CG-GAN: An Interactive Evolutionary GAN-based Approach for Facial Composite Generation)
This addresses the challenge for law enforcement and eyewitnesses in efficiently producing accurate facial composites, though it is incremental as it builds on existing GAN methods.
The paper tackles the problem of creating facial composites from eyewitness memory by introducing CG-GAN, which uses a generative adversarial network and evolutionary computation to enable casual users to generate high-resolution, photo-realistic faces interactively, resulting in a system that allows holistic changes and combination of multiple representations without expert knowledge.
Facial composites are graphical representations of an eyewitness's memory of a face. Many digital systems are available for the creation of such composites but are either unable to reproduce features unless previously designed or do not allow holistic changes to the image. In this paper, we improve the efficiency of composite creation by removing the reliance on expert knowledge and letting the system learn to represent faces from examples. The novel approach, Composite Generating GAN (CG-GAN), applies generative and evolutionary computation to allow casual users to easily create facial composites. Specifically, CG-GAN utilizes the generator network of a pg-GAN to create high-resolution human faces. Users are provided with several functions to interactively breed and edit faces. CG-GAN offers a novel way of generating and handling static and animated photo-realistic facial composites, with the possibility of combining multiple representations of the same perpetrator, generated by different eyewitnesses.