An Experience-based Direct Generation approach to Automatic Image Cropping

TL;DR

This paper introduces a CNN-based method for automatic image cropping that directly predicts crop bounding boxes without explicitly modeling aesthetics or saliency, achieving competitive results and faster inference.

Contribution

A novel one-stage CNN approach for image cropping that bypasses explicit aesthetic or saliency modeling, trained on a large editor-cropped dataset, and capable of handling multiple aspect ratios.

Findings

Performs better or comparably to existing methods on public datasets.

Faster inference and easier training compared to multi-stage approaches.

Generalizes well to unseen datasets and preserves image composition.

Abstract

Automatic Image Cropping is a challenging task with many practical downstream applications. The task is often divided into sub-problems - generating cropping candidates, finding the visually important regions, and determining aesthetics to select the most appealing candidate. Prior approaches model one or more of these sub-problems separately, and often combine them sequentially. We propose a novel convolutional neural network (CNN) based method to crop images directly, without explicitly modeling image aesthetics, evaluating multiple crop candidates, or detecting visually salient regions. Our model is trained on a large dataset of images cropped by experienced editors and can simultaneously predict bounding boxes for multiple fixed aspect ratios. We consider the aspect ratio of the cropped image to be a critical factor that influences aesthetics. Prior approaches for automatic image cropping, did not enforce the aspect ratio of the outputs, likely due to a lack of datasets for this task. We, therefore, benchmark our method on public datasets for two related tasks - first, aesthetic image cropping without regard to aspect ratio, and second, thumbnail generation that requires fixed aspect ratio outputs, but where aesthetics are not crucial. We show that our strategy is competitive with or performs better than existing methods in both these tasks. Furthermore, our one-stage model is easier to train and significantly faster than existing two-stage or end-to-end methods for inference. We present a qualitative evaluation study, and find that our model is able to generalize to diverse images from unseen datasets and often retains compositional properties of the original images after cropping. Our results demonstrate that explicitly modeling image aesthetics or visual attention regions is not necessarily required to build a competitive image cropping algorithm.