Paper Detail
Jiayu Li, Yixiao Fang, Tianyu Hu, Wei Cheng, Ping Huang, Zheheng Fan, Gang Yu, Xingjun Ma
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.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@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},
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 sce},
url = {https://huggingface.co/papers/2606.25763},
keywords = {multimodal large language models, aesthetic cropping, visual annotations, supervised fine-tuning, reinforcement fine-tuning, photographer-side composition, subject-side pose recommendation, code available, huggingface daily},
eprint = {2606.25763},
archiveprefix = {arXiv},
}
{}