简化低光RAW图像去噪的噪声建模流程，准备时间从天缩短至小时。
Noise Modeling in One Hour: Minimizing Preparation Efforts for Self-supervised Low-Light RAW Image Denoising
- 基于噪声特性分析，省去繁琐的增益校准和独立噪声建模步骤。
- 仅需数小时准备，去噪性能比现有最佳方法提升最高0.54dB PSNR。
- 适合希望快速部署低光图像去噪系统的工程团队使用。
数据驱动的低光RAW图像去噪面临数据短缺问题，噪声合成是潜在解决方案。然而，现有高精度噪声合成方法通常需要耗时的校准与参数化流程，难以大规模落地。本文通过深入分析噪声特性并验证广泛技术的有效性，提出一种实用且简便的噪声合成流程。相比其他方法，该流程省去了复杂的系统增益校准与信号无关噪声建模环节，将噪声合成的准备时间从数天压缩至数小时。同时，该方法在去噪性能上表现优异，相比当前最优噪声合成技术，最高实现0.54dB的PSNR提升。代码已公开于https://github.com/SonyResearch/raw_image_denoising。
原文摘要 · Abstract (English)
Noise synthesis is a promising solution for addressing the data shortage problem in data-driven low-light RAW image denoising. However, accurate noise synthesis methods often necessitate labor-intensive calibration and profiling procedures during preparation, preventing them from landing to practice at scale. This work introduces a practically simple noise synthesis pipeline based on detailed analyses of noise properties and extensive justification of widespread techniques. Compared to other approaches, our proposed pipeline eliminates the cumbersome system gain calibration and signal-independent noise profiling steps, reducing the preparation time for noise synthesis from days to hours. Meanwhile, our method exhibits strong denoising performance, showing an up to 0.54dB PSNR improvement over the current state-of-the-art noise synthesis technique. Code is released at https://github.com/SonyResearch/raw_image_denoising
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。