EfficientPEAL: Efficient prior-embedded attention learning for partially overlapping point cloud registration

计算机科学 点云 点(几何) 人工智能 云计算 数学 几何学 操作系统
作者
Junle Yu,Wenhui Zhou,Zhehao Shen,Yongwei Miao
出处
期刊:Expert Systems With Applications [Elsevier BV]
卷期号:293: 128591-128591 被引量:3
标识
DOI:10.1016/j.eswa.2025.128591
摘要

• We propose an efficient prior-embedded learning framework for enhancing the pose registration of point clouds, demonstrating significant robustness across both high-overlap and low-overlap scenarios. • The proposed local geometric self-attention module effectively reduces the GPU memory consumption and inference time compared to previous work, while maintaining comparable performance. • The proposed method efficiently integrates various overlap priors to enhance registration performance, such as 2D prior, 3D prior, hybrid 2D/3D prior and random prior. • The proposed method outperforms the state-of-the-art on several public datasets, including 3DMatch/3DLoMatch, ScanNet and KITTI datasets, demonstrating its generality and effectiveness across different datasets. Learning discriminative point-wise features is critical for partially overlapping point cloud registration. In recent years, the integration of a Transformer into point cloud feature representation has demonstrated remarkable success, which typically involves a self-attention module to learn intra-point-cloud features, followed by a cross-attention module for feature exchange between input point clouds. Transformer models mainly benefit from the use of self-attention to capture the global correlations in feature space. However, the global correlations involved in self-attention may not only result in a significant amount of redundant computational overhead but also introduce feature ambiguities, especially in low-overlap scenarios. This is because overlapping regions of point clouds typically do not span a wide range but are rather concentrated around a localized area. Therefore, the correlations with an extensive range of non-overlapping points are ineffective and may degrade the discriminability of features. To address this issue, we present a E fficient P rior- E mbedded A ttention L earning model ( E fficientPEAL). By incorporating overlap prior to the learning process, the point clouds are divided into two parts. One part includes points lying in the putative overlapping region and the other includes points located in the putative non-overlapping region. Then, EfficientPEAL performs localized attention with the putative overlapping points. The proposed attention module significantly reduces the computational complexity of the model while achieving competitive performance. Extensive experiments on 3DMatch/3DLoMatch, ScanNet, and KITTI datasets demonstrate its effectiveness.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
安静寒云完成签到,获得积分10
刚刚
沐沐完成签到,获得积分20
刚刚
刚刚
华仔的应助被Avolie采纳,获得10
刚刚
烟雨完成签到,获得积分10
刚刚
lumos完成签到,获得积分10
1秒前
时笙完成签到,获得积分10
1秒前
酷波er的应助被七七酱采纳,获得10
1秒前
小SCI发布了新的文献求助10
1秒前
tang完成签到,获得积分10
2秒前
2秒前
fantasy的应助被什玖采纳,获得10
3秒前
何文微完成签到,获得积分10
3秒前
又又完成签到 ,获得积分10
3秒前
4秒前
无所谓发布了新的文献求助10
4秒前
4秒前
ccc发布了新的文献求助10
5秒前
董竹君完成签到,获得积分10
5秒前
爱壹帆完成签到,获得积分10
5秒前
seeyou发布了新的文献求助10
6秒前
7秒前
CipherSage的应助被Guhuiying采纳,获得10
7秒前
宝宝贝贝发布了新的文献求助10
7秒前
accelerate的应助被科研人采纳,获得10
7秒前
8秒前
8秒前
李琦发布了新的文献求助10
8秒前
8秒前
maliwen完成签到,获得积分10
8秒前
Porkpike完成签到 ,获得积分10
9秒前
9秒前
9秒前
脑洞疼的应助被何文微采纳,获得10
10秒前
LX完成签到,获得积分10
10秒前
去码头整点薯条完成签到 ,获得积分10
10秒前
11秒前
大脚丫dds完成签到,获得积分10
11秒前
虚幻仇血完成签到,获得积分10
11秒前
deng发布了新的文献求助10
12秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8187480
求助须知:如何正确求助?哪些是违规求助? 9575554
关于积分的说明 21841909
捐赠科研通 7785230
什么是DOI,文献DOI怎么找? 3434949
关于科研通互助平台的介绍 2559412
邀请新用户注册赠送积分活动 2481898