  (2023-04-02T06:43:40Z)
• A recursive robust filtering approach for 3D registration [3.5270468102327004]
  The proposed method has four advantages that have not yet occurred altogether in any previous solution. It is able to deal with inherent noise contaminating sensory data. It is robust to uncertainties caused by noisy feature localisation.
  arXiv  Detail & Related papers  (2021-10-28T07:50:02Z)
• Fast and Robust Certifiable Estimation of the Relative Pose Between Two Calibrated Cameras [0.0]
  Relative Pose problem (RPp) for cameras aims to the relative orientation translation (pose) given a set of pair-wise rotations between two cameras. In this paper, we introduce a family of certifiers that is shown to increase the ratio of detected optimal solutions. We prove through synthetic and real data that the proposed framework provides a fast and robust relative pose estimation.
  arXiv  Detail & Related papers  (2021-01-21T10:07:05Z)
• Canny-VO: Visual Odometry with RGB-D Cameras based on Geometric 3D-2D Edge Alignment [85.32080531133799]
  This paper reviews the classical problem of free-form curve registration and applies it to an efficient RGBD visual odometry system called Canny-VO. Two replacements for the distance transformation commonly used in edge registration are proposed: Approximate Nearest Neighbour Fields and Oriented Nearest Neighbour Fields. 3D2D edge alignment benefits from these alternative formulations in terms of both efficiency and accuracy.
  arXiv  Detail & Related papers  (2020-12-15T11:42:17Z)
• Triple Wins: Boosting Accuracy, Robustness and Efficiency Together by Enabling Input-Adaptive Inference [119.19779637025444]
  Deep networks were recently suggested to face the odds between accuracy (on clean natural images) and robustness (on adversarially perturbed images) This paper studies multi-exit networks associated with input-adaptive inference, showing their strong promise in achieving a "sweet point" in cooptimizing model accuracy, robustness and efficiency.
  arXiv  Detail & Related papers  (2020-02-24T00:40:22Z)

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.