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/
@article{arxiv.2510.02469,
title = {SIMSplat: Predictive Driving Scene Editing with Language-aligned 4D Gaussian Splatting},
author = {Sung-Yeon Park and Adam Lee and Juanwu Lu and Can Cui and Luyang Jiang and Rohit Gupta and Kyungtae Han and Ahmadreza Moradipari and Ziran Wang},
journal= {arXiv preprint arXiv:2510.02469},
year = {2025}
}