凸性感知噪声校准：面向噪声水平未知图像去噪的自监督框架
Convexity-Aware Noise Calibration: A Self-Supervised Framework for Noise-Level-Unknown Image Denoising
把噪声水平估计转化为「去噪后方差随噪声水平变化」的单调关系，并用三分搜索加深度模型求解，可直接复用于盲去噪、真实噪声数据合成训练对以及任何需要估计未知噪声强度的复原流程。
原文依据 we rigorously derive a relationship between the noise level and the variance of the denoised image
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论图像去噪是计算机视觉中的一项基础任务，旨在从受噪声污染的观测中恢复干净图像。有监督深度学习方法在已知噪声水平的成对数据上训练时能够取得显著性能，但由于真实场景中的噪声特性往往未知，其实际适用性受到限制。现有的无监督技术，如盲点网络或基于统计估计的方法，要么因信息损失而牺牲性能，要么受噪声水平估计不准确之困。为应对这些挑战，我们提出一种新颖的两阶段自监督去噪框架，首先直接从含噪图像中准确估计噪声水平，无需干净参考图像或噪声先验知识。基于 Noisier2Noise 的理论洞见，我们严格推导了噪声水平与去噪图像方差之间的关系，从而可借助深度学习模型与三分搜索策略实现稳健估计。随后，估计得到的噪声水平被用于合成训练对，以进行有监督去噪。实验表明，本方法优于现有无监督方法与传统噪声估计技术，性能与使用已知噪声水平训练的有监督方法相当，在某些情况下甚至更优。所提框架有效克服了有监督方法在未知加性白高斯噪声情形下的训练数据对限制。代码已开源：https://github.com/zhanzhanblue/CANC。
英文原文摘要 1575 字符
Image denoising is a fundamental task in computer vision aimed at recovering clean images from noise-corrupted observations. While supervised deep learning methods achieve remarkable performance when trained on paired data with known noise levels, their real-world applicability is limited as noise characteristics are often unknown. Existing unsupervised techniques, such as blind-spot networks or methods based on statistical estimation, either compromise performance due to information loss or suffer from inaccuracies in noise level estimation. To address these challenges, we propose a novel two-stage self-supervised denoising framework that first accurately estimates the noise level directly from noisy images, without requiring clean references or prior noise knowledge. Building upon theoretical insights from Noisier2Noise, we rigorously derive a relationship between the noise level and the variance of the denoised image, enabling robust estimation via a deep learning model and a ternary search strategy. The estimated noise level is then used to synthesize training pairs for supervised denoising. Experiments demonstrate that our method outperforms existing unsupervised approaches and traditional noise estimation techniques, achieving performance competitive with--and in some cases surpassing--supervised methods trained with known noise levels. The proposed framework effectively overcomes the training data pair limitations of supervised approaches for unknown additive white Gaussian noise. Our code is available at https://github.com/zhanzhanblue/CANC.