Personal View site logo
Machines: A deep-learning photographer capable of creating professional work
  • image

    Machine-learning excels in many areas with well-defined goals. However, a clear goal is usually not available in art forms, such as photography. The success of a photograph is measured by its aesthetic value, a very subjective concept. This adds to the challenge for a machine learning approach.

    We introduce Creatism, a deep-learning system for artistic content creation. In our system, we break down aesthetics into multiple aspects, each can be learned individually from a shared dataset of professional examples. Each aspect corresponds to an image operation that can be optimized efficiently. A novel editing tool, dramatic mask, is introduced as one operation that improves dramatic lighting for a photo. Our training does not require a dataset with before/after image pairs, or any additional labels to indicate different aspects in aesthetics.

  • 1 Reply sorted by
  • Given that many (authentic) interesting pictures already exist that simply almost nobody took notice of in the gargantuan pool of images available, I found the following work also interesting: