Solving General Noisy Inverse Problem via Posterior Sampling: A Policy Gradient Viewpoint

arXiv:2403.10585v1 Announce Type: cross
Abstract: 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 …

abstract arxiv cs.ai cs.cv cs.lg diffusion eess.iv fidelity general generative gradient guidance image inpainting low policy posterior sampling solve type via