VIPaint: Image Inpainting with Pre-Trained Diffusion Models via Variational Inference

ArXi:2411.18929v2 Announce Type: replace-cross Diffusion probabilistic models, generating novel data (e.g., images) from Gaussian noise through sequential denoising. However, conditioning the generative process on corrupted or masked images is challenging. While various methods have been proposed for inpainting masked images with diffusion priors, they often fail to produce samples from the true conditional distribution, especially for large masked regions. Many baselines also cannot be applied to latent diffusion models which generate high-quality images with much lower computational cost.