paper-with-me

Papers

HDMNet: A Hierarchical Matching Network with Double Attention for Large-scale Outdoor LiDAR Point Cloud Registration

2023-10-29 · Weiyi Xue, Fan Lu, Guang Chen

Outdoor LiDAR point clouds are typically large-scale and complexly distributed. To achieve efficient and accurate registration, emphasizing the similarity among local regions and prioritizing global local-to-local matching is of utmost importance, subsequent to which accuracy can be enhanced through cost-effective fine registration. In this paper, a novel hierarchical neural network with double attention named HDMNet is proposed for large-scale outdoor LiDAR point cloud registration. Specifically, A novel feature consistency enhanced double-soft matching network is introduced to achieve two-stage matching with high flexibility while enlarging the receptive field with high efficiency in a patch-to patch manner, which significantly improves the registration performance. Moreover, in order to further utilize the sparse matching information from deeper layer, we develop a novel trainable embedding mask to incorporate the confidence scores of correspondences obtained from pose estimation of deeper layer, eliminating additional computations. The high-confidence keypoints in the sparser point cloud of the deeper layer correspond to a high-confidence spatial neighborhood region in shallower layer, which will receive more attention, while the features of non-key regions will be masked. Extensive experiments are conducted on two large-scale outdoor LiDAR point cloud datasets to demonstrate the high accuracy and efficiency of the proposed HDMNet.

📄 PDF Abstract BibTeX arXiv:2310.18874

Code (0)

등록된 구현이 없습니다.

Tasks

Point Cloud RegistrationPose Estimation

Similar Papers 제목 키워드 기반

Hierarchical Dense Correlation Distillation for Few-Shot Segmentation

2023-03-26 · CVPR 2023 1 · Bohao Peng, Zhuotao Tian, Xiaoyang Wu, Chenyao Wang 외

Few-shot semantic segmentation (FSS) aims to form class-agnostic models segmenting unseen classes with only a handful of annotations. Previous methods limited to the semantic feature and prototype representation suffer f…

Few-Shot Semantic SegmentationSegmentationSemantic correspondenceSemantic Segmentation

Hierarchical Dense Correlation Distillation for Few-Shot Segmentation-Extended Abstract

2023-06-27 · Bohao Peng, Zhuotao Tian, Xiaoyang Wu, Chengyao Wang 외

Few-shot semantic segmentation (FSS) aims to form class-agnostic models segmenting unseen classes with only a handful of annotations. Previous methods limited to the semantic feature and prototype representation suffer f…

Few-Shot Semantic SegmentationSegmentationSemantic correspondenceSemantic Segmentation

Eliminating Feature Ambiguity for Few-Shot Segmentation

2024-07-13 · Qianxiong Xu, Guosheng Lin, Chen Change Loy, Cheng Long 외

Recent advancements in few-shot segmentation (FSS) have exploited pixel-by-pixel matching between query and support features, typically based on cross attention, which selectively activate query foreground (FG) features …

Few-Shot Semantic Segmentation

Double-P: Hierarchical Top-P Sparse Attention for Long-Context LLMs

2026-02-05 · Wentao Ni, Kangqi Zhang, Zhongming Yu, Oren Nelson 외 arxiv

As long-context inference becomes central to large language models (LLMs), attention over growing key-value caches emerges as a dominant decoding bottleneck, motivating sparse attention for scalable inference. Fixed-budg…

IDEA: Interactive DoublE Attentions from Label Embedding for Text Classification

2022-09-23 · Ziyuan Wang, Hailiang Huang, Songqiao Han

Current text classification methods typically encode the text merely into embedding before a naive or complicated classifier, which ignores the suggestive information contained in the label text. As a matter of fact, hum…

text-classificationText Classification