Enregistré dans:
Détails bibliographiques
Auteurs principaux: Loya, Rafe, Hamara, Andrew, Estell, Benjamin, Kilpatrick, Benjamin, Freeman, Andrew C.
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2511.04680
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909890743631872
author Loya, Rafe
Hamara, Andrew
Estell, Benjamin
Kilpatrick, Benjamin
Freeman, Andrew C.
author_facet Loya, Rafe
Hamara, Andrew
Estell, Benjamin
Kilpatrick, Benjamin
Freeman, Andrew C.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_04680
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Carousel: A High-Resolution Dataset for Multi-Target Automatic Image Cropping
Loya, Rafe
Hamara, Andrew
Estell, Benjamin
Kilpatrick, Benjamin
Freeman, Andrew C.
Computer Vision and Pattern Recognition
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.
title Carousel: A High-Resolution Dataset for Multi-Target Automatic Image Cropping
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.04680