提出可任意放大上百倍的图像超分辨率方法，解决大尺度放大模糊问题。
Stroke-based Cyclic Amplifier: Image Super-Resolution at Arbitrary Ultra-Large Scales
- 用笔画向量分解图像，逐轮迭代放大并修复细节。
- 在×100放大下仍保持清晰，显著优于现有方法。
- 适合需要超大倍数放大的图像修复与增强任务。
现有任意尺度图像超分辨率方法在放大倍数超出训练范围时性能显著下降，导致严重模糊。为此，我们提出统一模型Stroke-based Cyclic Amplifier（SbCA），用于超大尺度放大。其核心是笔画向量放大器，将图像分解为一系列以向量图形表示的笔画进行放大；随后，细节补全模块恢复缺失细节，确保高保真重建。通过循环策略，仅需一次训练即可实现所有放大尺度的迭代精修，且子尺度保持在训练范围内。该方法有效缓解分布漂移问题，消除伪影、噪声和模糊，生成高质量高分辨率图像。在合成与真实数据集上的实验表明，本方法在超大尺度放大任务（如×100）中显著优于现有技术，视觉质量远超当前最优方案。
原文摘要 · Abstract (English)
Prior Arbitrary-Scale Image Super-Resolution (ASISR) methods often experience a significant performance decline when the upsampling factor exceeds the range covered by the training data, introducing substantial blurring. To address this issue, we propose a unified model, Stroke-based Cyclic Amplifier (SbCA), for ultra-large upsampling tasks. The key of SbCA is the stroke vector amplifier, which decomposes the image into a series of strokes represented as vector graphics for magnification. Then, the detail completion module also restores missing details, ensuring high-fidelity image reconstruction. Our cyclic strategy achieves ultra-large upsampling by iteratively refining details with this unified SbCA model, trained only once for all, while keeping sub-scales within the training range. Our approach effectively addresses the distribution drift issue and eliminates artifacts, noise and blurring, producing high-quality, high-resolution super-resolved images. Experimental validations on both synthetic and real-world datasets demonstrate that our approach significantly outperforms existing methods in ultra-large upsampling tasks (e.g. $\times100$), delivering visual quality far superior to state-of-the-art techniques.
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。