ShutterMuse：基于MLLMs的实时摄影指导

摘要

现实摄影需要在拍摄时对取景构图和被摄者姿态进行引导。然而，现有的美学裁剪基准主要评估事后裁剪预测，忽略了被摄者侧的建议，使得多模态大语言模型（MLLMs）在拍摄时引导能力上的探索尚不充分。为填补这一空白，我们提出了CaptureGuide-Bench，这是一个包含两个互补任务的基准：摄影师侧的构图决策与优化，以及被摄者侧的基于场景的姿态推荐。我们的评估揭示了现有方法的局限性：通用型MLLMs能够做出构图决策，但缺乏精确的优化定位能力；而专门的美学裁剪模型虽能有效定位裁剪区域，却仅限于优化任务，两者均无法提供可执行的姿态引导。为支持模型开发，我们进一步构建了CaptureGuide-Dataset，包含13万个带有文本理由和结构化视觉标注的样本，并开发了ShutterMuse——一个统一的多模态大语言模型，通过监督学习和强化学习微调进行训练。在CaptureGuide-Bench上的实验表明，ShutterMuse在评估基线中取得了最佳的摄影师侧综合性能，同时在显著降低推理成本的情况下，在被摄者侧姿态推荐方面也表现出色，展示了多模态大语言模型作为图像拍摄过程中交互式助手的潜力。

English

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.