Research Progress of Image Inpainting Methods Based on Deep Learning

Image inpainting is the process of recovering and repairing damaged or missing parts of an image through algorithms or techniques, which is a significant research focus in the field of computer vision. This paper reviews the development trajectory of deep learning-based image inpainting methods in recent years, and categorizes them into single-modal and multi-modal methods. The single-modal image inpainting methods are divided into convolutional autoencoder-based methods, GAN-based methods, Transformer-based methods and diffusion model-based methods. Meanwhile, the multimodal image inpainting methods include text-guided methods, audio-guided methods, video-guided methods and multimodal fusion-based methods. Furthermore, this paper provides a comparative analysis of the principles, advantages and disadvantages of various methods. It also introduces commonly used datasets and evaluation metrics, assesses the performance of representative methods on standard datasets, and discusses current challenges and future directions in this domain. © 2024 Journal of Computer Engineering and Applications Beijing Co., Ltd.; Science Press. All rights reserved.