AI 拍照指导：不只裁图，还教你怎么摆
现在的 AI 修图工具只能事后裁切，但拍照时怎么构图、人往哪站才是关键。这篇论文发现，通用多模态大模型能判断构图好坏，但说不出具体该往左移几厘米；专门的裁切模型能精准定位，但不会给人摆姿势的建议。研究者建了一个新基准和 13 万样本的数据集，训练出统一模型 ShutterMuse，既能给摄影师调构图，又能给被拍者建议姿势，且推理成本更低。它不是你明天就能用的功能，但指向了 AI 从「事后修图」转向「实时指导」的方向。
📄 原文摘要(英文)
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.