Solving General Noisy Inverse Problem via Posterior Sampling: A Policy Gradient Viewpoint
This work addresses image restoration challenges for applications in computer vision, offering a robust solution to various inverse problems, though it is incremental as it builds on existing diffusion models.
The paper tackles the problem of solving general noisy image inverse tasks like super-resolution and inpainting by proposing Diffusion Policy Gradient (DPG), a method that uses a pretrained diffusion model without task-specific fine-tuning, resulting in higher restoration quality on datasets such as FFHQ, ImageNet, and LSUN.
Solving image inverse problems (e.g., super-resolution and inpainting) requires generating a high fidelity image that matches the given input (the low-resolution image or the masked image). By using the input image as guidance, we can leverage a pretrained diffusion generative model to solve a wide range of image inverse tasks without task specific model fine-tuning. To precisely estimate the guidance score function of the input image, we propose Diffusion Policy Gradient (DPG), a tractable computation method by viewing the intermediate noisy images as policies and the target image as the states selected by the policy. Experiments show that our method is robust to both Gaussian and Poisson noise degradation on multiple linear and non-linear inverse tasks, resulting into a higher image restoration quality on FFHQ, ImageNet and LSUN datasets.