Federated Learning for Blind Image Super-Resolution

TL;DR

This paper introduces a federated learning approach for blind image super-resolution that preserves user privacy, models real-world degradations across distributed devices, and proposes new benchmarks to evaluate such methods in realistic scenarios.

Contribution

It pioneers the integration of federated learning with blind image super-resolution and develops benchmarks to evaluate this approach under diverse degradation distributions.

Findings

Federated learning enables training on real-world degradations without data centralization.

New benchmarks simulate diverse degradation types across users.

The approach improves applicability of super-resolution models in real-world, privacy-sensitive settings.

Abstract

Traditional blind image SR methods need to model real-world degradations precisely. Consequently, current research struggles with this dilemma by assuming idealized degradations, which leads to limited applicability to actual user data. Moreover, the ideal scenario - training models on data from the targeted user base - presents significant privacy concerns. To address both challenges, we propose to fuse image SR with federated learning, allowing real-world degradations to be directly learned from users without invading their privacy. Furthermore, it enables optimization across many devices without data centralization. As this fusion is underexplored, we introduce new benchmarks specifically designed to evaluate new SR methods in this federated setting. By doing so, we employ known degradation modeling techniques from SR research. However, rather than aiming to mirror real degradations, our benchmarks use these degradation models to simulate the variety of degradations found across clients within a distributed user base. This distinction is crucial as it circumvents the need to precisely model real-world degradations, which limits contemporary blind image SR research. Our proposed benchmarks investigate blind image SR under new aspects, namely differently distributed degradation types among users and varying user numbers. We believe new methods tested within these benchmarks will perform more similarly in an application, as the simulated scenario addresses the variety while federated learning enables the training on actual degradations.