DiffuseRAW: End-to-End Generative RAW Image Processing for Low-Light Images

arXiv:2402.18575v1 Announce Type: cross
Abstract: Imaging under extremely low-light conditions presents a significant challenge and is an ill-posed problem due to the low signal-to-noise ratio (SNR) caused by minimal photon capture. Previously, diffusion models have been used for multiple kinds of generative tasks and image-to-image tasks, however, these models work as a post-processing step. These diffusion models are trained on processed images and learn on processed images. However, such approaches are often not well-suited for extremely low-light tasks. Unlike the …

abstract arxiv challenge cs.ai cs.cv cs.lg diffusion diffusion models eess.iv generative image image processing images image-to-image imaging light low multiple noise photon processing raw signal tasks type work