GRIG: Few-Shot Generative Residual Image Inpainting
This addresses the challenge of training image inpainting models on small datasets, which is incremental as it builds on existing generative adversarial networks with novel components.
The paper tackles the problem of image inpainting with limited training data by proposing a few-shot generative residual method, achieving high-quality results that outperform previous methods in evaluations.
Image inpainting is the task of filling in missing or masked region of an image with semantically meaningful contents. Recent methods have shown significant improvement in dealing with large-scale missing regions. However, these methods usually require large training datasets to achieve satisfactory results and there has been limited research into training these models on a small number of samples. To address this, we present a novel few-shot generative residual image inpainting method that produces high-quality inpainting results. The core idea is to propose an iterative residual reasoning method that incorporates Convolutional Neural Networks (CNNs) for feature extraction and Transformers for global reasoning within generative adversarial networks, along with image-level and patch-level discriminators. We also propose a novel forgery-patch adversarial training strategy to create faithful textures and detailed appearances. Extensive evaluations show that our method outperforms previous methods on the few-shot image inpainting task, both quantitatively and qualitatively.