[2603.22796] PhotoAgent: A Robotic Photographer with Spatial and Aesthetic Understanding

Computer Science > Computer Vision and Pattern Recognition arXiv:2603.22796 (cs) [Submitted on 24 Mar 2026] Title:PhotoAgent: A Robotic Photographer with Spatial and Aesthetic Understanding Authors:Lirong Che, Zhenfeng Gan, Yanbo Chen, Junbo Tan, Xueqian Wang View a PDF of the paper titled PhotoAgent: A Robotic Photographer with Spatial and Aesthetic Understanding, by Lirong Che and 4 other authors View PDF HTML (experimental) Abstract: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. Comments: Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Robotics (cs.RO) Cite as: arXiv:2603.22796 [cs.CV]   ...