Deep Denoising of Flash and No-Flash Pairs for Photography in Low-Light Environments
This method offers significant improvements in low-light photography for consumers and professionals by producing high-quality, noise-free images with accurate ambient colors, overcoming limitations of existing flash-based or no-flash denoising techniques.
This paper presents a neural network method for denoising pairs of flash and no-flash images captured in low-light conditions. The method successfully combines the ambient color and mood from the noisy no-flash image with texture and detail from the flash image, producing high-quality, noise-free images with accurate ambient colors.
We introduce a neural network-based method to denoise pairs of images taken in quick succession, with and without a flash, in low-light environments. Our goal is to produce a high-quality rendering of the scene that preserves the color and mood from the ambient illumination of the noisy no-flash image, while recovering surface texture and detail revealed by the flash. Our network outputs a gain map and a field of kernels, the latter obtained by linearly mixing elements of a per-image low-rank kernel basis. We first apply the kernel field to the no-flash image, and then multiply the result with the gain map to create the final output. We show our network effectively learns to produce high-quality images by combining a smoothed out estimate of the scene's ambient appearance from the no-flash image, with high-frequency albedo details extracted from the flash input. Our experiments show significant improvements over alternative captures without a flash, and baseline denoisers that use flash no-flash pairs. In particular, our method produces images that are both noise-free and contain accurate ambient colors without the sharp shadows or strong specular highlights visible in the flash image.