Learning Invariant Representation for Unsupervised Image Restoration
This addresses domain-shift issues in unsupervised image restoration for applications like noise removal, but it appears incremental as it builds on existing domain transfer frameworks with added modules.
The paper tackles the problem of domain-shift in unsupervised image restoration by proposing a method that learns invariant representations from noisy data to reconstruct clear images, achieving comparable performance to state-of-the-art supervised and unsupervised methods on synthetic and real noise removal tasks.
Recently, cross domain transfer has been applied for unsupervised image restoration tasks. However, directly applying existing frameworks would lead to domain-shift problems in translated images due to lack of effective supervision. Instead, we propose an unsupervised learning method that explicitly learns invariant presentation from noisy data and reconstructs clear observations. To do so, we introduce discrete disentangling representation and adversarial domain adaption into general domain transfer framework, aided by extra self-supervised modules including background and semantic consistency constraints, learning robust representation under dual domain constraints, such as feature and image domains. Experiments on synthetic and real noise removal tasks show the proposed method achieves comparable performance with other state-of-the-art supervised and unsupervised methods, while having faster and stable convergence than other domain adaption methods.