Joint Multi-Scale Tone Mapping and Denoising for HDR Image Enhancement
This addresses a specific issue in HDR imaging for image processing applications, offering an incremental improvement by integrating denoising and tone-mapping.
The paper tackles the problem of noise amplification in high dynamic range (HDR) image enhancement, where tone-mapping operators increase noise, especially in low-light conditions, by proposing a joint multi-scale denoising and tone-mapping framework that optimizes both operations together, resulting in outperforming existing methods on most benchmarking datasets.
An image processing unit (IPU), or image signal processor (ISP) for high dynamic range (HDR) imaging usually consists of demosaicing, white balancing, lens shading correction, color correction, denoising, and tone-mapping. Besides noise from the imaging sensors, almost every step in the ISP introduces or amplifies noise in different ways, and denoising operators are designed to reduce the noise from these sources. Designed for dynamic range compressing, tone-mapping operators in an ISP can significantly amplify the noise level, especially for images captured in low-light conditions, making denoising very difficult. Therefore, we propose a joint multi-scale denoising and tone-mapping framework that is designed with both operations in mind for HDR images. Our joint network is trained in an end-to-end format that optimizes both operators together, to prevent the tone-mapping operator from overwhelming the denoising operator. Our model outperforms existing HDR denoising and tone-mapping operators both quantitatively and qualitatively on most of our benchmarking datasets.