Multi-dimensional Signal Recovery using Low-rank Deconvolution
This work addresses signal recovery challenges in computer vision, but it appears incremental as it builds on existing methods like convolutional sparse coding and low-rank approximation.
The authors tackled the problem of signal recovery by introducing Low-rank Deconvolution, a framework that combines convolutional sparse coding and low-rank approximation to learn efficient feature maps, and demonstrated its effectiveness in compressed video representation and image in-painting tasks.
In this work we present Low-rank Deconvolution, a powerful framework for low-level feature-map learning for efficient signal representation with application to signal recovery. Its formulation in multi-linear algebra inherits properties from convolutional sparse coding and low-rank approximation methods as in this setting signals are decomposed in a set of filters convolved with a set of low-rank tensors. We show its advantages by learning compressed video representations and solving image in-painting problems.