发表机构
Morpho, Inc.（Morpho公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出一种保真度约束锚定框架，可将黑盒去噪器输出锚定到输入，通过PSNR或SSIM控制混合因子，在DIV2K数据集上验证其能平衡去噪性能与自然性，且SSIM锚定方法一致性更优。
AI 中文摘要
我们提出了一种保真度约束框架，该框架无需重新训练且仅需少量额外计算，即可将黑盒去噪器的输出锚定到其输入。该方法将去噪图像与输入进行线性混合，并选择满足规定局部保真度约束的最大混合因子，约束依据峰值信噪比（PSNR）或结构相似性指数（SSIM）设定。对于PSNR控制，在局部常数混合假设下可获得闭式解；对于SSIM控制，我们在相同假设下基于逆SSIM推导了易处理的公式，并通过迭代求根法高效求解。在带有合成高斯噪声的DIV2K图像，以及Real-ESRGAN和非局部均值去噪器的输出上开展的实验表明，所提锚定策略可在平衡去噪性能与统计自然性（由残差噪声的超额峰度衡量）的同时提供有效的保真度控制。特别地，基于SSIM的锚定方法相较于基于PSNR的锚定方法，在不同噪声水平下表现出更一致的行为。
英文摘要
We propose a fidelity-constrained framework that anchors the output of a black-box denoiser to its input without retraining and with little additional computation. The method linearly blends the denoised image with the input and selects the maximum blending factor that satisfies a prescribed local fidelity constraint using Peak Signal-to-Noise Ratio (PSNR) or Structural Similarity Index (SSIM). For PSNR control, a closed-form solution is obtained under a local constant-blending assumption. For SSIM control, we derive a tractable formulation based on inverse SSIM under the same assumption and solve it efficiently using iterative root finding. Experiments on DIV2K images with synthetic Gaussian noise and outputs from Real-ESRGAN and a non-local means denoiser show that the proposed anchoring strategy provides effective fidelity control while balancing denoising performance and statistical naturalness, as measured by the excess kurtosis of residual noise. In particular, SSIM-based anchoring yields more consistent behavior across noise levels than PSNR-based anchoring.
Comments5 pages, 5 figures. Supplementary material is available as an ancillary file
