AI RESEARCH

VistaGEN: Consistent Driving Video Generation with Fine-Grained Control Using Multiview Visual-Language Reasoning

arXiv CS.CV

ArXi:2603.28353v1 Announce Type: new Driving video generation has achieved much progress in controllability, video resolution, and length, but fails to fine-grained object-level controllability for diverse driving videos, while preserving the spatiotemporal consistency, especially in long video generation. In this paper, we present a new driving video generation technique, called VistaGEN, which enables fine-grained control of specific entities, including 3D objects, images, and text descriptions, while maintaining spatiotemporal consistency in long video sequences.