# Image Cropping with Composition and Saliency Aware Aesthetic Score Map

arXiv: https://arxiv.org/abs/1911.10492 · HTML: https://mlsanity.com/paper/1911.10492/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Nov 2019.

## Built on by (most cited first, 21 of 21)

- [Temporal and Heterogeneous Graph Neural Network for Financial Time Series Prediction](https://mlsanity.com/paper/2305.08740/) (2023)
- [Image Composition Assessment with Saliency-augmented Multi-pattern Pooling](https://mlsanity.com/paper/2104.03133/) (2021)
- [Salient Objects in Clutter](https://mlsanity.com/paper/2105.03053/) (2021)
- [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)
- [Human-centric Image Cropping with Partition-aware and Content-preserving Features](https://mlsanity.com/paper/2207.10269/) (2022)
- [Cropper: Vision-Language Model for Image Cropping through In-Context Learning](https://mlsanity.com/paper/2408.07790/) (2024)
- [A Hypothesis for the Aesthetic Appreciation in Neural Networks](https://mlsanity.com/paper/2108.02646/) (2021)
- [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)
- [Towards Smart Point-and-Shoot Photography](https://mlsanity.com/paper/2505.03638/) (2025)
- [Venus: Benchmarking and Empowering Multimodal Large Language Models for Aesthetic Guidance and Cropping](https://mlsanity.com/paper/2602.23980/) (2026)
- [Camera View Adjustment Prediction for Improving Image Composition](https://mlsanity.com/paper/2104.07608/) (2021)
- [Horizontal-to-Vertical Video Conversion](https://mlsanity.com/paper/2101.04051/) (2021)
- [An Experience-based Direct Generation approach to Automatic Image Cropping](https://mlsanity.com/paper/2212.14561/) (2022)
- [Photography Perspective Composition: Towards Aesthetic Perspective Recommendation](https://mlsanity.com/paper/2505.20655/) (2025)
- [Efficient Multi-Crop Saliency Partitioning for Automatic Image Cropping](https://mlsanity.com/paper/2506.22814/) (2025)
- [Global Attention-Fused Image Cropping with Attention-Guided and Global-Aligned Crop Evaluator](https://mlsanity.com/paper/2608.04821/) (2026)
- [GeoComposer: Geometry-Grounded Photographic Composition Instruction](https://mlsanity.com/paper/2609.26620/) (2026)
- [FrameLite: Decision-Oriented Aesthetic Cropping with a Compact Vision-Language Model](https://mlsanity.com/paper/2610.17639/) (2026)

## Abstract (arXiv)

Aesthetic image cropping is a practical but challenging task which aims at finding the best crops with the highest aesthetic quality in an image. Recently, many deep learning methods have been proposed to address this problem, but they did not reveal the intrinsic mechanism of aesthetic evaluation. In this paper, we propose an interpretable image cropping model to unveil the mystery. For each image, we use a fully convolutional network to produce an aesthetic score map, which is shared among all candidate crops during crop-level aesthetic evaluation. Then, we require the aesthetic score map to be both composition-aware and saliency-aware. In particular, the same region is assigned with different aesthetic scores based on its relative positions in different crops. Moreover, a visually salient region is supposed to have more sensitive aesthetic scores so that our network can learn to place salient objects at more proper positions. Such an aesthetic score map can be used to localize aesthetically important regions in an image, which sheds light on the composition rules learned by our model. We show the competitive performance of our model in the image cropping task on several benchmark datasets, and also demonstrate its generality in real-world applications.