Damaged Image Repair using Masks with Computer Vision Inpaint Method

Abstract

Image inpainting is the technique used to automatically fix damaged areas using data from sections that have been saved. With the development of deep learning in recent years, image drawing performance has substantially increased. This research study reviews the main methods used for automating image inpainting. This research study provides a brief overview of traditional techniques while concentrating on deep learning-based inpainting techniques, covering model categorization, strengths and drawbacks, scope of application, and performance comparison. Finally, the challenges and trends surrounding automated image inpainting are examined and foreseen. A tool called image inpainting uses the data from the remaining components to repair damaged areas. With the advancement of society, image inpainting has become a vital research area in the field of computer vision. It is extensively used in culture, daily life, and security, including object removal and the preservation of digital cultural assets. Conventional methods build geometric models based on geometric consistency and image content similarity, or they use texture generation to patch up small sections of damaged images. It partially solves the problem of loose coupling between high-level semantics and low-level image properties, enabling deep learning to gradually overtake traditional methods in computer vision.