AI RESEARCH

HorizonWeaver: Generalizable Multi-Level Semantic Editing for Driving Scenes

arXiv CS.CV

ArXi:2604.04887v1 Announce Type: new Ensuring safety in autonomous driving requires scalable generation of realistic, controllable driving scenes beyond what real-world testing provides. Yet existing instruction guided image editors, trained on object-centric or artistic data, struggle with dense, safety-critical driving layouts.