Saved in:
Bibliographic Details
Main Authors: Wen, Fei, Wang, Wei, Yan, Zeyu, Jiang, Wenbin
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2305.00273
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914039277289472
author Wen, Fei
Wang, Wei
Yan, Zeyu
Jiang, Wenbin
author_facet Wen, Fei
Wang, Wei
Yan, Zeyu
Jiang, Wenbin
contents Optimal transport (OT) has recently been shown as a promising criterion for unsupervised restoration when no explicit prior model is available. Despite its theoretical appeal, OT still significantly falls short of supervised methods on challenging tasks such as super-resolution, deraining, and dehazing. In this paper, we propose a \emph{sparsity-aware optimal transport} (SOT) framework to bridge this gap by leveraging a key observation: the degradations in these tasks exhibit distinct sparsity in the frequency domain. Incorporating this sparsity prior into OT can significantly reduce the ambiguity of the inverse mapping for restoration and substantially boost performance. We provide analysis to show exploiting degradation sparsity benefits unsupervised restoration learning. Extensive experiments on real-world super-resolution, deraining, and dehazing demonstrate that SOT offers notable performance gains over standard OT, while achieving superior perceptual quality compared to existing supervised and unsupervised methods. In particular, SOT consistently outperforms existing unsupervised methods across all three tasks and narrows the performance gap to supervised counterparts.
format Preprint
id arxiv_https___arxiv_org_abs_2305_00273
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Optimal Transport Based Unsupervised Restoration Learning Exploiting Degradation Sparsity
Wen, Fei
Wang, Wei
Yan, Zeyu
Jiang, Wenbin
Computer Vision and Pattern Recognition
Image and Video Processing
Optimal transport (OT) has recently been shown as a promising criterion for unsupervised restoration when no explicit prior model is available. Despite its theoretical appeal, OT still significantly falls short of supervised methods on challenging tasks such as super-resolution, deraining, and dehazing. In this paper, we propose a \emph{sparsity-aware optimal transport} (SOT) framework to bridge this gap by leveraging a key observation: the degradations in these tasks exhibit distinct sparsity in the frequency domain. Incorporating this sparsity prior into OT can significantly reduce the ambiguity of the inverse mapping for restoration and substantially boost performance. We provide analysis to show exploiting degradation sparsity benefits unsupervised restoration learning. Extensive experiments on real-world super-resolution, deraining, and dehazing demonstrate that SOT offers notable performance gains over standard OT, while achieving superior perceptual quality compared to existing supervised and unsupervised methods. In particular, SOT consistently outperforms existing unsupervised methods across all three tasks and narrows the performance gap to supervised counterparts.
title Optimal Transport Based Unsupervised Restoration Learning Exploiting Degradation Sparsity
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2305.00273