DELFlow: Dense Efficient Learning of Scene Flow for Large-Scale Point Clouds

• URL: http://arxiv.org/abs/2308.04383v2
• Date: Wed, 9 Aug 2023 13:21:56 GMT
• Title: DELFlow: Dense Efficient Learning of Scene Flow for Large-Scale Point Clouds
• Authors: Chensheng Peng, Guangming Wang, Xian Wan Lo, Xinrui Wu, Chenfeng Xu, Masayoshi Tomizuka, Wei Zhan, Hesheng Wang
• Abstract summary: We regularize raw points to a dense format by storing 3D coordinates in 2D grids. Unlike the sampling operation commonly used in existing works, the dense 2D representation preserves most points. We also present a novel warping projection technique to alleviate the information loss problem.
• Score: 42.64433313672884
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Point clouds are naturally sparse, while image pixels are dense. The inconsistency limits feature fusion from both modalities for point-wise scene flow estimation. Previous methods rarely predict scene flow from the entire point clouds of the scene with one-time inference due to the memory inefficiency and heavy overhead from distance calculation and sorting involved in commonly used farthest point sampling, KNN, and ball query algorithms for local feature aggregation. To mitigate these issues in scene flow learning, we regularize raw points to a dense format by storing 3D coordinates in 2D grids. Unlike the sampling operation commonly used in existing works, the dense 2D representation 1) preserves most points in the given scene, 2) brings in a significant boost of efficiency, and 3) eliminates the density gap between points and pixels, allowing us to perform effective feature fusion. We also present a novel warping projection technique to alleviate the information loss problem resulting from the fact that multiple points could be mapped into one grid during projection when computing cost volume. Sufficient experiments demonstrate the efficiency and effectiveness of our method, outperforming the prior-arts on the FlyingThings3D and KITTI dataset.

Related papers

• Quadric Representations for LiDAR Odometry, Mapping and Localization [93.24140840537912]
  Current LiDAR odometry, mapping and localization methods leverage point-wise representations of 3D scenes. We propose a novel method of describing scenes using quadric surfaces, which are far more compact representations of 3D objects. Our method maintains low latency and memory utility while achieving competitive, and even superior, accuracy.
  arXiv  Detail & Related papers  (2023-04-27T13:52:01Z)
• PointFlowHop: Green and Interpretable Scene Flow Estimation from Consecutive Point Clouds [49.7285297470392]
  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.
  arXiv  Detail & Related papers  (2023-02-27T23:06:01Z)
• 3D Scene Flow Estimation on Pseudo-LiDAR: Bridging the Gap on Estimating Point Motion [19.419030878019974]
  3D scene flow characterizes how the points at the current time flow to the next time in the 3D Euclidean space. The stability of the predicted scene flow is improved by introducing the dense nature of 2D pixels into the 3D space. Disparity consistency loss is proposed to achieve more effective unsupervised learning of 3D scene flow.
  arXiv  Detail & Related papers  (2022-09-27T03:27:09Z)
• 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)
• Stratified Transformer for 3D Point Cloud Segmentation [89.9698499437732]
  Stratified Transformer is able to capture long-range contexts and demonstrates strong generalization ability and high performance. To combat the challenges posed by irregular point arrangements, we propose first-layer point embedding to aggregate local information. Experiments demonstrate the effectiveness and superiority of our method on S3DIS, ScanNetv2 and ShapeNetPart datasets.
  arXiv  Detail & Related papers  (2022-03-28T05:35:16Z)
• Residual 3D Scene Flow Learning with Context-Aware Feature Extraction [11.394559627312743]
  We propose a novel context-aware set conv layer to exploit contextual structure information of Euclidean space. We also propose an explicit residual flow learning structure in the residual flow refinement layer to cope with long-distance movement. Our method achieves state-of-the-art performance, surpassing all other previous works to the best of our knowledge by at least 25%.
  arXiv  Detail & Related papers  (2021-09-10T06:15:18Z)
• DV-Det: Efficient 3D Point Cloud Object Detection with Dynamic Voxelization [0.0]
  We propose a novel two-stage framework for the efficient 3D point cloud object detection. We parse the raw point cloud data directly in the 3D space yet achieve impressive efficiency and accuracy. We highlight our KITTI 3D object detection dataset with 75 FPS and on Open dataset with 25 FPS inference speed with satisfactory accuracy.
  arXiv  Detail & Related papers  (2021-07-27T10:07:39Z)
• 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)

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.