Training method and device of image processing model and image processing method and device

Abstract

The invention relates to an image processing model training method and device and an image processing method and device.The training method comprises the steps that a training image is obtained, the training image comprises at least one instance, and each instance is marked with real transparency; obtaining a mask of each instance of the at least one instance; for each instance, based on the mask of at least one instance, generating a target mask, a reference mask and a background mask of the current instance, and inputting the training image, the target mask, the reference mask and the background mask into an image processing model to obtain target transparency, reference transparency and background transparency of the current instance; calculating loss based on the target transparency, the reference transparency, the background transparency and the true transparency of each instance; the image processing model is trained by adjusting parameters of the image processing model based on the loss. According to the method and the device, instance segmentation and instance extraction can be combined to finish fine instance matting.

Description

technical field [0001] The present disclosure relates to the field of image processing, and in particular, to a training method and device for an image processing model and an image processing method and device. Background technique [0002] The rapid development of mobile Internet technology has made image processing more possible. The current Internet platforms provide a variety of image processing methods, such as beautifying and editing uploaded photos, or re-creating images. As a basic image processing and editing technology, map technology has achieved great improvement in performance under the wide application of deep neural networks. However, the existing map technology still has certain limitations in many scenarios. For example, each instance in the image cannot be edited individually. SUMMARY OF THE INVENTION [0003] The present disclosure provides a training method and apparatus for an image processing model, and an image processing method and apparatus, so a...

AI Technical Summary

Problems solved by technology

[0002] The rapid development of mobile Internet technology has made image processing more possibilities. The current Internet platform provides a variety of image processing methods, such as beautifying and editing uploaded photos, or recreating images. As a basic image processing and editing technology, image technology has greatly improved its performance under the wide application of deep neural networks. However, the existing image matting technology still has certain limitations in many scenarios. For example, individual editing of each instance in an image is not possible

Images