PointFlowHop: Green and Interpretable Scene Flow Estimation from Consecutive Point Clouds

• URL: http://arxiv.org/abs/2302.14193v1
• Date: Mon, 27 Feb 2023 23:06:01 GMT
• Title: PointFlowHop: Green and Interpretable Scene Flow Estimation from Consecutive Point Clouds
• Authors: Pranav Kadam, Jiahao Gu, Shan Liu, C.-C. Jay Kuo
• Abstract summary: An efficient 3D scene flow estimation method called PointFlowHop is proposed in this work. PointFlowHop takes two consecutive point clouds and determines the 3D flow vectors for every point in the first point cloud. It decomposes the scene flow estimation task into a set of subtasks, including ego-motion compensation, object association and object-wise motion estimation.
• Score: 49.7285297470392
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: An efficient 3D scene flow estimation method called PointFlowHop is proposed in this work. PointFlowHop takes two consecutive point clouds and determines the 3D flow vectors for every point in the first point cloud. PointFlowHop decomposes the scene flow estimation task into a set of subtasks, including ego-motion compensation, object association and object-wise motion estimation. It follows the green learning (GL) pipeline and adopts the feedforward data processing path. As a result, its underlying mechanism is more transparent than deep-learning (DL) solutions based on end-to-end optimization of network parameters. We conduct experiments on the stereoKITTI and the Argoverse LiDAR point cloud datasets and demonstrate that PointFlowHop outperforms deep-learning methods with a small model size and less training time. Furthermore, we compare the Floating Point Operations (FLOPs) required by PointFlowHop and other learning-based methods in inference, and show its big savings in computational complexity.

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)
• SCOOP: Self-Supervised Correspondence and Optimization-Based Scene Flow [25.577386156273256]
  Scene flow estimation is a long-standing problem in computer vision, where the goal is to find the 3D motion of a scene from its consecutive observations. We introduce SCOOP, a new method for scene flow estimation that can be learned on a small amount of data without employing ground-truth flow supervision.
  arXiv  Detail & Related papers  (2022-11-25T10:52:02Z)
• What Matters for 3D Scene Flow Network [44.02710380584977]
  3D scene flow estimation from point clouds is a low-level 3D motion perception task in computer vision. We propose a novel all-to-all flow embedding layer with backward reliability validation during the initial scene flow estimation. Our proposed model surpasses all existing methods by at least 38.2% on FlyingThings3D dataset and 24.7% on KITTI Scene Flow dataset for EPE3D metric.
  arXiv  Detail & Related papers  (2022-07-19T09:27:05Z)
• RCP: Recurrent Closest Point for Scene Flow Estimation on 3D Point Clouds [44.034836961967144]
  3D motion estimation including scene flow and point cloud registration has drawn increasing interest. Recent methods employ deep neural networks to construct the cost volume for estimating accurate 3D flow. We decompose the problem into two interlaced stages, where the 3D flows are optimized point-wisely at the first stage and then globally regularized in a recurrent network at the second stage.
  arXiv  Detail & Related papers  (2022-05-23T04:04:30Z)
• GPCO: An Unsupervised Green Point Cloud Odometry Method [64.86292006892093]
  A lightweight point cloud odometry solution is proposed and named the green point cloud odometry (GPCO) method. GPCO is an unsupervised learning method that predicts object motion by matching features of consecutive point cloud scans. It is observed that GPCO outperforms benchmarking deep learning methods in accuracy while it has a significantly smaller model size and less training time.
  arXiv  Detail & Related papers  (2021-12-08T00:24:03Z)
• Self-Point-Flow: Self-Supervised Scene Flow Estimation from Point Clouds with Optimal Transport and Random Walk [59.87525177207915]
  We develop a self-supervised method to establish correspondences between two point clouds to approximate scene flow. Our method achieves state-of-the-art performance among self-supervised learning methods.
  arXiv  Detail & Related papers  (2021-05-18T03:12:42Z)
• SCTN: Sparse Convolution-Transformer Network for Scene Flow Estimation [71.2856098776959]
  Estimating 3D motions for point clouds is challenging, since a point cloud is unordered and its density is significantly non-uniform. We propose a novel architecture named Sparse Convolution-Transformer Network (SCTN) that equips the sparse convolution with the transformer. We show that the learned relation-based contextual information is rich and helpful for matching corresponding points, benefiting scene flow estimation.
  arXiv  Detail & Related papers  (2021-05-10T15:16:14Z)
• Do not trust the neighbors! Adversarial Metric Learning for Self-Supervised Scene Flow Estimation [0.0]
  Scene flow is the task of estimating 3D motion vectors to individual points of a dynamic 3D scene. We propose a 3D scene flow benchmark and a novel self-supervised setup for training flow models. We find that our setup is able to keep motion coherence and preserve local geometries, which many self-supervised baselines fail to grasp.
  arXiv  Detail & Related papers  (2020-11-01T17:41:32Z)
• PointHop++: A Lightweight Learning Model on Point Sets for 3D Classification [55.887502438160304]
  The PointHop method was recently proposed by Zhang et al. for 3D point cloud classification with unsupervised feature extraction. We improve the PointHop method furthermore in two aspects: 1) reducing its model complexity in terms of the model parameter number and 2) ordering discriminant features automatically based on the cross-entropy criterion. With experiments conducted on the ModelNet40 benchmark dataset, we show that the PointHop++ method performs on par with deep neural network (DNN) solutions and surpasses other unsupervised feature extraction methods.
  arXiv  Detail & Related papers  (2020-02-09T04:49:32Z)

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.