Learning to Compose with Professional Photographs on the Web
This addresses the problem of automated photo composition for photography and image editing applications, but it is incremental as it builds on existing ranking and cropping methods.
The paper tackles the challenge of modeling photo composition aesthetics by formulating it as a view-finding process and training a deep ranking network using web-sourced professional photographs, achieving state-of-the-art performance on two image cropping datasets.
Photo composition is an important factor affecting the aesthetics in photography. However, it is a highly challenging task to model the aesthetic properties of good compositions due to the lack of globally applicable rules to the wide variety of photographic styles. Inspired by the thinking process of photo taking, we formulate the photo composition problem as a view finding process which successively examines pairs of views and determines their aesthetic preferences. We further exploit the rich professional photographs on the web to mine unlimited high-quality ranking samples and demonstrate that an aesthetics-aware deep ranking network can be trained without explicitly modeling any photographic rules. The resulting model is simple and effective in terms of its architectural design and data sampling method. It is also generic since it naturally learns any photographic rules implicitly encoded in professional photographs. The experiments show that the proposed view finding network achieves state-of-the-art performance with sliding window search strategy on two image cropping datasets.