{"ID":5438614,"CreatedAt":"2026-07-01T01:17:58.482524686Z","UpdatedAt":"2026-07-03T03:45:45.236501583Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.31109","arxiv_id":"2606.31109","title":"InfiniVerse: Occupancy Guided Unbounded Scene Generation for Autonomous Driving","abstract":"Generating realistic, controllable, and temporally coherent urban environments is a critical yet unresolved challenge in the autonomous driving community. In this paper, we introduce InfiniVerse, a unified pipeline for long-range, 2D-3D-aligned, and controllable synthesis of dynamic urban scenes from a single frame. In practice, our approach first reconstructs a 3D occupancy representation from the input multi-view frame. This representation serves as a foundation for autoregressive scene extension along arbitrary trajectories. Subsequently, a video diffusion model translates the coarse occupancy grid into realistic, spatiotemporally consistent video sequences. Moreover, we propose a hierarchical sketch-and-refine paradigm, in which the generated videos are re-projected as image-conditioned feedback to enhance the 3D occupancy representation, establishing cross-modal alignment and mutual enhancement between the visual and spatial domains. Extensive evaluations on the Waymo Open Dataset and nuScenes demonstrate that InfiniVerse achieves state-of-the-art performance, with a FID of 6.4 and FVD of 67.97, significantly outperforming existing benchmarks in both duration and stability.","short_abstract":"Generating realistic, controllable, and temporally coherent urban environments is a critical yet unresolved challenge in the autonomous driving community. In this paper, we introduce InfiniVerse, a unified pipeline for long-range, 2D-3D-aligned, and controllable synthesis of dynamic urban scenes from a single frame. In...","url_abs":"https://arxiv.org/abs/2606.31109","url_pdf":"https://arxiv.org/pdf/2606.31109v1","authors":"[\"Xiaoyu Ye\",\"Leheng Li\",\"Xinyu Ji\",\"Yingjie Cai\",\"Hongda He\",\"Xu Yan\",\"Guanyi Zhao\",\"Ying-Cong Chen\",\"Bingbing Liu\",\"Shuguang Cui\",\"Zhen Li\"]","published":"2026-06-30T04:08:22Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}