Multi-level encoder-decoder architectures for image restoration

Show simple item record Mastan, Indra Deep Raman, Shanmuganathan 2019-05-20T11:11:56Z 2019-05-20T11:11:56Z 2019-05
dc.identifier.citation Mastan, Indra Deep and Raman, Shanmuganathan, “Multi-level encoder-decoder architectures for image restoration”, arXiv, Cornell University Library, DOI: arXiv:1905.00322, May 2019. en_US
dc.description.abstract Many real-world solutions for image restoration are learning-free and based on handcrafted image priors such as self-similarity. Recently, deep-learning methods that use training data have achieved state-of-the-art results in various image restoration tasks (e.g., super-resolution and inpainting). Ulyanov et al. bridge the gap between these two families of methods (CVPR 18). They have shown that learning-free methods perform close to the state-of-the-art learning-based methods (approximately 1 PSNR). Their approach benefits from the encoder-decoder network. In this paper, we propose a framework based on the multi-level extensions of the encoder-decoder network, to investigate interesting aspects of the relationship between image restoration and network construction independent of learning. Our framework allows various network structures by modifying the following network components: skip links, cascading of the network input into intermediate layers, a composition of the encoder-decoder subnetworks, and network depth. These handcrafted network structures illustrate how the construction of untrained networks influence the following image restoration tasks: denoising, super-resolution, and inpainting. We also demonstrate image reconstruction using flash and no-flash image pairs. We provide performance comparisons with the state-of-the-art methods for all the restoration tasks above. en_US
dc.description.statementofresponsibility by Indra Deep Mastan and Shanmuganathan Raman
dc.language.iso en_US en_US
dc.publisher Cornell University Library en_US
dc.title Multi-level encoder-decoder architectures for image restoration en_US
dc.type Preprint en_US
dc.relation.journal arXiv

Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search Digital Repository


My Account