Cross-Level Cross-Scale Cross-Attention Network for Point Cloud Representation

• URL: http://arxiv.org/abs/2104.13053v1
• Date: Tue, 27 Apr 2021 09:01:14 GMT
• Title: Cross-Level Cross-Scale Cross-Attention Network for Point Cloud Representation
• Authors: Xian-Feng Han and Zhang-Yue He and Jia Chen and Guo-Qiang Xiao
• Abstract summary: Self-attention mechanism recently achieves impressive advancement in Natural Language Processing (NLP) and Image Processing domains. We propose an end-to-end architecture, dubbed Cross-Level Cross-Scale Cross-Attention Network (CLCSCANet) for point cloud representation learning.
• Score: 8.76786786874107
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Self-attention mechanism recently achieves impressive advancement in Natural Language Processing (NLP) and Image Processing domains. And its permutation invariance property makes it ideally suitable for point cloud processing. Inspired by this remarkable success, we propose an end-to-end architecture, dubbed Cross-Level Cross-Scale Cross-Attention Network (CLCSCANet), for point cloud representation learning. First, a point-wise feature pyramid module is introduced to hierarchically extract features from different scales or resolutions. Then a cross-level cross-attention is designed to model long-range inter-level and intra-level dependencies. Finally, we develop a cross-scale cross-attention module to capture interactions between-and-within scales for representation enhancement. Compared with state-of-the-art approaches, our network can obtain competitive performance on challenging 3D object classification, point cloud segmentation tasks via comprehensive experimental evaluation.

Related papers

• Unsupervised Non-Rigid Point Cloud Matching through Large Vision Models [1.3030624795284795]
  We propose a learning-based framework for non-rigid point cloud matching. Key insight is to incorporate semantic features derived from large vision models (LVMs) Our framework effectively leverages the structural information contained in the semantic features to address ambiguities arise from self-similarities among local geometries.
  arXiv  Detail & Related papers  (2024-08-16T07:02:19Z)
• Boosting Cross-Domain Point Classification via Distilling Relational Priors from 2D Transformers [59.0181939916084]
  Traditional 3D networks mainly focus on local geometric details and ignore the topological structure between local geometries. We propose a novel Priors Distillation (RPD) method to extract priors from the well-trained transformers on massive images. Experiments on the PointDA-10 and the Sim-to-Real datasets verify that the proposed method consistently achieves the state-of-the-art performance of UDA for point cloud classification.
  arXiv  Detail & Related papers  (2024-07-26T06:29:09Z)
• CRA-PCN: Point Cloud Completion with Intra- and Inter-level Cross-Resolution Transformers [29.417270066061864]
  We present Cross-Resolution Transformer that efficiently performs cross-resolution aggregation with local attention mechanisms. We integrate two forms of Cross-Resolution Transformers into one up-sampling block for point generation, and following the coarse-to-fine manner, we construct CRA-PCN to incrementally predict complete shapes.
  arXiv  Detail & Related papers  (2024-01-03T05:57:39Z)
• PointCAT: Cross-Attention Transformer for point cloud [1.3176016397292067]
  We present Point Cross-Attention Transformer (PointCAT), a novel end-to-end network architecture. Our approach combines multi-scale features via two seprate cross-attention transformer branches. Our method outperforms or achieves comparable performance to several approaches in shape classification, part segmentation and semantic segmentation tasks.
  arXiv  Detail & Related papers  (2023-04-06T11:58:18Z)
• Self-positioning Point-based Transformer for Point Cloud Understanding [18.394318824968263]
  Self-Positioning point-based Transformer (SPoTr) is designed to capture both local and global shape contexts with reduced complexity. SPoTr achieves an accuracy gain of 2.6% over the previous best models on shape classification with ScanObjectNN.
  arXiv  Detail & Related papers  (2023-03-29T04:27:11Z)
• Rethinking Range View Representation for LiDAR Segmentation [66.73116059734788]
  "Many-to-one" mapping, semantic incoherence, and shape deformation are possible impediments against effective learning from range view projections. We present RangeFormer, a full-cycle framework comprising novel designs across network architecture, data augmentation, and post-processing. We show that, for the first time, a range view method is able to surpass the point, voxel, and multi-view fusion counterparts in the competing LiDAR semantic and panoptic segmentation benchmarks.
  arXiv  Detail & Related papers  (2023-03-09T16:13:27Z)
• 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)
• REGTR: End-to-end Point Cloud Correspondences with Transformers [79.52112840465558]
  We conjecture that attention mechanisms can replace the role of explicit feature matching and RANSAC. We propose an end-to-end framework to directly predict the final set of correspondences. Our approach achieves state-of-the-art performance on 3DMatch and ModelNet benchmarks.
  arXiv  Detail & Related papers  (2022-03-28T06:01:00Z)
• DFC: Deep Feature Consistency for Robust Point Cloud Registration [0.4724825031148411]
  We present a novel learning-based alignment network for complex alignment scenes. We validate our approach on the 3DMatch dataset and the KITTI odometry dataset.
  arXiv  Detail & Related papers  (2021-11-15T08:27:21Z)
• PC-RGNN: Point Cloud Completion and Graph Neural Network for 3D Object Detection [57.49788100647103]
  LiDAR-based 3D object detection is an important task for autonomous driving. Current approaches suffer from sparse and partial point clouds of distant and occluded objects. In this paper, we propose a novel two-stage approach, namely PC-RGNN, dealing with such challenges by two specific solutions.
  arXiv  Detail & Related papers  (2020-12-18T18:06:43Z)
• Point Transformer [122.2917213154675]
  We investigate the application of self-attention networks to 3D point cloud processing. We design self-attention layers for point clouds and use these to construct self-attention networks for tasks such as semantic scene segmentation. Our Point Transformer design improves upon prior work across domains and tasks.
  arXiv  Detail & Related papers  (2020-12-16T18:58:56Z)

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.