解决超分辨率任意缩放下的分布偏移问题，实现稳定高倍放大。
CASR: A Robust Cyclic Framework for Arbitrary Large-Scale Super-Resolution with Distribution Alignment and Self-Similarity Awareness
- 采用循环框架将超分分解为一系列分布一致的尺度过渡。
- 在极端放大下仍保持纹理一致性，误差积累显著减少。
- 仅需一个模型，适合需要通用高倍放大的实际应用。
任意尺度超分辨率（ASISR）受限于跨尺度分布偏移：当推理尺度超出训练范围时，噪声、模糊和伪影会急剧累积。本文从跨尺度分布转移视角重新审视该问题，提出CASR——一种简单高效的循环超分框架，将超大幅放转换为一系列分布一致的尺度过渡。该设计确保任意尺度下推理稳定，且仅需单一模型。CASR解决两大瓶颈：迭代中的分布漂移与局部块间扩散不一致。提出的SSAM模块通过超像素聚合对齐结构分布，防止误差累积；SARM模块通过相关性引导的一致性恢复高频纹理，并通过相关性对齐保留自相似结构。尽管仅使用单个模型，方法仍显著降低分布漂移，维持长程纹理一致性，在极端放大下实现卓越泛化能力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。