CASR：面向任意大尺度超分辨率的分布对齐与自相似感知鲁棒循环框架
CASR: A Robust Cyclic Framework for Arbitrary Large-Scale Super-Resolution with Distribution Alignment and Self-Similarity Awareness
把超大倍率超分拆解为多次「分布内」尺度跃迁的循环框架，配合超像素聚合对齐结构分布、相关性引导保持自相似纹理，为任意尺度超分在训练尺度之外稳定推理提供了可复用的单模型方案。
原文依据 reformulates ultra-magnification as a sequence of in-distribution scale transitions
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论任意尺度超分辨率（ASISR）仍从根本上受限于跨尺度分布偏移：一旦推理尺度离开训练范围，噪声、模糊与伪影便会急剧累积。本文从跨尺度分布迁移的视角重新审视这一挑战，提出 CASR——一个简单却高效的循环超分框架，将超大倍率放大重新表述为一系列处于分布内的尺度跃迁。该设计在仅需单一模型的前提下保证了任意尺度下的稳定推理。CASR 针对两大瓶颈：迭代过程中的分布漂移与逐块扩散不一致性。所提出的 SSAM 模块通过超像素聚合对齐结构分布，防止误差累积；SARM 模块则通过施加相关性引导的一致性、并借助相关性对齐保持自相似结构，从而恢复高频纹理。尽管仅使用单一模型，本方法仍显著降低了分布漂移，保持了长程纹理一致性，并即使在极端放大倍率下也取得了更优的泛化能力。
英文原文摘要 1121 字符
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.