ProCrop: Learning Aesthetic Image Cropping from Professional Compositions

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Ke, Ding, Tianyu, Jiang, Jiachen, Chen, Tianyi, Zharkov, Ilya, Patel, Vishal M., Liang, Luming
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915310367408128
author Zhang, Ke
Ding, Tianyu
Jiang, Jiachen
Chen, Tianyi
Zharkov, Ilya
Patel, Vishal M.
Liang, Luming
author_facet Zhang, Ke
Ding, Tianyu
Jiang, Jiachen
Chen, Tianyi
Zharkov, Ilya
Patel, Vishal M.
Liang, Luming
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_22490
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ProCrop: Learning Aesthetic Image Cropping from Professional Compositions
Zhang, Ke
Ding, Tianyu
Jiang, Jiachen
Chen, Tianyi
Zharkov, Ilya
Patel, Vishal M.
Liang, Luming
Computer Vision and Pattern Recognition
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.
title ProCrop: Learning Aesthetic Image Cropping from Professional Compositions
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.22490