This paper introduces PromptIR, a prompt-based learning approach for all-in-one image restoration. The goal of PromptIR is to effectively restore images from various types and levels of degradation. The method uses prompts to encode degradation-specific information, which is then used to dynamically guide the restoration network. This allows the method to generalize to different degradation types and levels, while still achieving state-of-the-art results on image denoising, deraining, and dehazing. The authors argue that their approach offers a generic and efficient plugin module with few lightweight prompts that can be used to restore images of various types and levels of degradation with no prior information on the corruptions present in the image.
Publication date: June 22, 2023
Project Page: https://github.com/va1shn9v/PromptIR
Paper: https://arxiv.org/pdf/2306.13090.pdf
