两篇新研究论文探讨了图像超分辨率（SR）技术的进展，特别关注扩散模型。第一篇论文“Mind the Gap”量化了跨传感器SR中的域间隙，强调了在合成数据与Sentinel-2和PlanetScope等传感器生成的真实世界卫星图像上训练模型所面临的挑战。第二篇论文“TinySR”介绍了一种更高效的扩散模型，专为真实世界图像超分辨率设计，通过剪枝和架构优化，实现了实时性能，同时显著减小了模型尺寸和计算成本。 AI
影响 这些论文推进了扩散模型的效率，并解决了域适应挑战，有望改善超分辨率技术的实际应用。
排序理由 两篇在arXiv上发表的学术论文，详细介绍了使用扩散模型进行图像超分辨率的新方法和分析。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2606.28039v1 Announce Type: cross Abstract: Demand for high-resolution satellite imagery has increased interest in super-resolution (SR) to bridge the spatial resolution gap between freely available missions such as Sentinel-2 and commercial systems like PlanetScope. Becaus…
Demand for high-resolution satellite imagery has increased interest in super-resolution (SR) to bridge the spatial resolution gap between freely available missions such as Sentinel-2 and commercial systems like PlanetScope. Because no sensor provides true paired low- and high-res…
arXiv:2508.17434v3 Announce Type: replace Abstract: Real-world image super-resolution (Real-ISR) focuses on recovering high-quality images from low-resolution inputs that suffer from complex degradations like noise, blur, and compression. Recently, diffusion models (DMs) have sho…