A Dynamic Network for Efficient Point Cloud Registration
- URL: http://arxiv.org/abs/2312.02877v1
- Date: Tue, 5 Dec 2023 16:47:46 GMT
- Title: A Dynamic Network for Efficient Point Cloud Registration
- Authors: Yang Ai, Xi Yang
- Abstract summary: We introduce a dynamic approach, widely utilized to improve network efficiency in computer vision tasks, to the point cloud registration task.
We employ an iterative registration process on point cloud data multiple times to identify regions where matching points cluster, ultimately enabling us to remove noisy points.
- Score: 6.254197536395784
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: For the point cloud registration task, a significant challenge arises from
non-overlapping points that consume extensive computational resources while
negatively affecting registration accuracy. In this paper, we introduce a
dynamic approach, widely utilized to improve network efficiency in computer
vision tasks, to the point cloud registration task. We employ an iterative
registration process on point cloud data multiple times to identify regions
where matching points cluster, ultimately enabling us to remove noisy points.
Specifically, we begin with deep global sampling to perform coarse global
registration. Subsequently, we employ the proposed refined node proposal module
to further narrow down the registration region and perform local registration.
Furthermore, we utilize a spatial consistency-based classifier to evaluate the
results of each registration stage. The model terminates once it reaches
sufficient confidence, avoiding unnecessary computations. Extended experiments
demonstrate that our model significantly reduces time consumption compared to
other methods with similar results, achieving a speed improvement of over 41%
on indoor dataset (3DMatch) and 33% on outdoor datasets (KITTI) while
maintaining competitive registration recall requirements.
Related papers
- Point Cloud Pre-training with Diffusion Models [62.12279263217138]
We propose a novel pre-training method called Point cloud Diffusion pre-training (PointDif)
PointDif achieves substantial improvement across various real-world datasets for diverse downstream tasks such as classification, segmentation and detection.
arXiv Detail & Related papers (2023-11-25T08:10:05Z) - 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) - SphereNet: Learning a Noise-Robust and General Descriptor for Point
Cloud Registration [5.641476052216014]
We introduce SphereNet to learn a noise-robust and unseen-general descriptor for point cloud registration.
A new benchmark 3DMatch-noise with strong noise is introduced to evaluate our methods.
It sets a new state-of-the-art performance for the 3DMatch and 3DLoMatch benchmarks with 93.5% and 75.6% registration recall.
arXiv Detail & Related papers (2023-07-18T15:37:35Z) - GAFAR: Graph-Attention Feature-Augmentation for Registration A Fast and
Light-weight Point Set Registration Algorithm [12.592563880121816]
rigid registration of point clouds is a fundamental problem in computer vision.
Deep learning in computer vision has brought new drive to research on this topic.
We present a novel fast and light-weight network architecture using the attention mechanism to augment point descriptors.
arXiv Detail & Related papers (2023-07-05T14:50:36Z) - CloudAttention: Efficient Multi-Scale Attention Scheme For 3D Point
Cloud Learning [81.85951026033787]
We set transformers in this work and incorporate them into a hierarchical framework for shape classification and part and scene segmentation.
We also compute efficient and dynamic global cross attentions by leveraging sampling and grouping at each iteration.
The proposed hierarchical model achieves state-of-the-art shape classification in mean accuracy and yields results on par with the previous segmentation methods.
arXiv Detail & Related papers (2022-07-31T21:39:15Z) - Fast and Robust Registration of Partially Overlapping Point Clouds [5.073765501263891]
Real-time registration of partially overlapping point clouds has emerging applications in cooperative perception for autonomous vehicles.
Relative translation between point clouds in these applications is higher than in traditional SLAM and odometry applications.
We propose a novel registration method for partially overlapping point clouds where correspondences are learned using an efficient point-wise feature encoder.
arXiv Detail & Related papers (2021-12-18T12:39:05Z) - GenReg: Deep Generative Method for Fast Point Cloud Registration [18.66568286698704]
We propose a new data-driven registration algorithm by investigating deep generative neural networks to point cloud registration.
The experiments on both ModelNet40 and 7Scene datasets demonstrate that the proposed algorithm achieves state-of-the-art accuracy and efficiency.
arXiv Detail & Related papers (2021-11-23T10:52:09Z) - 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) - Consistent Two-Flow Network for Tele-Registration of Point Clouds [74.51029406361997]
We present a learning-based technique that allows registration between point clouds, presented in arbitrary poses, and having little or even no overlap.
Our technique is based on a novel neural network design that learns a prior of a class of shapes and can complete a partial shape.
We show that, compared with each separate flow, this two-flow training leads to robust and reliable tele-registration.
arXiv Detail & Related papers (2021-06-01T09:03:21Z) - End-to-End 3D Point Cloud Learning for Registration Task Using Virtual
Correspondences [17.70819292121181]
3D Point cloud registration is still a very challenging topic due to the difficulty in finding the rigid transformation between two point clouds.
In this paper, we present an end-to-end deep-learning based approach to resolve the point cloud registration problem.
arXiv Detail & Related papers (2020-11-30T06:55:05Z) - SoftPoolNet: Shape Descriptor for Point Cloud Completion and
Classification [93.54286830844134]
We propose a method for 3D object completion and classification based on point clouds.
For the decoder stage, we propose regional convolutions, a novel operator aimed at maximizing the global activation entropy.
We evaluate our approach on different 3D tasks such as object completion and classification, achieving state-of-the-art accuracy.
arXiv Detail & Related papers (2020-08-17T14:32:35Z)
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.