Fast Unsupervised Tensor Restoration via Low-rank Deconvolution

2024/06/15 by David Reixach, Reixach, David, Josep Ramon Morros +1
Engineering · #Advanced SAR Imaging Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences

paper · pdf · doi:10.48550/arxiv.2406.10679

openalex publication_date 2024/06/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Low-rank Deconvolution (LRD) has appeared as a new multi-dimensional representation model that enjoys important efficiency and flexibility properties. In this work we ask ourselves if this analytical model can compete against Deep Learning (DL) frameworks like Deep Image Prior (DIP) or Blind-Spot Networks (BSN) and other classical methods in the task of signal restoration. More specifically, we propose to extend LRD with differential regularization. This approach allows us to easily incorporate Total Variation (TV) and integral priors to the formulation leading to considerable performance tested on signal restoration tasks such image denoising and video enhancement, and at the same time benefiting from its small computational cost.

Related

• Multi-dimensional Signal Recovery using Low-rank Deconvolution
• Under-Sampled High-Dimensional Data Recovery via Symbiotic Multi-Prior Tensor Reconstruction
• DeepTensor: Low-Rank Tensor Decomposition with Deep Network Priors
• Image Restoration using Total Variation Regularized Deep Image Prior
• The Power of Complementary Regularizers: Image Recovery via Transform Learning and Low-Rank Modeling