Diffusion Image Prior
This addresses the challenge of handling complex, undefined degradations in real-world image restoration for applications in computer vision and image processing, though it is incremental as it builds on existing prior-based methods.
The authors tackled the problem of zero-shot image restoration without needing an explicit degradation model by introducing the Diffusion Image Prior (DIIP), which leverages pretrained diffusion models as a stronger prior than Deep Image Prior, achieving state-of-the-art results on tasks like JPEG artifact removal, waterdrop removal, denoising, and super-resolution.
Zero-shot image restoration (IR) methods based on pretrained diffusion models have recently achieved significant success. These methods typically require at least a parametric form of the degradation model. However, in real-world scenarios, the degradation may be too complex to define explicitly. To handle this general case, we introduce the Diffusion Image Prior (DIIP). We take inspiration from the Deep Image Prior (DIP)[16], since it can be used to remove artifacts without the need for an explicit degradation model. However, in contrast to DIP, we find that pretrained diffusion models offer a much stronger prior, despite being trained without knowledge from corrupted data. We show that, the optimization process in DIIP first reconstructs a clean version of the image before eventually overfitting to the degraded input, but it does so for a broader range of degradations than DIP. In light of this result, we propose a blind image restoration (IR) method based on early stopping, which does not require prior knowledge of the degradation model. We validate DIIP on various degradation-blind IR tasks, including JPEG artifact removal, waterdrop removal, denoising and super-resolution with state-of-the-art results.