Scholarlink

<p>3D Gaussian Splatting (3DGS) has emerged as a&#xa0;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&#xa0;parallel Gaussian splatting method termed <i>PG-SAG</i>. This method fully exploits semantic cues for 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 are 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&#xa0;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 loss. Extensive experiments are tested on various urban datasets, the results demonstrated the superior performance of our <i>PG-SAG</i> on building surface reconstruction, compared to several state-of-the-art 3DGS-based methods. Project Web: <a href="https://github.com/TFWang-9527/PG-SAG">https://github.com/TFWang-9527/PG-SAG</a>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

PG-SAG: Parallel Gaussian Splatting for Fine-Grained Large-Scale Urban Buildings Reconstruction via Semantic-Aware Grouping

  • 期刊论文

  • 发表日期：

    2025年5月20日

查看全文
  • Tengfei Wang,
  • Xin Wang,
  • Yongmao Hou,
  • Yiwei Xu,
  • Wendi Zhang,
  • Zongqian Zhan

摘要

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. This method fully exploits semantic cues for 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 are 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 loss. 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.