# 着色噪声：对抗性Sobolev对齐实现保真图像超分辨率

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-05-22 08:00
- AIHOT 分数：53
- AIHOT 链接：https://aihot.virxact.com/items/cmpmd6ghh0noksl01gtrhw888
- 原文链接：https://arxiv.org/abs/2605.23264

## AI 摘要

图像超分辨率（SR）中的生成先验常因频谱失配而牺牲保真度。本文提出ASASR框架，通过“着色”噪声转换核以匹配自然图像频谱衰减，将生成流重构为Sobolev诱导的黎曼几何，从而解决这一问题。其核心在于集成一个基于Riesz表示定理的参数化对抗器，该对抗器生成等价于最差Sobolev梯度的负样本，沿可行结构失败的切线空间引导优化。评估表明，ASASR在保持频谱一致性与结构保真度方面优于现有生成方法，能有效缓解伪影。

## 正文

Generative priors in Image Super-Resolution (SR) often compromise faithful restoration, we attribute this limitation to a fundamental spectral misalignment between isotropic objectives and the intrinsic natural image manifold. While Direct Preference Optimization offers a path to alignment, its reliance on spectrally flat Gaussian noise fails to distinguish authentic high-frequency details from hallucinations. To bridge this geometric gap, we propose ASASR, a theoretically grounded framework that recasts the generative flow into a Sobolev-induced Riemannian geometry by explicitly coloring the noise transition kernel to mirror natural spectral decay. Driving this geometric alignment, we integrate a parametric adversary grounded in the Riesz Representation Theorem, which synthesizes targeted negative samples equivalent to worst-case Sobolev gradients to direct optimization along the tangent space of plausible structural failures. Extensive evaluations demonstrate that ASASR outperforms leading generative baselines, particularly in preserving spectral consistency and structural fidelity, offering a robust solution that effectively mitigates artifacts.