GSGN-TSIIG: a gradient semantics generation network-based two-stage image inpainting generator for enhanced image restoration

Image inpainting is the recent hot research direction in the domain of artificial intelligence due to its significance in image restoration. Even though the traditional image inpainting approaches have shown promising outcomes, they are prone to ambiguous artifacts, particularly in high semantic and boundary areas. To resolve these challenges, we propose an efficient image inpainting model termed Gradient Semantics Generation Network-based Two-stage Image Inpainting Generator (GSGN-TSIIG) for comprehensive image restoration. Firstly, we design GSGN a comprehensive gradient learning framework by employing a convolutional autoencoder as a backbone for accurately determining gradient semantics in the hole region of the corrupted images. Secondly, we develop TSIIG an image inpainting network that leverages the significance of structural and textural generators for repairing the missing pixels and generating better image inpainting outcomes. Furthermore, our model leverages image data collected from diverse sources, including the Places-2_MIT dataset, CelebA dataset, Paris Streetview dataset, and ImageNet dataset for comprehensive performance assessment. Experimental results, including essential measures and quantitative analyses, demonstrate the efficacy of our approach by achieving a PSNR of 35.2 dB and a mean error of 0.01. Notably, comparative evaluations underscore the superior performance of our proposed model over existing approaches, establishing its potential for robust image restoration applications.