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.
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
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

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
重要忆秋完成签到,获得积分10
1秒前
yy发布了新的文献求助10
1秒前
wwm98656完成签到,获得积分10
4秒前
4秒前
totpto完成签到,获得积分20
5秒前
7秒前
My完成签到,获得积分10
7秒前
孙颖莎粉丝完成签到,获得积分10
7秒前
尼古拉耶维奇完成签到,获得积分10
7秒前
阿卡宁发布了新的文献求助10
8秒前
9秒前
温柔翰完成签到,获得积分10
10秒前
文龙完成签到 ,获得积分10
10秒前
11秒前
Xiaopan完成签到,获得积分10
11秒前
xiaoming发布了新的文献求助200
12秒前
12秒前
QT完成签到,获得积分20
13秒前
朱华彪完成签到,获得积分10
13秒前
活在当下发布了新的文献求助10
13秒前
13秒前
haha发布了新的文献求助10
14秒前
aurora完成签到 ,获得积分10
15秒前
茉莉完成签到,获得积分10
15秒前
123完成签到,获得积分10
17秒前
17秒前
wwewew完成签到,获得积分10
18秒前
saying发布了新的文献求助10
18秒前
123123完成签到,获得积分10
18秒前
隐形曼青应助阿卡宁采纳,获得10
19秒前
负责紊完成签到,获得积分10
19秒前
善良的火发布了新的文献求助10
21秒前
haha完成签到,获得积分10
21秒前
23秒前
sugar完成签到,获得积分10
24秒前
活在当下完成签到,获得积分10
24秒前
26秒前
ssy发布了新的文献求助10
26秒前
小嘉贞完成签到,获得积分10
28秒前
鸡蛋黄完成签到,获得积分10
29秒前
高分求助中
【提示信息,请勿应助】关于scihub 10000
Les Mantodea de Guyane: Insecta, Polyneoptera [The Mantids of French Guiana] 3000
徐淮辽南地区新元古代叠层石及生物地层 3000
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
Global Eyelash Assessment scale (GEA) 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 550
Research on Disturbance Rejection Control Algorithm for Aerial Operation Robots 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 4038524
求助须知:如何正确求助?哪些是违规求助? 3576221
关于积分的说明 11374737
捐赠科研通 3305912
什么是DOI,文献DOI怎么找? 1819354
邀请新用户注册赠送积分活动 892688
科研通“疑难数据库(出版商)”最低求助积分说明 815048