click on the image to open the gallery or scroll down for more info
click on the image to open the gallery or scroll down for more info
What does AI look like? One might say it looks like a robot, or flashing LEDs, or a waveform on a screen. But what would AI say AI looks like? Why would drawing a self-portrait be such a challenge for AI? We already know that AI can perform exceptionally well at tasks such as language and image analysis. Creating new content, on the other hand, is a much more experimental activity. We introduce a multi-modal discriminative and generative framework capable of assisting humans in producing visual content related to a given theme, starting from a collection of documents (textual, visual, or both). This framework can be used by editors to generate images for articles, as well as books or music album covers. Motivated by a request from the The New York Times (NYT) seeking help to use AI to create art for their special section on Artificial Intelligence, we demonstrated the application of our system in producing such image: an AI Self Portrait. The result is shown above and was published in the New York Times special session on Artificial Intelligence on October 19th, 2018. Starting from a corpus of documents and a keyword term (AI), the goal of our system is to generate an image reflecting those inputs. We accomplish it with the pipeline described in the diagram below, which involves three major steps: identify a core visual concept (related to AI), create an original image that captures the given concept, and present the image in a way that fits the magazine visual style.
