Learning Joint Denoising, Demosaicing, and Compression from the Raw Natural Image Noise Dataset
This addresses the problem of efficient and flexible image processing for photography and computer vision applications, representing a paradigm shift rather than an incremental improvement.
The paper tackles the problem of image denoising by introducing the Raw Natural Image Noise Dataset (RawNIND) and two denoising methods that operate on raw Bayer or linear RGB data, outperforming traditional approaches and showing that integrating denoising with compression at the raw data level significantly enhances rate-distortion performance and computational efficiency.
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.