Deep-PE: A Learning-Based Pose Evaluator for Point Cloud Registration

• URL: http://arxiv.org/abs/2405.16085v1
• Date: Sat, 25 May 2024 06:32:32 GMT
• Title: Deep-PE: A Learning-Based Pose Evaluator for Point Cloud Registration
• Abstract summary: Deep-PE is a lightweight, learning-based pose evaluator designed to enhance the accuracy of pose selection. Our network incorporates a Pose-Aware Attention (PAA) module to simulate and learn the alignment status of point clouds. Deep-PE significantly outperforms state-of-the-art methods by at least 8% and 11% in registration recall.
• Score: 35.77554768853786
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In the realm of point cloud registration, the most prevalent pose evaluation approaches are statistics-based, identifying the optimal transformation by maximizing the number of consistent correspondences. However, registration recall decreases significantly when point clouds exhibit a low overlap rate, despite efforts in designing feature descriptors and establishing correspondences. In this paper, we introduce Deep-PE, a lightweight, learning-based pose evaluator designed to enhance the accuracy of pose selection, especially in challenging point cloud scenarios with low overlap. Our network incorporates a Pose-Aware Attention (PAA) module to simulate and learn the alignment status of point clouds under various candidate poses, alongside a Pose Confidence Prediction (PCP) module that predicts the likelihood of successful registration. These two modules facilitate the learning of both local and global alignment priors. Extensive tests across multiple benchmarks confirm the effectiveness of Deep-PE. Notably, on 3DLoMatch with a low overlap rate, Deep-PE significantly outperforms state-of-the-art methods by at least 8% and 11% in registration recall under handcrafted FPFH and learning-based FCGF descriptors, respectively. To the best of our knowledge, this is the first study to utilize deep learning to select the optimal pose without the explicit need for input correspondences.

