Papers
arxiv:2605.12545

CROP: Expert-Aligned Image Cropping via Compositional Reasoning and Optimizing Preference

Published on May 9
Authors:
,
,
,

Abstract

The study proposes a multimodal reasoning framework that guides vision-language models through compositional analysis and expert preference alignment to improve aesthetic image cropping.

Aesthetic image cropping aims to enhance the aesthetic quality of an image by improving its composition through spatial cropping. Previous methods often rely on saliency prediction or retrieval augmentation, ignoring the task's core requirement: a deep understanding of composition and aesthetics. Consequently, saliency-based methods struggle to make compositional trade-offs in complex scenes, while retrieval-based methods blindly refer to similar cases, lacking adaptive reasoning for unique scenes. Both approaches fail to align their automated cropping results with those of human experts. To address the above issues, we propose a novel paradigm that reformulates aesthetic cropping as a multimodal reasoning task, aiming to activate the VLM's analytical and comprehension capabilities in aesthetics. We design a Compositional Reasoning and Optimizing Preference method (CROP) that directs the VLM to think like a professional photographer. It deconstructs a complex and subjective aesthetic problem into an "analysis-proposal-decision" process, reasoning step by step through the analysis of scene elements and compositional principles. Meanwhile, our expert preference alignment module makes the model's decision consistent with human expert aesthetics. Extensive experiments across multiple datasets validate our method's superiority and component effectiveness.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2605.12545
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2605.12545 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2605.12545 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2605.12545 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.