AI RESEARCH
LangDriveCTRL: Natural Language Controllable Driving Scene Editing with Multi-modal Agents
arXiv CS.CV
•
ArXi:2512.17445v2 Announce Type: replace LangDriveCTRL is a natural-language-controllable framework for editing real-world driving videos to synthesize diverse traffic scenarios. It represents each video as an explicit 3D scene graph, decomposing the scene into a static background and dynamic object nodes. To enable fine-grained editing and realism, it