RPSRNet: End-to-End Trainable Rigid Point Set Registration Network using Barnes-Hut $2^D$-Tree Representation

• URL: http://arxiv.org/abs/2104.05328v1
• Date: Mon, 12 Apr 2021 10:16:09 GMT
• Title: RPSRNet: End-to-End Trainable Rigid Point Set Registration Network using Barnes-Hut $2^D$-Tree Representation
• Abstract summary: 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.
• Score: 13.351162559710124
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose RPSRNet - a novel end-to-end trainable deep neural network for rigid point set registration. For this task, we use a novel $2^D$-tree representation for the input point sets and a hierarchical deep feature embedding in the neural network. An iterative transformation refinement module in our network boosts the feature matching accuracy in the intermediate stages. We achieve an inference speed of 12-15ms to register a pair of input point clouds as large as 250K. Extensive evaluation on (i) KITTI LiDAR odometry and (ii) ModelNet-40 datasets shows that our method outperforms prior state-of-the-art methods - e.g., on the KITTI data set, DCP-v2 by1.3 and 1.5 times, and PointNetLK by 1.8 and 1.9 times better rotational and translational accuracy respectively. Evaluation on ModelNet40 shows that RPSRNet is more robust than other benchmark methods when the samples contain a significant amount of noise and other disturbances. RPSRNet accurately registers point clouds with non-uniform sampling densities, e.g., LiDAR data, which cannot be processed by many existing deep-learning-based registration methods.

Related papers

• A Unified Platform to Evaluate STDP Learning Rule and Synapse Model using Pattern Recognition in a Spiking Neural Network [0.0]
  We develop a unified platform to evaluate Ideal, Linear, and Non-linear $textPr_0.7textCa_0.3textMnO_3$ memristor-based synapse models.<n>On MNIST with small train set and large test set, our two-layer SNN with ideal, 25-state, and 12-state nonlinear memristor synapses achieves 92.73 %, 91.07 %, and 80 % accuracy, respectively.
  arXiv  Detail & Related papers  (2025-06-24T07:10:43Z)
• R2DN: Scalable Parameterization of Contracting and Lipschitz Recurrent Deep Networks [1.1060425537315086]
  The Robust Recurrent Deep Network (R2DN) is a scalable parameterization of robust recurrent neural networks for machine learning and data-driven control. We construct R2DNs as a feedback of a linear time-invariant system and a 1-Lipschitz deep feedforward network. We find that training and inference are both up to an order of magnitude faster with similar test set performance, and that training/inference times scale more favorably with respect to model expressivity.
  arXiv  Detail & Related papers  (2025-04-01T23:37:43Z)
• CS-Net:Contribution-based Sampling Network for Point Cloud Simplification [50.55658910053004]
  Point cloud sampling plays a crucial role in reducing computation costs and storage requirements for various vision tasks. Traditional sampling methods, such as farthest point sampling, lack task-specific information. We propose a contribution-based sampling network (CS-Net), where the sampling operation is formulated as a Top-k operation.
  arXiv  Detail & Related papers  (2025-01-18T14:56:09Z)
• Neural Implicit Dictionary via Mixture-of-Expert Training [111.08941206369508]
  We present a generic INR framework that achieves both data and training efficiency by learning a Neural Implicit Dictionary (NID) Our NID assembles a group of coordinate-based Impworks which are tuned to span the desired function space. Our experiments show that, NID can improve reconstruction of 2D images or 3D scenes by 2 orders of magnitude faster with up to 98% less input data.
  arXiv  Detail & Related papers  (2022-07-08T05:07:19Z)
• Unsupervised Representation Learning via Neural Activation Coding [66.65837512531729]
  We present neural activation coding (NAC) as a novel approach for learning deep representations from unlabeled data for downstream applications. We show that NAC learns both continuous and discrete representations of data, which we respectively evaluate on two downstream tasks.
  arXiv  Detail & Related papers  (2021-12-07T21:59:45Z)
• Network-wide Multi-step Traffic Volume Prediction using Graph Convolutional Gated Recurrent Neural Network [16.56822335262946]
  We propose a novel deep learning model, Graph Convolutional Gated Recurrent Neural Network (GCGRNN), to predict network-wide, multi-step traffic volume. We have evaluated our model using two traffic datasets extracted from 150 sensors in Los Angeles, California, at the time resolutions one hour and 15 minutes, respectively.
  arXiv  Detail & Related papers  (2021-11-22T16:41:13Z)
• Logsig-RNN: a novel network for robust and efficient skeleton-based action recognition [3.775860173040509]
  We propose a novel module, namely Logsig-RNN, which is the combination of the log-native layer and recurrent type neural networks (RNNs) In particular, we achieve the state-of-the-art accuracy on Chalearn2013 gesture data by combining simple path transformation layers with the Logsig-RNN.
  arXiv  Detail & Related papers  (2021-10-25T14:47:15Z)
• Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling [52.464516118826765]
  We introduce RandLA-Net, an efficient and lightweight neural architecture to infer per-point semantics for large-scale point clouds. The key to our approach is to use random point sampling instead of more complex point selection approaches. Our RandLA-Net can process 1 million points in a single pass up to 200x faster than existing approaches.
  arXiv  Detail & Related papers  (2021-07-06T05:08:34Z)
• 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)
• Manifold Regularized Dynamic Network Pruning [102.24146031250034]
  This paper proposes a new paradigm that dynamically removes redundant filters by embedding the manifold information of all instances into the space of pruned networks. The effectiveness of the proposed method is verified on several benchmarks, which shows better performance in terms of both accuracy and computational cost.
  arXiv  Detail & Related papers  (2021-03-10T03:59:03Z)
• 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)
• 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)
• Compressing deep neural networks on FPGAs to binary and ternary precision with HLS4ML [13.325670094073383]
  We present the implementation of binary and ternary neural networks in the hls4ml library. We discuss the trade-off between model accuracy and resource consumption. The binary and ternary implementation has similar performance to the higher precision implementation while using drastically fewer FPGA resources.
  arXiv  Detail & Related papers  (2020-03-11T10:46:51Z)

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.