SIMSplat: Predictive Driving Scene Editing with Language-aligned 4D Gaussian Splatting
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909821676027904 |
|---|---|
| author | Park, Sung-Yeon Lee, Adam Lu, Juanwu Cui, Can Jiang, Luyang Gupta, Rohit Han, Kyungtae Moradipari, Ahmadreza Wang, Ziran |
| author_facet | Park, Sung-Yeon Lee, Adam Lu, Juanwu Cui, Can Jiang, Luyang Gupta, Rohit Han, Kyungtae Moradipari, Ahmadreza Wang, Ziran |
| contents | 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/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_02469 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SIMSplat: Predictive Driving Scene Editing with Language-aligned 4D Gaussian Splatting Park, Sung-Yeon Lee, Adam Lu, Juanwu Cui, Can Jiang, Luyang Gupta, Rohit Han, Kyungtae Moradipari, Ahmadreza Wang, Ziran Robotics Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition 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/ |
| title | SIMSplat: Predictive Driving Scene Editing with Language-aligned 4D Gaussian Splatting |
| topic | Robotics Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.02469 |