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

arXiv: https://arxiv.org/abs/2605.12545 · HTML: https://mlsanity.com/paper/2605.12545/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 48 references that are in the map.
- First posted on arXiv 9 May 2026.

## Builds on (most cited first, 28 of 28)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Improving language models by retrieving from trillions of tokens](https://mlsanity.com/paper/2112.04426/) (2021)
- [Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations](https://mlsanity.com/paper/2312.08935/) (2023)
- [Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding](https://mlsanity.com/paper/2311.16922/) (2023)
- [WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct](https://mlsanity.com/paper/2308.09583/) (2023)
- [SLiC-HF: Sequence Likelihood Calibration with Human Feedback](https://mlsanity.com/paper/2305.10425/) (2023)
- [Dueling RL: Reinforcement Learning with Trajectory Preferences](https://mlsanity.com/paper/2111.04850/) (2021)
- [Reliable and Efficient Image Cropping: A Grid Anchor based Approach](https://mlsanity.com/paper/1904.04441/) (2019)
- [Quantitative Analysis of Automatic Image Cropping Algorithms: A Dataset and Comparative Study](https://mlsanity.com/paper/1701.01480/) (2017)
- [Grid Anchor based Image Cropping: A New Benchmark and An Efficient Model](https://mlsanity.com/paper/1909.08989/) (2019)
- [Learning to Compose with Professional Photographs on the Web](https://mlsanity.com/paper/1702.00503/) (2017)
- [Image Composition Assessment with Saliency-augmented Multi-pattern Pooling](https://mlsanity.com/paper/2104.03133/) (2021)
- [Code-Optimise: Self-Generated Preference Data for Correctness and Efficiency](https://mlsanity.com/paper/2406.12502/) (2024)
- [Multimodal LLMs Can Reason about Aesthetics in Zero-Shot](https://mlsanity.com/paper/2501.09012/) (2025)
- [Spatial-Semantic Collaborative Cropping for User Generated Content](https://mlsanity.com/paper/2401.08086/) (2024)
- [Learning Subject-Aware Cropping by Outpainting Professional Photos](https://mlsanity.com/paper/2312.12080/) (2023)
- [Cropper: Vision-Language Model for Image Cropping through In-Context Learning](https://mlsanity.com/paper/2408.07790/) (2024)
- [Beyond Image Borders: Learning Feature Extrapolation for Unbounded Image Composition](https://mlsanity.com/paper/2309.12042/) (2023)
- [Aligning CodeLLMs with Direct Preference Optimization](https://mlsanity.com/paper/2410.18585/) (2024)
- [PhotoFramer: Multi-modal Image Composition Instruction](https://mlsanity.com/paper/2512.00993/) (2025)
- [ProCrop: Learning Aesthetic Image Cropping from Professional Compositions](https://mlsanity.com/paper/2505.22490/) (2025)
- [Find Beauty in the Rare: Contrastive Composition Feature Clustering for Nontrivial Cropping Box Regression](https://mlsanity.com/paper/2302.08662/) (2023)

## Built on by (most cited first, 1 of 1)

- [FrameLite: Decision-Oriented Aesthetic Cropping with a Compact Vision-Language Model](https://mlsanity.com/paper/2610.17639/) (2026)

## Abstract (arXiv)

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.