PhotoAgent: 空間的・美的理解を備えたロボット写真家
PhotoAgent: A Robotic Photographer with Spatial and Aesthetic Understanding
ロボット写真家のためのエージェントで、大規模マルチモーダルモデルと3Dガウススプラッティングによる内部世界モデルを統合し、言語指示から美的に優れた視点を自動生成・反復改善する。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Lirong Che, Zhenfeng Gan, Yanbo Chen, Junbo Tan, Xueqian Wang
分類: cs.CV, cs.AI, cs.RO
原文アブストラクト
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.
