A Novel Image Inpainting Model Based on Multi-scale Parallel Dense Connection Network

Abstract

Existing image inpainting methods often fail to effectively exploit multi-scale feature information and lack sufficient interaction between shallow and deep representations, leading to unsatisfactory restoration performance in damaged regions. In addition, structural discontinuities and blurred details frequently occur near the boundaries of missing areas. To address these challenges, this paper proposes a novel image inpainting framework based on a Multi-Scale Parallel Dense Connection Network (MSPDCN). Specifically, holistically nested edge detection (HED) is first employed to extract structural priors and estimate edge information of missing regions, which provides guidance for subsequent reconstruction and alleviates boundary blurring. Subsequently, a multi-scale parallel dense connection module is integrated into the generation network to capture features with different receptive fields and to strengthen the interaction between hierarchical representations, thereby improving feature utilization. Extensive experiments are conducted to evaluate the proposed model against state-of-the-art methods, including GAN-based and diffusion-based approaches. Compared with the contextual attention (CA) model, the proposed method achieves improvements of 13.09% and 5.12% in PSNR and SSIM, respectively, while reducing LPIPS by 21.72%. The results demonstrate that the proposed MSPDCN not only enhances visual quality but also improves robustness to interference. Overall, the proposed approach consistently outperforms existing methods in image inpainting tasks.