用真实原始图像数据训练联合去噪、去马赛克与压缩模型，提升效率与泛化能力。
Learning Joint Denoising, Demosaicing, and Compression from the Raw Natural Image Noise Dataset
- 在原始Bayer数据上直接去噪，兼顾计算效率与灵活性。
- 联合处理去噪与压缩，率失真性能显著优于传统方法。
- 适用于跨传感器、跨风格的图像处理，适合工业级应用。
本文提出原始自然图像噪声数据集（RawNIND），包含多样化的成对原始图像，用于支持跨传感器、图像处理流程和风格的去噪模型训练。提出两种去噪方法：一种直接在原始拜耳数据上操作，具备计算高效性；另一种处理线性RGB图像，提升对不同传感器的泛化能力，同时保留后续处理的灵活性。两种方法均优于依赖已开发图像的传统方法。此外，在原始数据层面整合去噪与压缩，显著提升率失真性能与计算效率。研究结果表明，应向以原始数据为核心的处理范式转变，实现更高效、灵活的图像处理。
原文摘要 · Abstract (English)
This paper introduces the Raw Natural Image Noise Dataset (RawNIND), a diverse collection of paired raw images designed to support the development of denoising models that generalize across sensors, image development workflows, and styles. Two denoising methods are proposed: one operates directly on raw Bayer data, leveraging computational efficiency, while the other processes linear RGB images for improved generalization to different sensors, with both preserving flexibility for subsequent development. Both methods outperform traditional approaches which rely on developed images. Additionally, the integration of denoising and compression at the raw data level significantly enhances rate-distortion performance and computational efficiency. These findings suggest a paradigm shift toward raw data workflows for efficient and flexible image processing.
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。