R3PM-Net: Real-time, Robust, Real-world Point Matching Network

• URL: http://arxiv.org/abs/2604.05060v2
• Date: Fri, 10 Apr 2026 09:33:18 GMT
• Title: R3PM-Net: Real-time, Robust, Real-world Point Matching Network
• Abstract summary: This paper introduces R3PM-Net, a lightweight, global-aware, object-level point matching network.<n>Experiments demonstrate that R3PM-Net achieves competitive accuracy with unmatched speed.<n>These results confirm that R3PM-Net offers a robust, high-speed solution for critical industrial applications.
• Score: 2.5553138705231535
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Accurate Point Cloud Registration (PCR) is an important task in 3D data processing, involving the estimation of a rigid transformation between two point clouds. While deep-learning methods have addressed key limitations of traditional non-learning approaches, such as sensitivity to noise, outliers, occlusion, and initialization, they are developed and evaluated on clean, dense, synthetic datasets (limiting their generalizability to real-world industrial scenarios). This paper introduces R3PM-Net, a lightweight, global-aware, object-level point matching network designed to bridge this gap by prioritizing both generalizability and real-time efficiency. To support this transition, two datasets, Sioux-Cranfield and Sioux-Scans, are proposed. They provide an evaluation ground for registering imperfect photogrammetric and event-camera scans to digital CAD models, and have been made publicly available. Extensive experiments demonstrate that R3PM-Net achieves competitive accuracy with unmatched speed. On ModelNet40, it reaches a perfect fitness score of $1$ and inlier RMSE of $0.029$ cm in only $0.007$s, approximately 7 times faster than the state-of-the-art method RegTR. This performance carries over to the Sioux-Cranfield dataset, maintaining a fitness of $1$ and inlier RMSE of $0.030$ cm with similarly low latency. Furthermore, on the highly challenging Sioux-Scans dataset, R3PM-Net successfully resolves edge cases in under 50 ms. These results confirm that R3PM-Net offers a robust, high-speed solution for critical industrial applications, where precision and real-time performance are indispensable. The code and datasets are available at https://github.com/YasiiKB/R3PM-Net.

