A new deep learning algorithm developed by DataGrid Co Ltd in Japan can generate high-resolution, realistic images of people. This development of the "whole body model automatic generation AI" which generates whole body images of non-existent people with high resolution could be used in the advertising and clothing industries.
Datagrid developed idle automatic generation AI in June 2018. However, idle auto generation AI generates an image only for the face area, so it did not have enough expressive power. Therefore, in order to enhance the expressive power of the generated person, DataGrid have been working on two research and development projects for "whole body generation" and "motion generation". The high-precision whole-body generation model has no precedent, and DataGrid have succeeded in stably generating high-resolution (1024 × 1024) whole-body model images.
GAN (Generative Adversarial Network)
It is possible to generate non-existent whole body model images with high resolution and high quality by making AI that applies deep learning to learn a large number of whole body model images. Automatic generation of full-body model AI is expected to be used as a virtual model for advertising and apparel.
DataGrid will further improve the accuracy of the whole-body model automatic generation AI, and research and develop the motion generation AI. In addition, they will conduct demonstration experiments with advertising and apparel companies to develop functions required for actual operation.
Source and top image: DataGrid Co Ltd