paper-with-me

Papers

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

2022-12-01 · YiSi Luo, XiLe Zhao, Zhemin Li, Michael K. Ng, Deyu Meng

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 only represent data on finite meshgrid due to their intrinsical discrete nature, which hinders their potential applicability in many scenarios beyond meshgrid. To break this barrier, we propose a low-rank tensor function representation (LRTFR), which can continuously represent data beyond meshgrid with infinite resolution. 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. We theoretically justify that both low-rank and smooth regularizations are harmoniously unified in the 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.

📄 PDF Abstract BibTeX arXiv:2212.00262

Code (0)

등록된 구현이 없습니다.

Tasks

DenoisingHyperparameter OptimizationImage Inpaintingpoint cloud upsampling

Methods 이 논문이 사용한 방법론

Inpainting Train a convolutional neural network to generate the contents of an arbitrary image region conditioned on its surroundings.

Similar Papers 제목 키워드 기반

Tensor and Matrix Low-Rank Value-Function Approximation in Reinforcement Learning

2022-01-21 · Sergio Rozada, Santiago Paternain, Antonio G. Marques

Value-function (VF) approximation is a central problem in Reinforcement Learning (RL). Classical non-parametric VF estimation suffers from the curse of dimensionality. As a result, parsimonious parametric models have bee…

reinforcement-learningReinforcement Learning (RL)

An Iterative Reweighted Method for Tucker Decomposition of Incomplete Multiway Tensors

2015-11-15 · Linxiao Yang, Jun Fang, Hongbin Li, Bing Zeng

We consider the problem of low-rank decomposition of incomplete multiway tensors. Since many real-world data lie on an intrinsically low dimensional subspace, tensor low-rank decomposition with missing entries has applic…

Image InpaintingRecommendation Systems

Tensor-Efficient High-Dimensional Q-learning

2025-11-05 · Junyi Wu, Dan Li arxiv

High-dimensional reinforcement learning(RL) faces challenges with complex calculations and low sample efficiency in large state-action spaces. Q-learning algorithms struggle particularly with the curse of dimensionality,…

Reinforcement Learning

HLRTF: Hierarchical Low-Rank Tensor Factorization for Inverse Problems in Multi-Dimensional Imaging

2022-01-01 · CVPR 2022 1 · YiSi Luo, Xi-Le Zhao, Deyu Meng, Tai-Xiang Jiang

Inverse problems in multi-dimensional imaging, e.g., completion, denoising, and compressive sensing, are challenging owing to the big volume of the data and the inherent ill-posedness. To tackle these issues, this wo…

Compressive SensingDenoising

When Bayesian Tensor Completion Meets Multioutput Gaussian Processes: Functional Universality and Rank Learning

2025-12-25 · Siyuan Li, Shikai Fang, Lei Cheng, Feng Yin 외 arxiv

Functional tensor decomposition can analyze multi-dimensional data with real-valued indices, paving the path for applications in machine learning and signal processing. A limitation of existing approaches is the assumpti…

Gaussian Processes