解决扩散模型超分辨率中的伪影问题，提升图像质量与细节还原。
Spectral and Trajectory Regularization for Diffusion Transformer Super-Resolution
- 采用非对称判别式蒸馏，缓解采样轨迹差异。
- 通过频域分布匹配，抑制高频泄漏导致的周期性伪影。
- 适用于追求高质量真实图像超分的开发者与研究者。
扩散变换器（DiT）在真实世界图像超分辨率（Real-ISR）中展现出巨大潜力，但其计算开销大的迭代采样过程需采用单步蒸馏。现有单步蒸馏方法在DiT上表现不佳，存在根本性轨迹错位，生成严重的网格状周期性伪影。为此，我们提出StrSR，一种新颖的单步对抗蒸馏框架，包含谱正则化与轨迹正则化。具体地，设计了非对称判别式蒸馏结构以弥合轨迹差距；并提出频域分布匹配策略，有效抑制由高频谱泄漏引发的DiT特有周期性伪影。大量实验表明，StrSR在量化指标与视觉感知上均达到当前最优性能。代码与模型将发布于 https://github.com/jkwang28/StrSR。
原文摘要 · Abstract (English)
Diffusion transformer (DiT) architectures show great potential for real-world image super-resolution (Real-ISR). However, their computationally expensive iterative sampling necessitates one-step distillation. Existing one-step distillation methods struggle with Real-ISR on DiT. They suffer from fundamental trajectory mismatch and generate severe grid-like periodic artifacts. To tackle these challenges, we propose StrSR, a novel one-step adversarial distillation framework featuring spectral and trajectory regularization. Specifically, we propose an asymmetric discriminative distillation architecture to bridge the trajectory gap. Additionally, we design a frequency distribution matching strategy to effectively suppress DiT-specific periodic artifacts caused by high-frequency spectral leakage. Extensive experiments demonstrate that StrSR achieves state-of-the-art performance in Real-ISR, across both quantitative metrics and visual perception. The code and models will be released at https://github.com/jkwang28/StrSR .
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。