Point Tree Transformer for Point Cloud Registration

计算机科学 点云 云计算 计算机视觉 人工智能 操作系统
作者
Meiling Wang,Guangyan Chen,Yi Yang,Li Yuan,Yufeng Yue
出处
期刊:IEEE Transactions on Circuits and Systems for Video Technology [Institute of Electrical and Electronics Engineers]
卷期号:: 1-1
标识
DOI:10.1109/tcsvt.2025.3526680
摘要

Point cloud registration is a fundamental task in the fields of computer vision and robotics. Recent advancements in transformer-based methods have demonstrated enhanced performance in this domain. However, the standard attention mechanisms employed in these approaches tend to incorporate numerous points of low relevance, and therefore struggle to focus their attention weights on sparse yet meaningful points. This inefficiency leads to limited local structure modeling capabilities and quadratic computational complexity. To overcome these limitations, we propose the Point Tree Transformer (PTT), a novel transformer-based approach for point cloud registration that efficiently extracts comprehensive local and global features while maintaining linear computational complexity. The PTT constructs hierarchical feature trees from point clouds in a coarse-to-dense manner, and introduces a novel Point Tree Attention (PTA) mechanism. This mechanism adheres to the tree structure to facilitate the progressive convergence of attended regions toward salient points. Specifically, each tree layer selectively identifies a subset of relevant points with the highest attention scores, and subsequent layers focus attention on areas of significant relevance, derived from the child points of the selected point set. The feature extraction process additionally incorporates coarse point features that capture high-level semantic information, thus facilitating local structure modeling and the progressive integration of multiscale information. Consequently, the PTA enables the model to focus on essential local structures and extract intricate local information while maintaining linear computational complexity. Extensive experiments conducted on the 3DMatch, ModelNet40, and KITTI datasets demonstrate that our method outperforms state-of-the-art methods in terms of performance. The code for our method is publicly available at https://github.com/CGuangyan-BIT/PTT.

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
Monarch完成签到 ,获得积分10
1秒前
姜丝罐罐n完成签到 ,获得积分10
2秒前
cc发布了新的文献求助20
3秒前
3秒前
3秒前
上官若男的应助被浮云采纳,获得10
5秒前
putao发布了新的文献求助10
6秒前
残梦完成签到 ,获得积分10
7秒前
CJJ发布了新的文献求助10
7秒前
7秒前
Owen的应助被高大橙采纳,获得10
7秒前
往事随风的应助被稳重续采纳,获得30
8秒前
Hello的应助被THESHY采纳,获得10
8秒前
今后的应助被EasonYao采纳,获得10
9秒前
9秒前
Cheryl发布了新的文献求助30
9秒前
木兮木完成签到 ,获得积分10
12秒前
neuro1993完成签到,获得积分10
12秒前
苏苏发布了新的文献求助10
12秒前
lll完成签到,获得积分10
13秒前
张译尹完成签到,获得积分10
14秒前
打打的应助被Monarch采纳,获得10
14秒前
dawn末黎完成签到,获得积分10
14秒前
HHH发布了新的文献求助10
15秒前
余籁完成签到,获得积分10
16秒前
17秒前
mochiho关注了科研通微信公众号
17秒前
aiyiying完成签到,获得积分10
17秒前
不安的未来完成签到,获得积分10
17秒前
酷波er的应助被医生采纳,获得10
17秒前
19秒前
Maestro_S的应助被神勇的筝采纳,获得30
20秒前
20秒前
20秒前
20秒前
核桃的应助被ww采纳,获得30
22秒前
NexusExplorer的应助被shuangquan采纳,获得10
22秒前
小二郎的应助被kim采纳,获得10
22秒前
务实元风完成签到,获得积分10
22秒前
浮云发布了新的文献求助10
23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
Grapes 1000
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
John McDowells Bildungstheorie 800
八旗制度の研究 600
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 8179039
求助须知:如何正确求助?哪些是违规求助? 9569680
关于积分的说明 21805951
捐赠科研通 7774135
什么是DOI,文献DOI怎么找? 3432981
关于科研通互助平台的介绍 2556897
邀请新用户注册赠送积分活动 2478640