Related papers

• DPA-I2P: Depth-Guided Projective Alignment for Image-to-Point-Cloud Registration in Autonomous Driving [12.021166543643941]
  Image-to-Point Cloud Registration aims to estimate the camera pose of a given image within a 3D scene point cloud.<n>Recent implicit correspondence learning methods have improved registration performance by learning cross-modal alignment.<n>We propose Depth-Guided Projective Alignment for Image-to-Point-Cloud Registration (DPA-I2P)
  arXiv  Detail & Related papers  (2026-08-27T04:01:15Z)
• Cross-Coordinate Correspondence Pruning for Image-to-Point Cloud Registration [70.44225088078274]
  We propose a novel Cross-Coordinate Correspondences Pruning (CCP) strategy to acquire sufficient inliers while ensuring a low outlier ratio.<n>Our method achieves a significant performance improvement, surpassing existing state-of-the-art methods by at least 8.6% in Registration Recall across various benchmarks.
  arXiv  Detail & Related papers  (2026-07-19T11:45:14Z)
• GBPP: Grasp-Aware Base Placement Prediction for Robots via Two-Stage Learning [10.736029638634504]
  GBPP is a fast learning based scorer that selects a robot base pose for grasping from a single RGBD snapshot.<n>The method uses a two stage curriculum: (1) a simple distance-visibility rule auto-labels a large dataset at low cost; and (2) a smaller set of high fidelity simulation trials refine the model to match true grasp outcomes.
  arXiv  Detail & Related papers  (2025-09-15T05:25:40Z)
• LifelongPR: Lifelong knowledge fusion for point cloud place recognition based on replay and prompt learning [15.464706470200337]
  Point cloud place recognition (PCPR) plays a crucial role in photogrammetry and robotics applications.<n>Existing PCPR models often suffer from catastrophic forgetting, leading to significant performance degradation.<n>We propose LifelongPR, a novel continual learning framework for PCPR, which effectively extracts and fuses knowledge from sequential point cloud data.
  arXiv  Detail & Related papers  (2025-07-14T08:13:33Z)
• BiEquiFormer: Bi-Equivariant Representations for Global Point Cloud Registration [28.75341781515012]
  The goal of this paper is to address the problem of global point cloud registration (PCR) i.e., finding the optimal alignment between point clouds. We show that state-of-the-art deep learning methods suffer from huge performance degradation when the point clouds are arbitrarily placed in space.
  arXiv  Detail & Related papers  (2024-07-11T17:58:10Z)
• DIPR: Efficient Point Cloud Registration via Dynamic Iteration [4.491867613612359]
  We introduce a novel Efficient Point Cloud Registration via Dynamic It framework, DIPR, that makes the neural network interactively focus on overlapping points based on sparser input points. Our proposed approach achieves superior registration accuracy while significantly reducing computational time and GPU memory consumption compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-12-05T16:47:46Z)
• Q-REG: End-to-End Trainable Point Cloud Registration with Surface Curvature [81.25511385257344]
  We present a novel solution, Q-REG, which utilizes rich geometric information to estimate the rigid pose from a single correspondence. Q-REG allows to formalize the robust estimation as an exhaustive search, hence enabling end-to-end training. We demonstrate in the experiments that Q-REG is agnostic to the correspondence matching method and provides consistent improvement both when used only in inference and in end-to-end training.
  arXiv  Detail & Related papers  (2023-09-27T20:58:53Z)
• Overlap Bias Matching is Necessary for Point Cloud Registration [21.584033532099134]
  Overlap between point clouds to be registered may be relatively small. We propose an unsupervised network Overlap Bias Matching Network (OBMNet) for partial point cloud registration.
  arXiv  Detail & Related papers  (2023-08-18T07:47:22Z)
• VL4Pose: Active Learning Through Out-Of-Distribution Detection For Pose Estimation [79.50280069412847]
  We introduce VL4Pose, a first principles approach for active learning through out-of-distribution detection. Our solution involves modelling the pose through a simple parametric Bayesian network trained via maximum likelihood estimation. We perform qualitative and quantitative experiments on three datasets: MPII, LSP and ICVL, spanning human and hand pose estimation.
  arXiv  Detail & Related papers  (2022-10-12T09:03:55Z)
• PCKRF: Point Cloud Completion and Keypoint Refinement With Fusion Data for 6D Pose Estimation [33.226033672697795]
  We propose Point Cloud Completion and Keypoint Refinement with Fusion Data (PCKRF), a new pose refinement pipeline for 6D pose estimation. The PCKRF pipeline can be integrated with existing popular 6D pose estimation methods, such as the full flow bidirectional fusion network. Our method exhibits superior stability compared to existing approaches when optimizing initial poses with relatively high precision.
  arXiv  Detail & Related papers  (2022-10-07T10:13:30Z)
• Learning to Register Unbalanced Point Pairs [10.369750912567714]
  Recent 3D registration methods can effectively handle large-scale or partially overlapping point pairs. We present a novel 3D registration method, called UPPNet, for the unbalanced point pairs.
  arXiv  Detail & Related papers  (2022-07-09T08:03:59Z)
• Locally Aware Piecewise Transformation Fields for 3D Human Mesh Registration [67.69257782645789]
  We propose piecewise transformation fields that learn 3D translation vectors to map any query point in posed space to its correspond position in rest-pose space. We show that fitting parametric models with poses by our network results in much better registration quality, especially for extreme poses.
  arXiv  Detail & Related papers  (2021-04-16T15:16:09Z)
• SIMPLE: SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimation [81.03485688525133]
  We propose a novel multi-person pose estimation framework, SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimation (SIMPLE) Specifically, in the training process, we enable SIMPLE to mimic the pose knowledge from the high-performance top-down pipeline. Besides, SIMPLE formulates human detection and pose estimation as a unified point learning framework to complement each other in single-network.
  arXiv  Detail & Related papers  (2021-04-06T13:12:51Z)
• RPM-Net: Robust Point Matching using Learned Features [79.52112840465558]
  RPM-Net is a less sensitive and more robust deep learning-based approach for rigid point cloud registration. Unlike some existing methods, our RPM-Net handles missing correspondences and point clouds with partial visibility.
  arXiv  Detail & Related papers  (2020-03-30T13:45:27Z)

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.