Low-Rank Tensor Function Representation for Multi-Dimensional Data Recovery

张量(固有定义) 计算机科学 增采样 修补 秩(图论) 人工智能 代表(政治) 外部数据表示 点云 算法 数学 图像(数学) 组合数学 政治 政治学 纯数学 法学
作者
Yisi Luo,Xi-Le Zhao,Zhemin Li,Michael K. Ng,Deyu Meng
出处
期刊:IEEE Transactions on Pattern Analysis and Machine Intelligence [IEEE Computer Society]
卷期号:46 (5): 3351-3369 被引量:14
标识
DOI:10.1109/tpami.2023.3341688
摘要

Since higher-order tensors are naturally suitable for representing multi-dimensional data in real-world, e.g., color images and videos, low-rank tensor representation has become one of the emerging areas in machine learning and computer vision. However, classical low-rank tensor representations can solely represent multi-dimensional discrete data on meshgrid, which hinders their potential applicability in many scenarios beyond meshgrid. To break this barrier, we propose a low-rank tensor function representation (LRTFR) parameterized by multilayer perceptrons (MLPs), which can continuously represent data beyond meshgrid with powerful representation abilities. Specifically, the suggested tensor function, which maps an arbitrary coordinate to the corresponding value, can continuously represent data in an infinite real space. Parallel to discrete tensors, we develop two fundamental concepts for tensor functions, i.e., the tensor function rank and low-rank tensor function factorization, and utilize MLPs to paramterize factor functions of the tensor function factorization. We theoretically justify that both low-rank and smooth regularizations are harmoniously unified in LRTFR, which leads to high effectiveness and efficiency for data continuous representation. Extensive multi-dimensional data recovery applications arising from image processing (image inpainting and denoising), machine learning (hyperparameter optimization), and computer graphics (point cloud upsampling) substantiate the superiority and versatility of our method as compared with state-of-the-art methods. Especially, the experiments beyond the original meshgrid resolution (hyperparameter optimization) or even beyond meshgrid (point cloud upsampling) validate the favorable performances of our method for continuous representation.
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
刚刚
善学以致用应助薛华倩采纳,获得10
2秒前
huqingtao完成签到,获得积分10
2秒前
了了完成签到,获得积分10
2秒前
3秒前
3秒前
666完成签到,获得积分10
4秒前
7秒前
8秒前
星辰大海应助樱桃窝窝头采纳,获得10
9秒前
258369完成签到,获得积分10
10秒前
11秒前
12秒前
Sunwenrui发布了新的文献求助10
13秒前
薛华倩发布了新的文献求助10
17秒前
白白SAMA123发布了新的文献求助10
17秒前
17秒前
昏睡的飞机完成签到,获得积分10
17秒前
18秒前
19秒前
21秒前
miaojuly发布了新的文献求助10
21秒前
共享精神应助追寻筮采纳,获得10
21秒前
22秒前
莫歌完成签到 ,获得积分10
22秒前
2889580752发布了新的文献求助10
23秒前
量子星尘发布了新的文献求助10
23秒前
杨冠文发布了新的文献求助10
23秒前
HOME发布了新的文献求助10
25秒前
liz_应助努力工作的人采纳,获得10
26秒前
Lycerdoctor发布了新的文献求助10
26秒前
东瓜魔法师完成签到,获得积分10
26秒前
杨冠文完成签到,获得积分10
28秒前
28秒前
Owen应助肖肖采纳,获得10
29秒前
han应助薛华倩采纳,获得10
30秒前
Rational完成签到,获得积分10
30秒前
祁i应助liuzengzhang666采纳,获得10
31秒前
可爱的函函应助A阿澍采纳,获得10
32秒前
明理凝阳完成签到,获得积分10
33秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
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 3988868
求助须知:如何正确求助?哪些是违规求助? 3531255
关于积分的说明 11253071
捐赠科研通 3269858
什么是DOI,文献DOI怎么找? 1804822
邀请新用户注册赠送积分活动 881994
科研通“疑难数据库(出版商)”最低求助积分说明 809035