CoSurfGS:Collaborative 3D Surface Gaussian Splatting with Distributed Learning for Large Scene Reconstruction

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Gao, Yuanyuan, Dai, Yalun, Li, Hao, Ye, Weicai, Chen, Junyi, Chen, Danpeng, Zhang, Dingwen, He, Tong, Zhang, Guofeng, Han, Junwei
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915076994236416
author Gao, Yuanyuan
Dai, Yalun
Li, Hao
Ye, Weicai
Chen, Junyi
Chen, Danpeng
Zhang, Dingwen
He, Tong
Zhang, Guofeng
Han, Junwei
author_facet Gao, Yuanyuan
Dai, Yalun
Li, Hao
Ye, Weicai
Chen, Junyi
Chen, Danpeng
Zhang, Dingwen
He, Tong
Zhang, Guofeng
Han, Junwei
contents 3D Gaussian Splatting (3DGS) has demonstrated impressive performance in scene reconstruction. However, most existing GS-based surface reconstruction methods focus on 3D objects or limited scenes. Directly applying these methods to large-scale scene reconstruction will pose challenges such as high memory costs, excessive time consumption, and lack of geometric detail, which makes it difficult to implement in practical applications. To address these issues, we propose a multi-agent collaborative fast 3DGS surface reconstruction framework based on distributed learning for large-scale surface reconstruction. Specifically, we develop local model compression (LMC) and model aggregation schemes (MAS) to achieve high-quality surface representation of large scenes while reducing GPU memory consumption. Extensive experiments on Urban3d, MegaNeRF, and BlendedMVS demonstrate that our proposed method can achieve fast and scalable high-fidelity surface reconstruction and photorealistic rendering. Our project page is available at \url{https://gyy456.github.io/CoSurfGS}.
format Preprint
id arxiv_https___arxiv_org_abs_2412_17612
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CoSurfGS:Collaborative 3D Surface Gaussian Splatting with Distributed Learning for Large Scene Reconstruction
Gao, Yuanyuan
Dai, Yalun
Li, Hao
Ye, Weicai
Chen, Junyi
Chen, Danpeng
Zhang, Dingwen
He, Tong
Zhang, Guofeng
Han, Junwei
Computer Vision and Pattern Recognition
3D Gaussian Splatting (3DGS) has demonstrated impressive performance in scene reconstruction. However, most existing GS-based surface reconstruction methods focus on 3D objects or limited scenes. Directly applying these methods to large-scale scene reconstruction will pose challenges such as high memory costs, excessive time consumption, and lack of geometric detail, which makes it difficult to implement in practical applications. To address these issues, we propose a multi-agent collaborative fast 3DGS surface reconstruction framework based on distributed learning for large-scale surface reconstruction. Specifically, we develop local model compression (LMC) and model aggregation schemes (MAS) to achieve high-quality surface representation of large scenes while reducing GPU memory consumption. Extensive experiments on Urban3d, MegaNeRF, and BlendedMVS demonstrate that our proposed method can achieve fast and scalable high-fidelity surface reconstruction and photorealistic rendering. Our project page is available at \url{https://gyy456.github.io/CoSurfGS}.
title CoSurfGS:Collaborative 3D Surface Gaussian Splatting with Distributed Learning for Large Scene Reconstruction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.17612