用可调循环次数控制超分质量与计算成本，无需重训练。
Test-time Cost-and-Quality Controllable Arbitrary-Scale Super-Resolution with Variable Fourier Components
- 通过傅里叶分量递归估计实现任意缩放超分
- 组件数越多，PSNR越高，最多提升1.2dB
- 测试时动态调节性能，适合资源受限场景
任意尺度超分辨率（SR）在实际应用中需在测试时灵活控制计算成本与图像质量。现有方法需修改模型结构并重新训练才能调整性能，难以灵活适配。为此，我们提出一种基于循环神经网络（RNN）与傅里叶表示的新方法：RNN逐次估计傅里叶分量（频率与振幅），并聚合生成高分辨率图像。由于RNN的迭代次数可在测试时自由调节，因此单个模型即可实现成本与质量的可控：迭代次数少则计算开销低、质量稍降，反之则质量更高但耗时增加。实验表明，更多傅里叶分量显著提升PSNR，最高达1.2dB；即使使用较少分量，本方法的PSNR下降幅度也低于其他先进方法。
原文摘要 · Abstract (English)
Super-resolution (SR) with arbitrary scale factor and cost-and-quality controllability at test time is essential for various applications. While several arbitrary-scale SR methods have been proposed, these methods require us to modify the model structure and retrain it to control the computational cost and SR quality. To address this limitation, we propose a novel SR method using a Recurrent Neural Network (RNN) with the Fourier representation. In our method, the RNN sequentially estimates Fourier components, each consisting of frequency and amplitude, and aggregates these components to reconstruct an SR image. Since the RNN can adjust the number of recurrences at test time, we can control the computational cost and SR quality in a single model: fewer recurrences (i.e., fewer Fourier components) lead to lower cost but lower quality, while more recurrences (i.e., more Fourier components) lead to better quality but more cost. Experimental results prove that more Fourier components improve the PSNR score. Furthermore, even with fewer Fourier components, our method achieves a lower PSNR drop than other state-of-the-art arbitrary-scale SR methods.
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。