LCPFormer: Towards Effective 3D Point Cloud Analysis via Local Context Propagation in Transformers

• URL: http://arxiv.org/abs/2210.12755v1
• Date: Sun, 23 Oct 2022 15:43:01 GMT
• Title: LCPFormer: Towards Effective 3D Point Cloud Analysis via Local Context Propagation in Transformers
• Authors: Zhuoxu Huang, Zhiyou Zhao, Banghuai Li, Jungong Han
• Abstract summary: We propose a novel module named Local Context Propagation (LCP) to exploit the message passing between neighboring local regions. We use the overlap points of adjacent local regions as intermediaries, then re-weight the features of these shared points from different local regions before passing them to the next layers. The proposed method is applicable to different tasks and outperforms various transformer-based methods in benchmarks including 3D shape classification and dense prediction tasks.
• Score: 60.51925353387151
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Transformer with its underlying attention mechanism and the ability to capture long-range dependencies makes it become a natural choice for unordered point cloud data. However, separated local regions from the general sampling architecture corrupt the structural information of the instances, and the inherent relationships between adjacent local regions lack exploration, while local structural information is crucial in a transformer-based 3D point cloud model. Therefore, in this paper, we propose a novel module named Local Context Propagation (LCP) to exploit the message passing between neighboring local regions and make their representations more informative and discriminative. More specifically, we use the overlap points of adjacent local regions (which statistically show to be prevalent) as intermediaries, then re-weight the features of these shared points from different local regions before passing them to the next layers. Inserting the LCP module between two transformer layers results in a significant improvement in network expressiveness. Finally, we design a flexible LCPFormer architecture equipped with the LCP module. The proposed method is applicable to different tasks and outperforms various transformer-based methods in benchmarks including 3D shape classification and dense prediction tasks such as 3D object detection and semantic segmentation. Code will be released for reproduction.

Related papers

• 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)
• Local region-learning modules for point cloud classification [0.0]
  We present two local region-learning modules that infer the appropriate shift for each center point and alter the radius of each local region. We integrated both modules independently and together to the PointNet++ and PointCNN object classification architectures. Our experiments on ShapeNet data set showed that the modules are also effective on 3D CAD models.
  arXiv  Detail & Related papers  (2023-03-30T12:45:46Z)
• Adaptive Spot-Guided Transformer for Consistent Local Feature Matching [64.30749838423922]
  We propose Adaptive Spot-Guided Transformer (ASTR) for local feature matching. ASTR models the local consistency and scale variations in a unified coarse-to-fine architecture.
  arXiv  Detail & Related papers  (2023-03-29T12:28:01Z)
• Full Point Encoding for Local Feature Aggregation in 3D Point Clouds [29.402585297221457]
  We propose full point encoding which is applicable to convolution and transformer architectures. The key idea is to adaptively learn the weights from local and global geometric connections. We achieve state-of-the-art semantic segmentation results of 76% mIoU on S3DIS 6-fold and 72.2% on S3DIS Area5.
  arXiv  Detail & Related papers  (2023-03-08T09:14:17Z)
• SemAffiNet: Semantic-Affine Transformation for Point Cloud Segmentation [94.11915008006483]
  We propose SemAffiNet for point cloud semantic segmentation. We conduct extensive experiments on the ScanNetV2 and NYUv2 datasets.
  arXiv  Detail & Related papers  (2022-05-26T17:00:23Z)
• LCTR: On Awakening the Local Continuity of Transformer for Weakly Supervised Object Localization [38.376238216214524]
  Weakly supervised object localization (WSOL) aims to learn object localizer solely by using image-level labels. We propose a novel framework built upon the transformer, termed LCTR, which targets at enhancing the local perception capability of global features.
  arXiv  Detail & Related papers  (2021-12-10T01:48:40Z)
• Global Aggregation then Local Distribution for Scene Parsing [99.1095068574454]
  We show that our approach can be modularized as an end-to-end trainable block and easily plugged into existing semantic segmentation networks. Our approach allows us to build new state of the art on major semantic segmentation benchmarks including Cityscapes, ADE20K, Pascal Context, Camvid and COCO-stuff.
  arXiv  Detail & Related papers  (2021-07-28T03:46:57Z)
• Local Context Attention for Salient Object Segmentation [5.542044768017415]
  We propose a novel Local Context Attention Network (LCANet) to generate locally reinforcement feature maps in a uniform representational architecture. The proposed network introduces an Attentional Correlation Filter (ACF) module to generate explicit local attention by calculating the correlation feature map between coarse prediction and global context. Comprehensive experiments are conducted on several salient object segmentation datasets, demonstrating the superior performance of the proposed LCANet against the state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-09-24T09:20:06Z)
• LRC-Net: Learning Discriminative Features on Point Clouds by Encoding Local Region Contexts [65.79931333193016]
  We present a novel Local-Region-Context Network (LRC-Net) to learn discriminative features on point clouds. LRC-Net encodes fine-grained contexts inside and among local regions simultaneously. Results show LRC-Net is competitive with state-of-the-art methods in shape classification and shape segmentation applications.
  arXiv  Detail & Related papers  (2020-03-18T14:34:08Z)

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.