AI 当摄影师助手：拍照时实时指导构图和摆姿
现在的 AI 修图工具只能事后裁剪，但拍照时最需要的是现场指导——怎么构图、人往哪站。这篇论文做了三件事：建了一个评测基准，发现通用大模型能说“往左移一点”但说不清具体像素，而裁剪模型能精确框出位置却不会给建议；然后造了 13 万条带文字解释和视觉标注的训练数据；最后训练出一个统一模型 ShutterMuse，既能给出构图调整（比如“把主体放在右三分线”），又能根据场景推荐人物姿势（比如“侧身看镜头”），效果比肩甚至超过专用模型，且推理成本更低。它不是你明天就能用的 App，但指明了方向：未来的相机或手机拍照助手，可能在你按下快门前就告诉你“往右一步，头稍微低一点”。
📄 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.