{"ID":2864795,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.23402","arxiv_id":"2509.23402","title":"WorldSplat: Gaussian-Centric Feed-Forward 4D Scene Generation for Autonomous Driving","abstract":"Recent advances in driving-scene generation and reconstruction have demonstrated significant potential for enhancing autonomous driving systems by producing scalable and controllable training data. Existing generation methods primarily focus on synthesizing diverse and high-fidelity driving videos; however, due to limited 3D consistency and sparse viewpoint coverage, they struggle to support convenient and high-quality novel-view synthesis (NVS). Conversely, recent 3D/4D reconstruction approaches have significantly improved NVS for real-world driving scenes, yet inherently lack generative capabilities. To overcome this dilemma between scene generation and reconstruction, we propose WorldSplat, a novel feed-forward framework for 4D driving-scene generation. Our approach effectively generates consistent multi-track videos through two key steps: (i) We introduce a 4D-aware latent diffusion model integrating multi-modal information to produce pixel-aligned 4D Gaussians in a feed-forward manner. (ii) Subsequently, we refine the novel view videos rendered from these Gaussians using a enhanced video diffusion model. Extensive experiments conducted on benchmark datasets demonstrate that WorldSplat effectively generates high-fidelity, temporally and spatially consistent multi-track novel view driving videos. Project: https://wm-research.github.io/worldsplat/","short_abstract":"Recent advances in driving-scene generation and reconstruction have demonstrated significant potential for enhancing autonomous driving systems by producing scalable and controllable training data. Existing generation methods primarily focus on synthesizing diverse and high-fidelity driving videos; however, due to limi...","url_abs":"https://arxiv.org/abs/2509.23402","url_pdf":"https://arxiv.org/pdf/2509.23402v2","authors":"[\"Ziyue Zhu\",\"Zhanqian Wu\",\"Zhenxin Zhu\",\"Lijun Zhou\",\"Haiyang Sun\",\"Bing Wan\",\"Kun Ma\",\"Guang Chen\",\"Hangjun Ye\",\"Jin Xie\",\"jian Yang\"]","published":"2025-09-27T16:47:44Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}