发表机构
University of Toronto; Vector Institute; AI-Center Toronto, Samsung Electronics; York University（多伦多大学; 向量研究所; 多伦多人工智能中心，三星电子公司; 约克大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究低光原始图像去噪，提出无需相机校准的范式，引入偏差估计器网络预测黑电平误差，在多个数据集上评估表现出色，还发现SIDD数据集问题并提供校正基准。
AI 中文摘要
原始图像由于光线的随机性和传感器硬件缺陷而固有地存在噪声。随着实际光子数下降，噪声与信号的比率恶化，因此在低光条件下，强大的去噪对于高质量结果尤为重要。虽然最近的数据驱动方法性能强劲，但通常依赖大规模有噪声-无噪声图像对，成本高且难以收集。参数噪声模型可生成合成训练数据，但需要精确相机校准，对未知设备通常不实用。本文提出一种无需相机校准的低光原始图像去噪范式。识别出黑电平误差导致的颜色偏差是性能下降的主要来源并会引起严重颜色偏移。为此引入偏差估计器网络预测黑电平误差作为噪声输入的全局特征。在ELD、SID和LRID数据集上评估该方法，在盲去噪器中表现出色，特别是在颜色校正方面。还揭示广泛使用的SIDD数据集在其真值图像中存在显著颜色偏差，引入新的真值提取框架解决此问题并提供校正数据集上现有方法的基准。
英文摘要
Raw images inherently suffer from noise due to the stochastic nature of light and sensor hardware imperfections. As real photon counts fall, the ratio of this noise to the signal degrades; consequently, for low-light conditions, robust denoising is especially vital for high-quality results. While recent data-driven methods achieve strong performance, they typically rely on large-scale noisy-clean image pairs that are costly and difficult to collect. Alternatively, parametric noise models can generate synthetic training data, but this necessitates precise camera calibration, which is often impractical for unknown devices. In this work, we propose a camera-agnostic, calibration-free paradigm for low-light raw denoising. We identify that color bias from black-level error is a primary source of performance degradation and causes severe color shifts. To mitigate this, we introduce a bias estimator network that predicts the black-level error as a global feature of the noisy input. We evaluate our approach across the ELD, SID, and LRID datasets, demonstrating superior performance among blind denoisers, particularly in terms of color correction. In many cases, we are competitive with-or can even surpass-methods with stronger supervision. Furthermore, we reveal that the widely used SIDD dataset contains significant color bias in its ground-truth images, which yields unrealistic color reproduction in trained models. We introduce a new ground-truth extraction framework to resolve this issue and provide a benchmark of existing methods on the corrected dataset.
CommentsAccepted at ICCP 2026
