High Resolution Medical Image Inpainting Based on Super Resolution

Introduction: Image inpainting techniques and patents have made great progress in recent years. However, with higher image resolution, the large amount of computation and memory requirements cause great difficulties for training. Method: We propose a medical image inpainting model that utilizes super-resolution techniques to enhance the resolution of images during the repair process. Moreover, to maximize the utilization of semantic information and enhance network performance, we incorporate multi-scale dense residual blocks for feature extraction from the image. Results: Meanwhile, we utilize structural similarity as a loss function to encourage the network to synthesize more meaningful structural textures. Experimental results demonstrate that HRMII can effectively reduce the computation and memory occupation of the high-resolution image inpainting model, and obtain satisfactory inpainting results. Conclusion: Additionally, ablation studies have substantiated the efficacy of diverse modules within the network.