FrameLite: Decision-Oriented Aesthetic Cropping with a Compact Vision-Language Model

arXiv:2610.17639v1 Announce Type: new Abstract: Aesthetic image cropping improves composition by balancing subjects, context, and image boundaries. Large vision-language models bring semantic knowledge to this task, but their scale limits lightweight photography assistance. We propose FrameLite, a compact cropping model built on Qwen3.5-0.8B. Our approach is motivated by the observation that a small model can generate better crops than its first answer suggests. We develop three-stage training to turn this potential into stronger direct predictions. Spatial and composition training establishes localization and framing preferences. Quality-Guided Online Supervision (QOS) then learns the highest-quality complete answers among the current policy's generated candidates. Greedy-Referenced Optimization (GRO) further refines the policy using positive and negative quality differences relative to its current greedy answer. Both online stages use annotation-derived feedback, while inference returns one coordinate answer without search or an external scorer. Experiments show that FrameLite outperforms the compared large-VLM croppers across public benchmarks with a substantially smaller backbone. Controlled studies confirm that selecting high-quality training answers improves the final model beyond online sampling alone. We will release our code and model weights at https://github.com/JianzeLi-114/FrameLite .

Related

• Stage-wise Attention-Guided Region Sequencing for Adversarial Attacks on Large Vision-Language Models
• VisReflect: Latent Visual Reflection for Fine-Grained Perception in Long Visual Context
• Personalized Object Identification and Localization via In-Context Inference with Vision-Language Models

Source: arXiv cs.CV | 2026-10-14