Tell Me What You See: Text-Guided Real-World Image Denoising (2312.10191v2)

Abstract: Image reconstruction from noisy sensor measurements is a challenging problem. Many solutions have been proposed for it, where the main approach is learning good natural images prior along with modeling the true statistics of the noise in the scene. In the presence of very low lighting conditions, such approaches are usually not enough, and additional information is required, e.g., in the form of using multiple captures. We suggest as an alternative to add a description of the scene as prior, which can be easily done by the photographer capturing the scene. Inspired by the remarkable success of diffusion models for image generation, using a text-guided diffusion model we show that adding image caption information significantly improves image denoising and reconstruction on both synthetic and real-world images.