用新损失函数提升去模糊图像锐度，减少伪影。
Impact of a Sharpness Based Loss Function for Removing Out-of-Focus Blur
- 引入基于锐度的损失函数Q，优化去模糊模型。
- 锐度提升15%，新指标Omega提高10%。
- 适合关注图像清晰度与伪影控制的研究者。
近期研究探索了复杂的去模糊损失函数。本文探讨了一种先前提出的损失函数Q的影响力，该函数显式关注图像锐度，并用于微调当前最先进的去模糊模型。标准图像质量指标（如PSNR或SSIM）无法区分锐度与振铃伪影。为此，我们提出一种新型全参考图像质量度量Omega，结合PSNR与Q。该度量对振铃伪影敏感，但对锐度轻微提升不敏感，因而成为比较去模糊结果的公平指标。实验表明，相较于使用标准损失，本方法在锐度（Q）上提升15%，在Omega指标上最高提升10%。
原文摘要 · Abstract (English)
Recent research has explored complex loss functions for deblurring. In this work, we explore the impact of a previously introduced loss function - Q which explicitly addresses sharpness and employ it to fine-tune State-of-the-Art (SOTA) deblurring models. Standard image quality metrics such as PSNR or SSIM do not distinguish sharpness from ringing. Therefore, we propose a novel full-reference image quality metric Omega that combines PSNR with Q. This metric is sensitive to ringing artefacts, but not to a slight increase in sharpness, thus making it a fair metric for comparing restorations from deblurring mechanisms. Our approach shows an increase of 15 percent in sharpness (Q) and up to 10 percent in Omega over the use of standard losses.
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。