Saved in:
Bibliographic Details
Main Authors: Wang, Tengfei, Wang, Xin, Hou, Yongmao, Xu, Yiwei, Zhang, Wendi, Zhan, Zongqian
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.01677
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913634228109312
author Wang, Tengfei
Wang, Xin
Hou, Yongmao
Xu, Yiwei
Zhang, Wendi
Zhan, Zongqian
author_facet Wang, Tengfei
Wang, Xin
Hou, Yongmao
Xu, Yiwei
Zhang, Wendi
Zhan, Zongqian
contents 3D Gaussian Splatting (3DGS) has emerged as a transformative method in the field of real-time novel synthesis. Based on 3DGS, recent advancements cope with large-scale scenes via spatial-based partition strategy to reduce video memory and optimization time costs. In this work, we introduce a parallel Gaussian splatting method, termed PG-SAG, which fully exploits semantic cues for both partitioning and Gaussian kernel optimization, enabling fine-grained building surface reconstruction of large-scale urban areas without downsampling the original image resolution. First, the Cross-modal model - Language Segment Anything is leveraged to segment building masks. Then, the segmented building regions is grouped into sub-regions according to the visibility check across registered images. The Gaussian kernels for these sub-regions are optimized in parallel with masked pixels. In addition, the normal loss is re-formulated for the detected edges of masks to alleviate the ambiguities in normal vectors on edges. Finally, to improve the optimization of 3D Gaussians, we introduce a gradient-constrained balance-load loss that accounts for the complexity of the corresponding scenes, effectively minimizing the thread waiting time in the pixel-parallel rendering stage as well as the reconstruction lost. Extensive experiments are tested on various urban datasets, the results demonstrated the superior performance of our PG-SAG on building surface reconstruction, compared to several state-of-the-art 3DGS-based methods. Project Web:https://github.com/TFWang-9527/PG-SAG.
format Preprint
id arxiv_https___arxiv_org_abs_2501_01677
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PG-SAG: Parallel Gaussian Splatting for Fine-Grained Large-Scale Urban Buildings Reconstruction via Semantic-Aware Grouping
Wang, Tengfei
Wang, Xin
Hou, Yongmao
Xu, Yiwei
Zhang, Wendi
Zhan, Zongqian
Computer Vision and Pattern Recognition
3D Gaussian Splatting (3DGS) has emerged as a transformative method in the field of real-time novel synthesis. Based on 3DGS, recent advancements cope with large-scale scenes via spatial-based partition strategy to reduce video memory and optimization time costs. In this work, we introduce a parallel Gaussian splatting method, termed PG-SAG, which fully exploits semantic cues for both partitioning and Gaussian kernel optimization, enabling fine-grained building surface reconstruction of large-scale urban areas without downsampling the original image resolution. First, the Cross-modal model - Language Segment Anything is leveraged to segment building masks. Then, the segmented building regions is grouped into sub-regions according to the visibility check across registered images. The Gaussian kernels for these sub-regions are optimized in parallel with masked pixels. In addition, the normal loss is re-formulated for the detected edges of masks to alleviate the ambiguities in normal vectors on edges. Finally, to improve the optimization of 3D Gaussians, we introduce a gradient-constrained balance-load loss that accounts for the complexity of the corresponding scenes, effectively minimizing the thread waiting time in the pixel-parallel rendering stage as well as the reconstruction lost. Extensive experiments are tested on various urban datasets, the results demonstrated the superior performance of our PG-SAG on building surface reconstruction, compared to several state-of-the-art 3DGS-based methods. Project Web:https://github.com/TFWang-9527/PG-SAG.
title PG-SAG: Parallel Gaussian Splatting for Fine-Grained Large-Scale Urban Buildings Reconstruction via Semantic-Aware Grouping
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2501.01677