PhotoAgent：一种具有空间与审美理解的机器人摄影师
PhotoAgent: A Robotic Photographer with Spatial and Aesthetic Understanding
AI总结：
PhotoAgent通过整合大多模态模型与新型控制范式，将主观审美目标转化为几何约束，利用内部视觉模拟实现快速收敛于高质量图像结果。
摘要：
具身代理在如摄影等创造性任务中必须弥合高阶语言指令与几何控制之间的语义鸿沟。我们引入PhotoAgent，通过整合大多模态模型（LMMs）推理与新型控制范式实现这一目标。PhotoAgent首先通过LMM驱动的链式推理将主观审美目标转化为可解的几何约束，使分析求解器计算出高质量的初始视角。此初始姿态通过在由3D高斯点云（3DGS）构建的逼真内部世界模型中的视觉反馈进行迭代优化。这种「心理模拟」取代了昂贵且缓慢的物理试错，使代理能够快速收敛到更具审美价值的结果。评估证实PhotoAgent在空间推理方面表现出色，并实现了更优的最终图像质量。
英文摘要：
Embodied agents for creative tasks like photography must bridge the semantic gap between high-level language commands and geometric control. We introduce PhotoAgent, an agent that achieves this by integrating Large Multimodal Models (LMMs) reasoning with a novel control paradigm. PhotoAgent first translates subjective aesthetic goals into solvable geometric constraints via LMM-driven, chain-of-thought (CoT) reasoning, allowing an analytical solver to compute a high-quality initial viewpoint. This initial pose is then iteratively refined through visual reflection within a photorealistic internal world model built with 3D Gaussian Splatting (3DGS). This ``mental simulation'' replaces costly and slow physical trial-and-error, enabling rapid convergence to aesthetically superior results. Evaluations confirm that PhotoAgent excels in spatial reasoning and achieves superior final image quality.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
