DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Xiaoyu, Lin, Zhiwei, Shan, Xiaojun, Wang, Yongtao, Sun, Deqing, Yang, Ming-Hsuan
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909142864625664
author Zhou, Xiaoyu
Lin, Zhiwei
Shan, Xiaojun
Wang, Yongtao
Sun, Deqing
Yang, Ming-Hsuan
author_facet Zhou, Xiaoyu
Lin, Zhiwei
Shan, Xiaojun
Wang, Yongtao
Sun, Deqing
Yang, Ming-Hsuan
contents We present DrivingGaussian, an efficient and effective framework for surrounding dynamic autonomous driving scenes. For complex scenes with moving objects, we first sequentially and progressively model the static background of the entire scene with incremental static 3D Gaussians. We then leverage a composite dynamic Gaussian graph to handle multiple moving objects, individually reconstructing each object and restoring their accurate positions and occlusion relationships within the scene. We further use a LiDAR prior for Gaussian Splatting to reconstruct scenes with greater details and maintain panoramic consistency. DrivingGaussian outperforms existing methods in dynamic driving scene reconstruction and enables photorealistic surround-view synthesis with high-fidelity and multi-camera consistency. Our project page is at: https://github.com/VDIGPKU/DrivingGaussian.
format Preprint
id arxiv_https___arxiv_org_abs_2312_07920
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes
Zhou, Xiaoyu
Lin, Zhiwei
Shan, Xiaojun
Wang, Yongtao
Sun, Deqing
Yang, Ming-Hsuan
Computer Vision and Pattern Recognition
We present DrivingGaussian, an efficient and effective framework for surrounding dynamic autonomous driving scenes. For complex scenes with moving objects, we first sequentially and progressively model the static background of the entire scene with incremental static 3D Gaussians. We then leverage a composite dynamic Gaussian graph to handle multiple moving objects, individually reconstructing each object and restoring their accurate positions and occlusion relationships within the scene. We further use a LiDAR prior for Gaussian Splatting to reconstruct scenes with greater details and maintain panoramic consistency. DrivingGaussian outperforms existing methods in dynamic driving scene reconstruction and enables photorealistic surround-view synthesis with high-fidelity and multi-camera consistency. Our project page is at: https://github.com/VDIGPKU/DrivingGaussian.
title DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.07920