{"ID":2861669,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.02469","arxiv_id":"2510.02469","title":"SIMSplat: Predictive Driving Scene Editing with Language-aligned 4D Gaussian Splatting","abstract":"Driving scene manipulation with sensor data is emerging as a promising alternative to traditional virtual driving simulators. However, existing frameworks struggle to generate realistic scenarios efficiently due to limited editing capabilities. To address these challenges, we present SIMSplat, a predictive driving scene editor with language-aligned Gaussian splatting. As a language-controlled editor, SIMSplat enables intuitive manipulation using natural language prompts. By aligning language with Gaussian-reconstructed scenes, it further supports direct querying of road objects, allowing precise and flexible editing. Our method provides detailed object-level editing, including adding new objects and modifying the trajectories of both vehicles and pedestrians, while also incorporating predictive path refinement through multi-agent motion prediction to generate realistic interactions among all agents in the scene. Experiments on the Waymo dataset demonstrate SIMSplat's extensive editing capabilities and adaptability across a wide range of scenarios. Project page: https://sungyeonparkk.github.io/simsplat/","short_abstract":"Driving scene manipulation with sensor data is emerging as a promising alternative to traditional virtual driving simulators. However, existing frameworks struggle to generate realistic scenarios efficiently due to limited editing capabilities. To address these challenges, we present SIMSplat, a predictive driving scen...","url_abs":"https://arxiv.org/abs/2510.02469","url_pdf":"https://arxiv.org/pdf/2510.02469v1","authors":"[\"Sung-Yeon Park\",\"Adam Lee\",\"Juanwu Lu\",\"Can Cui\",\"Luyang Jiang\",\"Rohit Gupta\",\"Kyungtae Han\",\"Ahmadreza Moradipari\",\"Ziran Wang\"]","published":"2025-10-02T18:22:03Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.AI\",\"cs.CL\",\"cs.CV\"]","methods":"[]","has_code":false}