Learning Multiscale Convolutional Dictionaries for Image Reconstruction. (arXiv:2011.12815v3 [cs.CV] UPDATED)

Convolutional neural networks (CNNs) have been tremendously successful in
solving imaging inverse problems. To understand their success, an effective
strategy is to construct simpler and mathematically more tractable
convolutional sparse coding (CSC) models that share essential ingredients with
CNNs. Existing CSC methods, however, underperform leading CNNs in challenging
inverse problems. We hypothesize that the performance gap may be attributed in
part to how they process images at different spatial scales: While many CNNs
use multiscale feature representations, existing CSC models …

arxiv cv image learning