paper-with-me

홈 › Papers

DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving

2024-12-12 · Hao Lu, Tianshuo Xu, Wenzhao Zheng, Yunpeng Zhang, Wei Zhan, Dalong Du, Masayoshi Tomizuka, Kurt Keutzer, Yingcong Chen

Photorealistic 4D reconstruction of street scenes is essential for developing real-world simulators in autonomous driving. However, most existing methods perform this task offline and rely on time-consuming iterative processes, limiting their practical applications. To this end, we introduce the Large 4D Gaussian Reconstruction Model (DrivingRecon), a generalizable driving scene reconstruction model, which directly predicts 4D Gaussian from surround view videos. To better integrate the surround-view images, the Prune and Dilate Block (PD-Block) is proposed to eliminate overlapping Gaussian points between adjacent views and remove redundant background points. To enhance cross-temporal information, dynamic and static decoupling is tailored to better learn geometry and motion features. Experimental results demonstrate that DrivingRecon significantly improves scene reconstruction quality and novel view synthesis compared to existing methods. Furthermore, we explore applications of DrivingRecon in model pre-training, vehicle adaptation, and scene editing. Our code is available at https://github.com/EnVision-Research/DriveRecon.

📄 PDF Abstract BibTeX arXiv:2412.09043

Code (1)

envision-research/driverecon 공식 구현

Tasks

4D reconstructionAutonomous DrivingNovel View Synthesis

Similar Papers 제목 키워드 기반

Nighttime Autonomous Driving Scene Reconstruction with Physically-Based Gaussian Splatting

2026-02-14 · Tae-Kyeong Kim, Xingxin Chen, Guile Wu, Chengjie Huang 외 arxiv

This paper focuses on scene reconstruction under nighttime conditions in autonomous driving simulation. Recent methods based on Neural Radiance Fields (NeRFs) and 3D Gaussian Splatting (3DGS) have achieved photorealistic…

Autonomous Driving

AutoSplat: Constrained Gaussian Splatting for Autonomous Driving Scene Reconstruction

2024-07-02 · Mustafa Khan, Hamidreza Fazlali, Dhruv Sharma, Tongtong Cao 외

Realistic scene reconstruction and view synthesis are essential for advancing autonomous driving systems by simulating safety-critical scenarios. 3D Gaussian Splatting excels in real-time rendering and static scene recon…

Autonomous DrivingNovel View Synthesis

DrivingGaussian++: Towards Realistic Reconstruction and Editable Simulation for Surrounding Dynamic Driving Scenes

2025-08-28 · Yajiao Xiong, Xiaoyu Zhou, Yongtao Wan, Deqing Sun 외 arxiv

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 us…

Autonomous Driving

DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes

2023-12-13 · CVPR 2024 1 · Xiaoyu Zhou, Zhiwei Lin, Xiaojun Shan, Yongtao Wang 외

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 backgro…

Autonomous Driving

LT-Gaussian: Long-Term Map Update Using 3D Gaussian Splatting for Autonomous Driving

2025-08-03 · Luqi Cheng, Zhangshuo Qi, Zijie Zhou, Chao Lu 외 arxiv

Maps play an important role in autonomous driving systems. The recently proposed 3D Gaussian Splatting (3D-GS) produces rendering-quality explicit scene reconstruction results, demonstrating the potential for map constru…

Autonomous DrivingChange Detection