Image restoration method and device and electronic equipment

Abstract

The invention provides an image restoration method and device, and electronic equipment. The method comprises the steps of obtaining a target image and a target mask corresponding to a to-be-restored image, wherein the target image is a to-be-restored image containing a preset color region, the preset color region is a region corresponding to a missing region in the to-be-restored image, the color of the preset color region is different from that of an edge region of the missing region in the to-be-restored image, and the target mask is a mask consistent with the missing region in the to-be-restored image in size; and inputting the target image and the target mask into a pre-trained deep convolutional generative adversarial network DCGAN to enable the DCGAN to output a target restored image corresponding to the to-be-restored image according to the target image and the target mask, thereby restoring the to-be-restored image through the target image and the target mask consistent with the missing area in size. It can be ensured that the restored missing area and the edge area in the target restored image are naturally connected, and the visual effect of image restoration is improved.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an image restoration method, device and electronic equipment. Background technique [0002] Currently, image inpainting is an important problem in the field of computer vision and has important applications in many fields. Image restoration is mainly to restore the missing part of the image. The existing image restoration methods mainly include image restoration methods based on structural information, image restoration algorithms based on texture information, and image restoration algorithms using deep learning technology; among them, based on structure The image restoration method of information mainly realizes image restoration through the principle of information diffusion. Although this technology can quickly and effectively repair missing images, it does not take into account the integrity of image restoration and the details of the image, resulting in The visual ...

AI Technical Summary

Problems solved by technology

Image restoration is mainly to restore the missing part of the image. The existing image restoration methods mainly include image restoration methods based on structural information, image restoration algorithms based on texture information, and image restoration algorithms using deep learning technology; among them, based on structure The image restoration method of information mainly realizes image restoration through the principle of information diffusion. Although this technology can quickly and effectively repair missing images, it does not take into account the integrity of image restoration and the details of the image, resulting in The visual effect of the image is very poor; the image restoration algorithm based on texture information may have problems such as incomplete semantics and blurred images when repairing large areas of missing areas, resulting in uncontrolled repair effects and unclear repair images. ; while the image restoration algorithm using deep learning technology has the defects of unstable data training and collapse of the training process, which affects the visual effect of the repaired image

Therefore, although the existing image restoration methods can realize the restoration of the missing area in the image, the visual effect of the repaired image is not ideal, and cannot meet people's high requirements for the visual effect of image restoration.

Images