Image processing method and device, electronic equipment, storage medium and computer product

Abstract

The embodiment of the invention discloses an image processing method and device, electronic equipment, a storage medium and a computer product, and relates to the technical field of multimedia, games, artificial intelligence and cloud. The method comprises the following steps: acquiring a first data set comprising a plurality of first samples, wherein each first sample comprises a target image and a mask image of the target image; and for each first sample, predicting by calling the trained neural network model to obtain a foreground mask of the target image in the first sample, and constructing a training data set based on the target image in each first sample and the foreground mask of the target image. Based on the method provided by the embodiment of the invention, a richer training data set with a better training effect can be provided for the training of the neural network model.

Description

technical field [0001] The present application relates to the fields of multimedia, artificial intelligence, cloud technology and multimedia technology. Specifically, the present application relates to an image processing method, device, electronic equipment, storage medium and computer product. Background technique [0002] With the development of the cultural industry, the demand for high-quality characters in various industries such as movies and games is increasing. In order to reconstruct a high-quality character, multi-view stereo vision reconstruction (MVS, Multi-view Stereo) technology is widely used in the industry, but the reconstruction accuracy of this technology is not ideal, especially for parts with complex physiological structures. Errors can be catastrophic, requiring modelers to manually and time-consumingly fix them. [0003] In response to the above problems, people have also explored a series of methods to remove some parts of the person image to weaken...

AI Technical Summary

Problems solved by technology

In order to reconstruct a high-quality character, multi-view stereo vision reconstruction (MVS, Multi-view Stereo) technology is widely used in the industry, but the reconstruction accuracy of this technology is not ideal, especially for parts with complex physiological structures. Errors can be catastrophic and require manual, time-consuming repairs by modelers

[0003] In response to the above problems, people have also explored a series of methods to remove some parts of the person image to weaken the influence of these parts corresponding to geometric reconstruction. The data-driven deep learning method is one of them. This method can be obtained from real data. However, due to the incompleteness of the existing data sets, although the method based on deep learning can bring about some improvement in the reconstruction effect, the processing effect of some parts is still not ideal and needs to be improved.

Images