%0 Generic %1 fang2017creatism %A Fang, Hui %A Zhang, Meng %D 2017 %K 2017 art arxiv deep-learning photograph %T Creatism: A deep-learning photographer capable of creating professional work %U http://arxiv.org/abs/1707.03491 %X 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. Using our system, we mimic the workflow of a landscape photographer, from framing for the best composition to carrying out various post-processing operations. The environment for our virtual photographer is simulated by a collection of panorama images from Google Street View. We design a "Turing-test"-like experiment to objectively measure quality of its creations, where professional photographers rate a mixture of photographs from different sources blindly. Experiments show that a portion of our robot's creation can be confused with professional work.

@misc{fang2017creatism, abstract = {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. Using our system, we mimic the workflow of a landscape photographer, from framing for the best composition to carrying out various post-processing operations. The environment for our virtual photographer is simulated by a collection of panorama images from Google Street View. We design a "Turing-test"-like experiment to objectively measure quality of its creations, where professional photographers rate a mixture of photographs from different sources blindly. Experiments show that a portion of our robot's creation can be confused with professional work.}, added-at = {2017-07-15T20:39:22.000+0200}, author = {Fang, Hui and Zhang, Meng}, biburl = {https://www.bibsonomy.org/bibtex/231dc195f51d1f7c74cffb899057406dc/achakraborty}, description = {[1707.03491] Creatism: A deep-learning photographer capable of creating professional work}, interhash = {58aa3c91f84ad79059cdae7d8882f029}, intrahash = {31dc195f51d1f7c74cffb899057406dc}, keywords = {2017 art arxiv deep-learning photograph}, note = {cite arxiv:1707.03491}, timestamp = {2017-09-01T13:58:45.000+0200}, title = {Creatism: A deep-learning photographer capable of creating professional work}, url = {http://arxiv.org/abs/1707.03491}, year = 2017 }