通过优化VMAF指标，发现轻微亮度变化可显著提升图像质量评分而不影响主观感受。
Towards properties of adversarial image perturbations
- 直接在PyTorch中优化VMAF指标生成对抗扰动
- 局部亮度变化约10个像素单位使VMAF提升60%
- 扰动幅度与亮度呈近似线性关系，适合质量评估研究
采用随机梯度方法研究导致VMAF图像质量指标显著提升的对抗扰动特性。根据可接受的PSNR值，分析了扰动结构，并基于傅里叶功率谱计算进行研究。结果显示，图像局部区域亮度适度变化（约10像素单位）可使VMAF提升约60%，而主观质量几乎不变。与某些其他方法不同，该扰动表现出扰动幅度与图像亮度的近似线性关系。研究基于PyTorch中的直接VMAF优化实现。同时发现，在使用相同直接VMAF优化进行去噪修复时，指标值与主观评价存在显著差异。
原文摘要 · Abstract (English)
Using stochastic gradient approach we study the properties of adversarial perturbations resulting in noticeable growth of VMAF image quality metric. The structure of the perturbations is investigated depending on the acceptable PSNR values and based on the Fourier power spectrum computations for the perturbations. It is demonstrated that moderate variation of image brightness ($\sim 10$ pixel units in a restricted region of an image can result in VMAF growth by $\sim 60\%$). Unlike some other methods demonstrating similar VMAF growth, the subjective quality of an image remains almost unchanged. It is also shown that the adversarial perturbations may demonstrate approximately linear dependence of perturbation amplitudes on the image brightness. The perturbations are studied based on the direct VMAF optimization in PyTorch. The significant discrepancies between the metric values and subjective judgements are also demonstrated when image restoration from noise is carried out using the same direct VMAF optimization.
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。