Sparse Coding on Cascaded Residuals
This work addresses image processing tasks like denoising and inpainting for researchers and practitioners, representing an incremental improvement through a novel hybrid approach.
The paper tackled the problem of combining dictionary learning with hierarchical image representation by introducing a two-pass multi-resolution cascade framework that uses jointly learned dictionaries across resolutions. The method achieved more flexible and accurate representations with fewer coefficients, outperforming state-of-the-art techniques in image coding, denoising, inpainting, and artifact removal tasks.
This paper seeks to combine dictionary learning and hierarchical image representation in a principled way. To make dictionary atoms capturing 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. The cascade allows collaborative reconstructions at different resolutions using the same dimensional dictionary atoms. Our jointly learned dictionary comprises atoms that adapt to the information available at the coarsest layer where the support of atoms reaches their maximum range and the residual images where the supplementary details progressively refine the 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 more flexible and accurate representations using much less number of coefficients. Its computational efficiency stems from encoding at the coarsest resolution, which is minuscule, and encoding the residuals, which are relatively much sparse. Our extensive experiments on multiple datasets demonstrate that this new method is powerful in image coding, denoising, inpainting and artifact removal tasks outperforming the state-of-the-art techniques.