Cascade residuals guided nonlinear dictionary learning
Date
2018-04-18
Authors
Zhang, Tong
Porikli, Fatih
Journal Title
Journal ISSN
Volume Title
Publisher
Academic Press
Abstract
In this paper, we aim to extend dictionary learning onto hierarchical image representations in a principled way. To achieve dictionary atoms capture additional information from extended receptive fields and attain improved descriptive capacity, we present a two-pass multi-resolution cascade framework for dictionary learning and sparse coding. This cascade method allows collaborative reconstructions at different resolutions using only the same dimensional dictionary atoms. The jointly learned dictionary comprises atoms that adapt to the information available at the coarsest layer, where the support of atoms reaches a maximum range, and the residual images, where the supplementary details refine progressively a reconstruction objective. The residual at a layer is computed by the difference between the aggregated reconstructions of the previous layers and the downsampled original image at that layer. Our method generates flexible and accurate representations using only a small number of coefficients. It is computationally efficient since it encodes the image at the coarsest resolution while yielding very sparse residuals. Our extensive experiments on multiple image coding, denoising, inpainting and artifact removal tasks demonstrate that our method provides superior results.
Description
Keywords
Sparse coding, Dictionary learning
Citation
Collections
Source
Computer Vision and Image Understanding
Type
Journal article
Book Title
Entity type
Access Statement
License Rights
Restricted until
2037-12-31
Downloads
File
Description