| title | ShutterMuse: Capture-Time Photography Guidance with MLLMs |
|---|---|
| authors | Jiayu Li, Yixiao Fang, Tianyu Hu, Wei Cheng, Ping Huang, Zheheng Fan, Gang Yu, Xingjun Ma |
| date | 2026-06-24 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2606.25763 |
| affiliation | StepFun |
| upvotes | 44 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Real-world photography requires capture-time guidance for both camera framing and subject pose. Yet existing aesthetic cropping benchmarks mainly evaluate post-hoc crop prediction and overlook subject-side recommendations, leaving the capture-time guidance capabilities of multimodal large language models (MLLMs) underexplored. To address this gap, we introduce CaptureGuide-Bench, a benchmark with two complementary tasks: photographer-side composition decision and refinement, and subject-side scene-conditioned pose recommendation. Our evaluation reveals limitations: general-purpose MLLMs can make composition decisions but lack precise refinement localization, while specialized aesthetic cropping models localize crops effectively but are limited to refinement; neither provides actionable pose guidance. To support model development, we further construct CaptureGuide-Dataset, comprising 130K samples with textual rationales and structured visual annotations, and develop ShutterMuse, a unified MLLM trained with supervised and reinforcement fine-tuning. Experiments on CaptureGuide-Bench show that ShutterMuse achieves the best overall photographer-side performance among evaluated baselines and competitive subject-side pose recommendation with substantially lower inference cost, demonstrating the potential of MLLMs as interactive assistants for photography during image capture. |
cite
@misc{li2026shuttermuse,
title={ShutterMuse: Capture-Time Photography Guidance with MLLMs},
author={Jiayu Li and Yixiao Fang and Tianyu Hu and Wei Cheng and Ping Huang and Zheheng Fan and Gang Yu and Xingjun Ma},
year={2026},
eprint={2606.25763},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2606.25763}
}