Image Inpainting via Iteratively Decoupled Probabilistic Modeling
This addresses image completion challenges for computer vision applications, offering a more efficient solution compared to existing methods.
The paper tackles the problem of high-quality image inpainting, especially for large missing regions, by proposing a novel pixel spread model that combines GAN efficiency with probabilistic modeling, achieving state-of-the-art performance on multiple benchmarks.
Generative adversarial networks (GANs) have made great success in image inpainting yet still have difficulties tackling large missing regions. In contrast, iterative probabilistic algorithms, such as autoregressive and denoising diffusion models, have to be deployed with massive computing resources for decent effect. To achieve high-quality results with low computational cost, we present a novel pixel spread model (PSM) that iteratively employs decoupled probabilistic modeling, combining the optimization efficiency of GANs with the prediction tractability of probabilistic models. As a result, our model selectively spreads informative pixels throughout the image in a few iterations, largely enhancing the completion quality and efficiency. On multiple benchmarks, we achieve new state-of-the-art performance. Code is released at https://github.com/fenglinglwb/PSM.