paper-with-me

Papers

Unlocking Hidden Potential in Point Cloud Networks with Attention-Guided Grouping-Feature Coordination

2025-09-20 · Shangzhuo Xie, Qianqian Yang arxiv

Point cloud analysis has evolved with diverse network architectures, while existing works predominantly focus on introducing novel structural designs. However, conventional point-based architectures - processing raw points through sequential sampling, grouping, and feature extraction layers - demonstrate underutilized potential. We notice that substantial performance gains can be unlocked through strategic module integration rather than structural modifications. In this paper, we propose the Grouping-Feature Coordination Module (GF-Core), a lightweight separable component that simultaneously regulates both grouping layer and feature extraction layer to enable more nuanced feature aggregation. Besides, we introduce a self-supervised pretraining strategy specifically tailored for point-based inputs to enhance model robustness in complex point cloud analysis scenarios. On ModelNet40 dataset, our method elevates baseline networks to 94.0% accuracy, matching advanced frameworks' performance while preserving architectural simplicity. On three variants of the ScanObjectNN dataset, we obtain improvements of 2.96%, 6.34%, and 6.32% respectively.

📄 PDF Abstract BibTeX arXiv:2509.16639

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Natively Trainable Sparse Attention for Hierarchical Point Cloud Datasets

2025-08-14 · Nicolas Lapautre, Maria Marchenko, Carlos Miguel Patiño, Xin Zhou arxiv

Unlocking the potential of transformers on datasets of large physical systems depends on overcoming the quadratic scaling of the attention mechanism. This work explores combining the Erwin architecture with the Native Sp…

BranchPoseNet: Characterizing tree branching with a deep learning-based pose estimation approach

2024-09-23 · Stefano Puliti, Carolin Fischer, Rasmus Astrup

This paper presents an automated pipeline for detecting tree whorls in proximally laser scanning data using a pose-estimation deep learning model. Accurate whorl detection provides valuable insights into tree growth patt…

Pose Estimation

Interpreting Hidden Semantics in the Intermediate Layers of 3D Point Cloud Classification Neural Network

2023-03-12 · Weiquan Liu, Minghao Liu, Shijun Zheng, Cheng Wang

Although 3D point cloud classification neural network models have been widely used, the in-depth interpretation of the activation of the neurons and layers is still a challenge. We propose a novel approach, named Relevan…

3D Point Cloud ClassificationAdversarial AttackClassificationPoint Cloud Classification

Paired-Point Lifting for Enhanced Privacy-Preserving Visual Localization

2023-01-01 · CVPR 2023 1 · Chunghwan Lee, Jaihoon Kim, Chanhyuk Yun, Je Hyeong Hong

Visual localization refers to the process of recovering camera pose from input image relative to a known scene, forming a cornerstone of numerous vision and robotics systems. While many algorithms utilize sparse 3D p…

feature selectionPrivacy PreservingVisual Localization

Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Clouds

2022-03-19 · CVPR 2022 1 · Chenhang He, Ruihuang Li, Shuai Li, Lei Zhang

Transformer has demonstrated promising performance in many 2D vision tasks. However, it is cumbersome to compute the self-attention on large-scale point cloud data because point cloud is a long sequence and unevenly dist…

3D Object Detectionobject-detectionObject Detection