StreetSurfGS: Scalable Urban Street Surface Reconstruction with Planar-based Gaussian Splatting

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Cui, Xiao, Ye, Weicai, Wang, Yifan, Zhang, Guofeng, Zhou, Wengang, Li, Houqiang
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916447325782016
author Cui, Xiao
Ye, Weicai
Wang, Yifan
Zhang, Guofeng
Zhou, Wengang
Li, Houqiang
author_facet Cui, Xiao
Ye, Weicai
Wang, Yifan
Zhang, Guofeng
Zhou, Wengang
Li, Houqiang
contents Reconstructing urban street scenes is crucial due to its vital role in applications such as autonomous driving and urban planning. These scenes are characterized by long and narrow camera trajectories, occlusion, complex object relationships, and data sparsity across multiple scales. Despite recent advancements, existing surface reconstruction methods, which are primarily designed for object-centric scenarios, struggle to adapt effectively to the unique characteristics of street scenes. To address this challenge, we introduce StreetSurfGS, the first method to employ Gaussian Splatting specifically tailored for scalable urban street scene surface reconstruction. StreetSurfGS utilizes a planar-based octree representation and segmented training to reduce memory costs, accommodate unique camera characteristics, and ensure scalability. Additionally, to mitigate depth inaccuracies caused by object overlap, we propose a guided smoothing strategy within regularization to eliminate inaccurate boundary points and outliers. Furthermore, to address sparse views and multi-scale challenges, we use a dual-step matching strategy that leverages adjacent and long-term information. Extensive experiments validate the efficacy of StreetSurfGS in both novel view synthesis and surface reconstruction.
format Preprint
id arxiv_https___arxiv_org_abs_2410_04354
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle StreetSurfGS: Scalable Urban Street Surface Reconstruction with Planar-based Gaussian Splatting
Cui, Xiao
Ye, Weicai
Wang, Yifan
Zhang, Guofeng
Zhou, Wengang
Li, Houqiang
Computer Vision and Pattern Recognition
Reconstructing urban street scenes is crucial due to its vital role in applications such as autonomous driving and urban planning. These scenes are characterized by long and narrow camera trajectories, occlusion, complex object relationships, and data sparsity across multiple scales. Despite recent advancements, existing surface reconstruction methods, which are primarily designed for object-centric scenarios, struggle to adapt effectively to the unique characteristics of street scenes. To address this challenge, we introduce StreetSurfGS, the first method to employ Gaussian Splatting specifically tailored for scalable urban street scene surface reconstruction. StreetSurfGS utilizes a planar-based octree representation and segmented training to reduce memory costs, accommodate unique camera characteristics, and ensure scalability. Additionally, to mitigate depth inaccuracies caused by object overlap, we propose a guided smoothing strategy within regularization to eliminate inaccurate boundary points and outliers. Furthermore, to address sparse views and multi-scale challenges, we use a dual-step matching strategy that leverages adjacent and long-term information. Extensive experiments validate the efficacy of StreetSurfGS in both novel view synthesis and surface reconstruction.
title StreetSurfGS: Scalable Urban Street Surface Reconstruction with Planar-based Gaussian Splatting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.04354