ProCrop: Learning Aesthetic Image Cropping from Professional Compositions
This work addresses the challenge of enhancing visual appeal in photography for applications like photo editing and social media, though it is incremental as it builds on retrieval-based and data-driven approaches.
The paper tackles the problem of aesthetic image cropping by introducing ProCrop, a retrieval-based method that learns from professional compositions, and it significantly outperforms existing methods, matching fully supervised approaches when trained on a new large-scale dataset of 242K images.
Image cropping is crucial for enhancing the visual appeal and narrative impact of photographs, yet existing rule-based and data-driven approaches often lack diversity or require annotated training data. We introduce ProCrop, a retrieval-based method that leverages professional photography to guide cropping decisions. By fusing features from professional photographs with those of the query image, ProCrop learns from professional compositions, significantly boosting performance. Additionally, we present a large-scale dataset of 242K weakly-annotated images, generated by out-painting professional images and iteratively refining diverse crop proposals. This composition-aware dataset generation offers diverse high-quality crop proposals guided by aesthetic principles and becomes the largest publicly available dataset for image cropping. Extensive experiments show that ProCrop significantly outperforms existing methods in both supervised and weakly-supervised settings. Notably, when trained on the new dataset, our ProCrop surpasses previous weakly-supervised methods and even matches fully supervised approaches. Both the code and dataset will be made publicly available to advance research in image aesthetics and composition analysis.