Discrete Annotation, Continuous Preference: Rethinking Supervision for Accurate and Generalizable Aesthetic Image Cropping
cs.CV
Submitted: 2026-09-30
Updated: 2026-09-30
Comments: Code, model, and data are available at https://github.com/zzqingz/CPIC
Code: https://github.com/zzqingz/CPIC
License: http://creativecommons.org/licenses/by/4.0/
The gist: Aesthetic image cropping aims to identify the optimal crop of an image in terms of aesthetics and composition.
Terminology
Abstract
Aesthetic image cropping aims to identify the optimal crop of an image in terms of aesthetics and composition. While supervision based on annotated data is fundamental, the field has been hindered by a long-standing problem: existing datasets suffer from (1) human subjectivity and (2) rigid discreteness confined to fixed sampling grids. These flawed annotations not only limit the accuracy and generalization of trained models but also severely distort fair evaluation. To overcome this, we propose to model human cropping preference as a multi-peaked, continuous, and sharp field over the crop space. We introduce the Continuous Preference Field (CPF), which recovers a dense preference landscape from discrete annotations through (1) peak clustering, (2) off-lattice refinement, (3) negative shaping, and (4) field assembly. Based on this, we train CPIC, a VLM-based cropping model optimized via GRPO with the CPF reward, which overcomes template collapse, achieving state-of-the-art performance and exceptional out-of-domain generalization. Finally, to resolve the long-standing benchmark evaluation crisis, we introduce CPICD, a comprehensive recalibration of existing ground-truth boxes. By leveraging the CPF to correct grid-bound artifacts across mainstream benchmarks, CPICD establishes a rigorous and reliable foundation for future cropping research. Extensive experiments and user studies demonstrate the superiority of our CPF, CPIC, and CPICD. Code, model, and data are available at https://github.com/zzqingz/CPIC.
Sources
- Qwen3-VL Technical Report
- Qwen2.5-VL Technical Report
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Dog-IQA: Standard-guided Zero-shot MLLM for Mix-grained Image Quality Assessment
- Accelerating Rectified Flow Models via Trajectory-Aware Caching
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- DRScaffold: Boosting Dense-Scene Reasoning in Lightweight Vision Language Models
- InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
- COMEX: A Composition-Grounded Benchmark and Learning Framework for Explainable Aesthetic Image Cropping
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models