Carousel: A High-Resolution Dataset for Multi-Target Automatic Image Cropping
This addresses the need for multi-target cropping in social media applications, but it is incremental as it builds on existing single-crop methods.
The paper tackles the problem of generating multiple distinct and aesthetically pleasing image crops, introducing a dataset of 277 images with human labels and evaluating single-crop models with a partitioning algorithm.
Automatic image cropping is a method for maximizing the human-perceived quality of cropped regions in photographs. Although several works have proposed techniques for producing singular crops, little work has addressed the problem of producing multiple, distinct crops with aesthetic appeal. In this paper, we motivate the problem with a discussion on modern social media applications, introduce a dataset of 277 relevant images and human labels, and evaluate the efficacy of several single-crop models with an image partitioning algorithm as a pre-processing step. The dataset is available at https://github.com/RafeLoya/carousel.