用校准方法生成更真实的噪点图像，提升去噪模型训练效果。
SNIC: Synthesized Noisy Images using Calibration
- 通过暗帧捕捉信号无关噪声，校准多传感器噪点模型。
- 合成的噪点图像使PSNR与真实图像差距缩小54%-64%。
- 开源数据集含30场景、4种设备，适合去噪模型研究者使用。
训练先进的去噪模型需要大量高保真、物理准确的图像数据。尽管异方差噪声模型可模拟真实噪声，但其校准方法仍缺乏深入探索，大规模校准数据集稀缺。本文提出一套严谨的校准与调优流程，适用于多种传感器，引入暗帧以捕获信号无关噪声。在使用最先进的去噪器评估时，我们生成的合成噪点RAW图像相比厂商提供的噪声参数生成的图像，将峰值信噪比（PSNR）与真实噪声的差距降低了54%-64%，后者未考虑智能手机图像信号处理（ISP）在标定过程中抑制原始文件噪声的问题。基于此流程，我们构建了合成噪点图像校准数据集（SNIC）：包含超过6600张图像，覆盖30个场景和四种传感器（单反、便携相机、智能手机），提供开源校准代码与噪声模型。据我们所知，SNIC是目前唯一公开可用、具备校准合成噪声并提供配对RAW与TIFF数据的数据集，为去噪模型研发提供了新资源。
原文摘要 · Abstract (English)
Training advanced denoising models requires large datasets of high-fidelity, physically accurate images. While heteroscedastic noise models can simulate realistic noise, methodologies for their calibration remain under-explored, and large-scale calibrated datasets are scarce. We present a rigorous calibration and tuning pipeline for building high-quality heteroscedastic noise models across a range of sensors, incorporating dark frames to capture signal-independent noise. When evaluated with a state-of-the-art denoiser, our synthesized noisy RAW images reduce the Peak Signal to Noise Ratio (PSNR) gap to real-world noise by 54-64% compared to synthesized RAW images created using manufacturer-provided noise profiles, which fail to account for smart-phone ISP processing that suppresses noise in RAW files during calibration. Leveraging our pipeline, we introduce the Synthesized Noisy Images using Calibration (SNIC) dataset: over 6600 images across 30 scenes and four sensors (DSLR, point-and-shoot, and smartphone), with open-source calibration code and noise models. To our knowledge, SNIC is the only publicly available dataset with calibrated synthesized noise providing paired RAW and TIFF data, offering a new resource for researchers developing noise reduction models.
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。