Related papers

• Synthetic LiDAR Data Generation and Deterministic Downsampling for Point Cloud Classification on the Edge [0.0]
  This paper presents a hardware-constrained workflow optimized for native execution on the Raspberry Pi 5.6%.<n>To account for the reality gap between noiseless, clean computer-aided design (CAD) datasets and real-world sensor data, we use physics-based simulation to construct a synthetic LiDAR dataset.<n>Cross-dataset evaluations demonstrate a substantial drop in classification accuracy when networks trained on clean CAD data are evaluated on synthetic LiDAR sensor data.
  arXiv  Detail & Related papers  (2026-08-07T11:02:55Z)
• Enhancing 3D Point Cloud Classification with ModelNet-R and Point-SkipNet [1.0923877073891444]
  The classification of 3D point clouds is crucial for applications such as autonomous driving, robotics, and augmented reality.<n>The commonly used ModelNet40 dataset suffers from limitations such as inconsistent labeling, 2D data, size mismatches, and inadequate class differentiation.<n>This paper introduces ModelNet-R, a meticulously refined version of ModelNet40 designed to address these issues and serve as a more reliable benchmark.
  arXiv  Detail & Related papers  (2025-09-05T15:57:36Z)
• AutoSynth: Learning to Generate 3D Training Data for Object Point Cloud Registration [69.21282992341007]
  Auto Synth automatically generates 3D training data for point cloud registration. We replace the point cloud registration network with a much smaller surrogate network, leading to a $4056.43$ speedup. Our results on TUD-L, LINEMOD and Occluded-LINEMOD evidence that a neural network trained on our searched dataset yields consistently better performance than the same one trained on the widely used ModelNet40 dataset.
  arXiv  Detail & Related papers  (2023-09-20T09:29:44Z)
• Deep Learning for Day Forecasts from Sparse Observations [60.041805328514876]
  Deep neural networks offer an alternative paradigm for modeling weather conditions. MetNet-3 learns from both dense and sparse data sensors and makes predictions up to 24 hours ahead for precipitation, wind, temperature and dew point. MetNet-3 has a high temporal and spatial resolution, respectively, up to 2 minutes and 1 km as well as a low operational latency.
  arXiv  Detail & Related papers  (2023-06-06T07:07:54Z)
• Rethinking Voxelization and Classification for 3D Object Detection [68.8204255655161]
  The main challenge in 3D object detection from LiDAR point clouds is achieving real-time performance without affecting the reliability of the network. We present a solution to improve network inference speed and precision at the same time by implementing a fast dynamic voxelizer. In addition, we propose a lightweight detection sub-head model for classifying predicted objects and filter out false detected objects.
  arXiv  Detail & Related papers  (2023-01-10T16:22:04Z)
• SVNet: Where SO(3) Equivariance Meets Binarization on Point Cloud Representation [65.4396959244269]
  The paper tackles the challenge by designing a general framework to construct 3D learning architectures. The proposed approach can be applied to general backbones like PointNet and DGCNN. Experiments on ModelNet40, ShapeNet, and the real-world dataset ScanObjectNN, demonstrated that the method achieves a great trade-off between efficiency, rotation, and accuracy.
  arXiv  Detail & Related papers  (2022-09-13T12:12:19Z)
• ANNETTE: Accurate Neural Network Execution Time Estimation with Stacked Models [56.21470608621633]
  We propose a time estimation framework to decouple the architectural search from the target hardware. The proposed methodology extracts a set of models from micro- kernel and multi-layer benchmarks and generates a stacked model for mapping and network execution time estimation. We compare estimation accuracy and fidelity of the generated mixed models, statistical models with the roofline model, and a refined roofline model for evaluation.
  arXiv  Detail & Related papers  (2021-05-07T11:39:05Z)
• RPSRNet: End-to-End Trainable Rigid Point Set Registration Network using Barnes-Hut $2^D$-Tree Representation [13.351162559710124]
  We propose RPSRNet - a novel end-to-end trainable deep neural network for rigid point set registration. We use a novel $2D$-tree representation for the input point sets and a hierarchical deep feature embedding in the neural network. We achieve an inference speed of 12-15ms to register a pair of input point clouds as large as 250K.
  arXiv  Detail & Related papers  (2021-04-12T10:16:09Z)
• Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection [99.16162624992424]
  We devise a simple but effective voxel-based framework, named Voxel R-CNN. By taking full advantage of voxel features in a two stage approach, our method achieves comparable detection accuracy with state-of-the-art point-based models. Our results show that Voxel R-CNN delivers a higher detection accuracy while maintaining a realtime frame processing rate, emphi.e, at a speed of 25 FPS on an NVIDIA 2080 Ti GPU.
  arXiv  Detail & Related papers  (2020-12-31T17:02:46Z)
• Fully Dynamic Inference with Deep Neural Networks [19.833242253397206]
  Two compact networks, called Layer-Net (L-Net) and Channel-Net (C-Net), predict on a per-instance basis which layers or filters/channels are redundant and therefore should be skipped. On the CIFAR-10 dataset, LC-Net results in up to 11.9$times$ fewer floating-point operations (FLOPs) and up to 3.3% higher accuracy compared to other dynamic inference methods. On the ImageNet dataset, LC-Net achieves up to 1.4$times$ fewer FLOPs and up to 4.6% higher Top-1 accuracy than the other methods.
  arXiv  Detail & Related papers  (2020-07-29T23:17:48Z)
• AANet: Adaptive Aggregation Network for Efficient Stereo Matching [33.39794232337985]
  Current state-of-the-art stereo models are mostly based on costly 3D convolutions. We propose a sparse points based intra-scale cost aggregation method to alleviate the edge-fattening issue. We also approximate traditional cross-scale cost aggregation algorithm with neural network layers to handle large textureless regions.
  arXiv  Detail & Related papers  (2020-04-20T18:07:55Z)
• StickyPillars: Robust and Efficient Feature Matching on Point Clouds using Graph Neural Networks [16.940377259203284]
  StickyPillars is a fast, accurate and extremely robust deep middle-end 3D feature matching method on point clouds. We present state-of-art art accuracy results on the registration problem demonstrated on the KITTI dataset. We integrate our matching system into a LiDAR odometry pipeline yielding most accurate results on the KITTI dataset.
  arXiv  Detail & Related papers  (2020-02-10T17:53:41Z)

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.