用平均速度场一步实现高质量图像超分辨率，速度快且细节更真实。
MeanSR: Restoration Trajectory Learning for One-Step Perceptual Super-Resolution
- 学习低分辨率输入到高分辨率输出的平均运动轨迹，一步生成结果。
- 在CLIPIQA、MUSIQ等指标上超越CTMSR，FLOPs和延迟大幅降低。
- 适合追求高效与逼真视觉效果的图像重建应用。
基于扩散模型的超分辨率虽能生成高感知质量图像，但需耗时的迭代去噪。现有一步蒸馏方法依赖昂贵预训练教师模型，而CTMSR通过PF-ODE一致性训练避免蒸馏，但未显式建模从低分辨率（LR）到高分辨率（HR）的恢复动态。本文提出MeanSR，一种一步感知超分辨率方法，通过学习条件于低分辨率输入的平均速度场，直接捕捉从退化或噪声输入到合理高分辨率输出的有限时间转换过程。我们进一步重构分布轨迹匹配以生成平均速度场，并引入阶段感知时间采样策略提升轨迹学习效果。在合成与真实世界基准测试中，MeanSR在CLIPIQA、MUSIQ和MANIQA指标上优于CTMSR，同时显著降低计算量（FLOPs）与推理延迟。此外，其重建结构更锐利，纹理更真实，感知伪影更少。
原文摘要 · Abstract (English)
Diffusion-based super-resolution (SR) achieves strong perceptual quality but requires costly iterative denoising. Existing one-step distillation methods reduce inference time but depend on expensive pretrained teachers, whereas CTMSR avoids distillation through PF-ODE consistency training yet does not explicitly model the restoration dynamics from low-resolution (LR) inputs to high-resolution (HR) images. We propose MeanSR, a one-step perceptual SR method that learns an LR-conditioned average velocity field to directly capture the finite-time transition from degraded or noisy inputs to plausible HR outputs. We further reformulate distribution trajectory matching for average-velocity generation and introduce a Stage-Aware Temporal Sampling strategy to improve trajectory learning. Experiments on synthetic and real-world benchmarks show that MeanSR outperforms CTMSR on CLIPIQA, MUSIQ, and MANIQA while substantially reducing FLOPs and inference latency. MeanSR also reconstructs sharper structures and more realistic textures with fewer perceptual artifacts.
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。