InstDrive: Instance-Aware 3D Gaussian Splatting for Driving Scenes

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Hongyuan, Yu, Haochen, Zou, Bochao, Jiang, Jianfei, Liu, Qiankun, Chen, Jiansheng, Ma, Huimin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911238663962624
author Liu, Hongyuan
Yu, Haochen
Zou, Bochao
Jiang, Jianfei
Liu, Qiankun
Chen, Jiansheng
Ma, Huimin
author_facet Liu, Hongyuan
Yu, Haochen
Zou, Bochao
Jiang, Jianfei
Liu, Qiankun
Chen, Jiansheng
Ma, Huimin
contents Reconstructing dynamic driving scenes from dashcam videos has attracted increasing attention due to its significance in autonomous driving and scene understanding. While recent advances have made impressive progress, most methods still unify all background elements into a single representation, hindering both instance-level understanding and flexible scene editing. Some approaches attempt to lift 2D segmentation into 3D space, but often rely on pre-processed instance IDs or complex pipelines to map continuous features to discrete identities. Moreover, these methods are typically designed for indoor scenes with rich viewpoints, making them less applicable to outdoor driving scenarios. In this paper, we present InstDrive, an instance-aware 3D Gaussian Splatting framework tailored for the interactive reconstruction of dynamic driving scene. We use masks generated by SAM as pseudo ground-truth to guide 2D feature learning via contrastive loss and pseudo-supervised objectives. At the 3D level, we introduce regularization to implicitly encode instance identities and enforce consistency through a voxel-based loss. A lightweight static codebook further bridges continuous features and discrete identities without requiring data pre-processing or complex optimization. Quantitative and qualitative experiments demonstrate the effectiveness of InstDrive, and to the best of our knowledge, it is the first framework to achieve 3D instance segmentation in dynamic, open-world driving scenes.More visualizations are available at our project page.
format Preprint
id arxiv_https___arxiv_org_abs_2508_12015
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle InstDrive: Instance-Aware 3D Gaussian Splatting for Driving Scenes
Liu, Hongyuan
Yu, Haochen
Zou, Bochao
Jiang, Jianfei
Liu, Qiankun
Chen, Jiansheng
Ma, Huimin
Computer Vision and Pattern Recognition
Reconstructing dynamic driving scenes from dashcam videos has attracted increasing attention due to its significance in autonomous driving and scene understanding. While recent advances have made impressive progress, most methods still unify all background elements into a single representation, hindering both instance-level understanding and flexible scene editing. Some approaches attempt to lift 2D segmentation into 3D space, but often rely on pre-processed instance IDs or complex pipelines to map continuous features to discrete identities. Moreover, these methods are typically designed for indoor scenes with rich viewpoints, making them less applicable to outdoor driving scenarios. In this paper, we present InstDrive, an instance-aware 3D Gaussian Splatting framework tailored for the interactive reconstruction of dynamic driving scene. We use masks generated by SAM as pseudo ground-truth to guide 2D feature learning via contrastive loss and pseudo-supervised objectives. At the 3D level, we introduce regularization to implicitly encode instance identities and enforce consistency through a voxel-based loss. A lightweight static codebook further bridges continuous features and discrete identities without requiring data pre-processing or complex optimization. Quantitative and qualitative experiments demonstrate the effectiveness of InstDrive, and to the best of our knowledge, it is the first framework to achieve 3D instance segmentation in dynamic, open-world driving scenes.More visualizations are available at our project page.
title InstDrive: Instance-Aware 3D Gaussian Splatting for Driving Scenes
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.12015