Image Cropping with Composition and Saliency Aware Aesthetic Score Map

TL;DR

This paper introduces an interpretable deep learning model for aesthetic image cropping that uses a composition-aware and saliency-aware score map to identify optimal crop regions, revealing the underlying aesthetic evaluation mechanism.

Contribution

The proposed model uniquely combines composition and saliency awareness in an aesthetic score map, providing interpretability and improved cropping performance.

Findings

Competitive results on benchmark datasets

Effective localization of aesthetically important regions

Demonstrated generality in real-world applications

Abstract

Aesthetic image cropping is a practical but challenging task which aims at finding the best crops with the highest aesthetic quality in an image. Recently, many deep learning methods have been proposed to address this problem, but they did not reveal the intrinsic mechanism of aesthetic evaluation. In this paper, we propose an interpretable image cropping model to unveil the mystery. For each image, we use a fully convolutional network to produce an aesthetic score map, which is shared among all candidate crops during crop-level aesthetic evaluation. Then, we require the aesthetic score map to be both composition-aware and saliency-aware. In particular, the same region is assigned with different aesthetic scores based on its relative positions in different crops. Moreover, a visually salient region is supposed to have more sensitive aesthetic scores so that our network can learn to place salient objects at more proper positions. Such an aesthetic score map can be used to localize aesthetically important regions in an image, which sheds light on the composition rules learned by our model. We show the competitive performance of our model in the image cropping task on several benchmark datasets, and also demonstrate its generality in real-world applications.