将复杂光子噪声转为标准高斯噪声，提升图像去噪效果
Poisson2Gaussian: Noise Gaussianization to Enhance Image Denoising
- 通过概率密度匹配将泊松噪声转化为独立同分布高斯噪声
- 在非高斯噪声场景下提升峰值信噪比最高达0.75 dB
- 不依赖干净数据或噪声参数，适配各类去噪模型
光子探测的量子本质决定了其固有的泊松随机性，广泛存在于摄影、显微和天文等领域。然而，我们控制性的数值研究发现，泊松混合噪声的信号相关性、异方差性和统计不对称性使得现有去噪器难以学习。相比之下，具有统计独立性和对称分布的独立同分布高斯噪声更易建模。为此，我们提出泊松到高斯（Poisson2Gaussian, P2G）方法，通过超越低阶矩的概率密度匹配，将真实世界复杂噪声显式转换为i.i.d.高斯噪声。同时设计无偏去噪框架，与下游去噪器协同，确保收敛至原始信号，无需成对干净数据或显式噪声参数。大量实验表明，P2G在多种数据集上持续达到最优性能；在噪声显著偏离高斯分布的挑战性场景中，可使PSNR提升最高0.75 dB。值得注意的是，P2G具有架构无关性，能为各类去噪器提供通用改进。源代码将公开。
原文摘要 · Abstract (English)
The quantum nature of light determines the inherent Poisson stochasticity of photon detection, which is ubiquitous in photography, microscopy, and astronomy. However, our controlled numerical studies reveal that the signal-dependency, heteroscedasticity, and statistical asymmetry of Poisson-mixed noise make it challenging for existing denoisers to learn. In contrast, i.i.d. Gaussian noise, with its statistical independence and symmetric distribution, is easier to model for networks. To address this gap, we propose Poisson2Gaussian (P2G), a noise Gaussianization method that explicitly converts complex real-world noise to i.i.d. Gaussian noise via probability density matching beyond low-order moments. We also design an unbiased denoising framework that synergizes P2G with downstream denoisers, ensuring convergence to the underlying signal without requiring paired clean data or explicit noise parameters. Extensive experiments demonstrate that P2G consistently achieves state-of-the-art performance across diverse datasets. In challenging scenarios where noise strongly deviates from Gaussian statistics, our method improves the PSNR by up to 0.75 dB. Notably, P2G is architecture-agnostic and can provide universal improvements for various denoisers. The source code will be publicly available.
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。