CASR: A Robust Cyclic Framework for Arbitrary Large-Scale Super-Resolution with Distribution Alignment and Self-Similarity Awareness

TL;DR

CASR introduces a cyclic super-resolution framework that ensures stable, high-quality arbitrary-scale image enhancement by addressing distribution shift and self-similarity preservation.

Contribution

The paper proposes a novel cyclic framework with distribution alignment and self-similarity modules, enabling stable arbitrary-scale super-resolution with a single model.

Findings

Reduces distribution drift across iterations.

Preserves long-range texture consistency.

Achieves superior generalization at extreme magnifications.

Abstract

Arbitrary-Scale SR (ASISR) remains fundamentally limited by cross-scale distribution shift: once the inference scale leaves the training range, noise, blur, and artifacts accumulate sharply. We revisit this challenge from a cross-scale distribution transition perspective and propose CASR, a simple yet highly efficient cyclic SR framework that reformulates ultra-magnification as a sequence of in-distribution scale transitions. This design ensures stable inference at arbitrary scales while requiring only a single model. CASR tackles two major bottlenecks: distribution drift across iterations and patch-wise diffusion inconsistencies. The proposed SSAM module aligns structural distributions via superpixel aggregation, preventing error accumulation, while SARM module restores high-frequency textures by enforcing correlation-guided consistency and preserving self-similarity structure through correlation alignment. Despite using only a single model, our approach significantly reduces distribution drift, preserves long-range texture consistency, and achieves superior generalization even at extreme magnification.