Low-Rank Tensor Function Representation for Multi-Dimensional Data Recovery
This work addresses the problem of representing multi-dimensional data beyond discrete meshgrids for researchers and practitioners in machine learning, computer vision, and computer graphics, offering a novel continuous representation approach.
The paper tackles the limitation of classical low-rank tensor representations, which are restricted to finite meshgrids, by proposing a low-rank tensor function representation (LRTFR) that enables continuous data representation with infinite resolution. The method demonstrates superior performance in applications like image inpainting, denoising, hyperparameter optimization, and point cloud upsampling compared to state-of-the-art methods.
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.