Read our original research paper!
All images shown are completely computer generated
InfoGAN, without any supervision, can extract categorical information (discrete properties like identifying people, the authors of paintings, features) and continuous information (continual properties like rotation, color gradients, stylistic traits, incremental features) from images. This is a generative system, so all images shown are computer-generated images from the representation it learns, which has many useful applications. One could imagine a final evolution of this as like a video-game avatar generator. Create a photo-realistic version of any person with buttons and sliders for each of their traits; the same is possible for paintings, doodles, etc.
This poster should explain more clearly the purpose and context of our research:
Please feel free to reach out with questions or comments regarding our work! I love to hear from people interested in this stuff.
This research was conducted as part of Swarthmore Adaptive Robotics (CS 81) course.