DrivingGaussian++: Towards Realistic Reconstruction and Editable Simulation for Surrounding Dynamic Driving Scenes
This addresses the need for realistic and editable simulations in autonomous driving, offering incremental improvements over prior dynamic scene reconstruction techniques.
The paper tackles the problem of reconstructing and editing dynamic driving scenes by proposing DrivingGaussian++, which uses 3D Gaussians and a LiDAR prior to achieve realistic reconstruction and photorealistic synthesis, outperforming existing methods, and supports training-free editing like texture modification and object manipulation.
We present DrivingGaussian++, an efficient and effective framework for realistic reconstructing and controllable editing of surrounding dynamic autonomous driving scenes. DrivingGaussian++ models the static background using incremental 3D Gaussians and reconstructs moving objects with a composite dynamic Gaussian graph, ensuring accurate positions and occlusions. By integrating a LiDAR prior, it achieves detailed and consistent scene reconstruction, outperforming existing methods in dynamic scene reconstruction and photorealistic surround-view synthesis. DrivingGaussian++ supports training-free controllable editing for dynamic driving scenes, including texture modification, weather simulation, and object manipulation, leveraging multi-view images and depth priors. By integrating large language models (LLMs) and controllable editing, our method can automatically generate dynamic object motion trajectories and enhance their realism during the optimization process. DrivingGaussian++ demonstrates consistent and realistic editing results and generates dynamic multi-view driving scenarios, while significantly enhancing scene diversity. More results and code can be found at the project site: https://xiong-creator.github.io/DrivingGaussian_plus.github.io