ASAP-Net: Attention and Structure Aware Point Cloud Sequence Segmentation

• URL: http://arxiv.org/abs/2008.05149v1
• Date: Wed, 12 Aug 2020 07:37:16 GMT
• Title: ASAP-Net: Attention and Structure Aware Point Cloud Sequence Segmentation
• Authors: Hanwen Cao, Yongyi Lu, Cewu Lu, Bo Pang, Gongshen Liu, Alan Yuille
• Abstract summary: We further improve point-temporal cloud feature with a flexible module called ASAP. Our ASAP module contains an attentive temporal embedding layer to fuse the relatively informative local features across frames in a recurrent fashion. We show the generalization ability of the proposed ASAP module with different computation backbone networks for point cloud sequence segmentation.
• Score: 49.15948235059343
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent works of point clouds show that mulit-frame spatio-temporal modeling outperforms single-frame versions by utilizing cross-frame information. In this paper, we further improve spatio-temporal point cloud feature learning with a flexible module called ASAP considering both attention and structure information across frames, which we find as two important factors for successful segmentation in dynamic point clouds. Firstly, our ASAP module contains a novel attentive temporal embedding layer to fuse the relatively informative local features across frames in a recurrent fashion. Secondly, an efficient spatio-temporal correlation method is proposed to exploit more local structure for embedding, meanwhile enforcing temporal consistency and reducing computation complexity. Finally, we show the generalization ability of the proposed ASAP module with different backbone networks for point cloud sequence segmentation. Our ASAP-Net (backbone plus ASAP module) outperforms baselines and previous methods on both Synthia and SemanticKITTI datasets (+3.4 to +15.2 mIoU points with different backbones). Code is availabe at https://github.com/intrepidChw/ASAP-Net

Related papers

• FASTC: A Fast Attentional Framework for Semantic Traversability Classification Using Point Cloud [7.711666704468952]
  We address the problem of traversability assessment using point clouds. We propose a pillar feature extraction module that utilizes PointNet to capture features from point clouds organized in vertical volume. We then propose a newtemporal attention module to fuse multi-frame information, which can properly handle the varying density problem of LIDAR point clouds.
  arXiv  Detail & Related papers  (2024-06-24T12:01:55Z)
• ColorMNet: A Memory-based Deep Spatial-Temporal Feature Propagation Network for Video Colorization [62.751303924391564]
  How to effectively explore spatial-temporal features is important for video colorization. We develop a memory-based feature propagation module that can establish reliable connections with features from far-apart frames. We develop a local attention module to aggregate the features from adjacent frames in a spatial-temporal neighborhood.
  arXiv  Detail & Related papers  (2024-04-09T12:23:30Z)
• ESGCN: Edge Squeeze Attention Graph Convolutional Network for Traffic Flow Forecasting [15.475463516901938]
  We propose a network Edge Squeeze Convolutional Network (ESCN) to forecast traffic flow in multiple regions. ESGCN achieves state-of-the-art performance by a large margin on four realworld datasets.
  arXiv  Detail & Related papers  (2023-07-03T04:47:42Z)
• Abstract Flow for Temporal Semantic Segmentation on the Permutohedral Lattice [27.37701107719647]
  We extend a backbone LatticeNet to process temporal point cloud data. We propose a new module called Abstract Flow which allows the network to match parts of the scene with similar abstract features. We obtain state-of-the-art results on the Semantic KITTI dataset that contains LiDAR scans from real urban environments.
  arXiv  Detail & Related papers  (2022-03-29T12:14:31Z)
• PRA-Net: Point Relation-Aware Network for 3D Point Cloud Analysis [56.91758845045371]
  We propose a novel framework named Point Relation-Aware Network (PRA-Net) It is composed of an Intra-region Structure Learning (ISL) module and an Inter-region Relation Learning (IRL) module. Experiments on several 3D benchmarks covering shape classification, keypoint estimation, and part segmentation have verified the effectiveness and the ability of PRA-Net.
  arXiv  Detail & Related papers  (2021-12-09T13:24:43Z)
• Multi-Scale Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition [140.18376685167857]
  A simple yet effective multi-scale semantics-guided neural network is proposed for skeleton-based action recognition. MS-SGN achieves the state-of-the-art performance on the NTU60, NTU120, and SYSU datasets.
  arXiv  Detail & Related papers  (2021-11-07T03:50:50Z)
• DRINet: A Dual-Representation Iterative Learning Network for Point Cloud Segmentation [45.768040873409824]
  DRINet serves as the basic network structure for dual-representation learning. Our network achieves state-of-the-art results for point cloud classification and segmentation tasks. For large-scale outdoor scenarios, our method outperforms state-of-the-art methods with a real-time inference speed of 62ms per frame.
  arXiv  Detail & Related papers  (2021-08-09T13:23:54Z)
• BiCnet-TKS: Learning Efficient Spatial-Temporal Representation for Video Person Re-Identification [86.73532136686438]
  We present an efficient spatial-temporal representation for video person re-identification (reID) We propose a Bilateral Complementary Network (BiCnet) for spatial complementarity modeling. BiCnet-TKS outperforms state-of-the-arts with about 50% less computations.
  arXiv  Detail & Related papers  (2021-04-30T06:44:34Z)
• FatNet: A Feature-attentive Network for 3D Point Cloud Processing [1.502579291513768]
  We introduce a novel feature-attentive neural network layer, a FAT layer, that combines both global point-based features and local edge-based features in order to generate better embeddings. Our architecture achieves state-of-the-art results on the task of point cloud classification, as demonstrated on the ModelNet40 dataset.
  arXiv  Detail & Related papers  (2021-04-07T23:13:56Z)
• F2Net: Learning to Focus on the Foreground for Unsupervised Video Object Segmentation [61.74261802856947]
  We propose a novel Focus on Foreground Network (F2Net), which delves into the intra-inter frame details for the foreground objects. Our proposed network consists of three main parts: Siamese Module, Center Guiding Appearance Diffusion Module, and Dynamic Information Fusion Module. Experiments on DAVIS2016, Youtube-object, and FBMS datasets show that our proposed F2Net achieves the state-of-the-art performance with significant improvement.
  arXiv  Detail & Related papers  (2020-12-04T11:30:50Z)

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.