UnSCAR: Universal, Scalable, Controllable, and Adaptable Image Restoration

TL;DR

This paper introduces UnSCAR, a scalable and controllable universal image restoration method that uses a multi-branch mixture-of-experts architecture to handle over sixteen degradations, improving robustness and adaptability.

Contribution

The paper proposes a novel multi-branch mixture-of-experts architecture for scalable, universal image restoration that effectively manages multiple degradations and generalizes to unseen domains.

Findings

Supports over sixteen degradations simultaneously

Achieves superior performance on benchmark datasets

Enables user-controllable restoration across degradations

Abstract

Universal image restoration aims to recover clean images from arbitrary real-world degradations using a single inference model. Despite significant progress, existing all-in-one restoration networks do not scale to multiple degradations. As the number of degradations increases, training becomes unstable, models grow excessively large, and performance drops across both seen and unseen domains. In this work, we show that scaling universal restoration is fundamentally limited by interference across degradations during joint learning, leading to catastrophic task forgetting. To address this challenge, we introduce a unified inference pipeline with a multi-branch mixture-of-experts architecture that decomposes restoration knowledge across specialized task-adaptable experts. Our approach enables scalable learning (over sixteen degradations), adapts and generalizes robustly to unseen domains, and supports user-controllable restoration across degradations. Beyond achieving superior performance across benchmarks, this work establishes a new design paradigm for scalable and controllable universal image restoration.