首次用3D高斯实现大规模场景高质量表面重建
GigaGS: Scaling up Planar-Based 3D Gaussians for Large Scene Surface Reconstruction
- 按空间区域互视性分块，支持并行处理降低显存压力
- 引入多视角光度与几何一致性约束，提升细节还原质量
- 适合需要高保真大场景重建的研究者与工业应用
3D高斯点阵（3DGS）在新视角合成中表现优异。此前方法仅适用于单个3D物体或小范围场景。本文首次尝试解决大规模场景表面重建这一挑战性任务，该任务因高显存占用、几何表示细节层次不一及外观不一致而困难。为此，我们提出GigaGS，首个基于3DGS的高质量大场景表面重建方法。GigaGS采用基于空间区域互视性的分块策略，有效分组相机以支持并行处理。为提升表面质量，还提出基于细节层级（Level-of-Detail）表示的多视角光度与几何一致性约束，实现精细结构重建。在多个数据集上进行充分实验，结果一致显示性能优越。
原文摘要 · Abstract (English)
3D Gaussian Splatting (3DGS) has shown promising performance in novel view synthesis. Previous methods adapt it to obtaining surfaces of either individual 3D objects or within limited scenes. In this paper, we make the first attempt to tackle the challenging task of large-scale scene surface reconstruction. This task is particularly difficult due to the high GPU memory consumption, different levels of details for geometric representation, and noticeable inconsistencies in appearance. To this end, we propose GigaGS, the first work for high-quality surface reconstruction for large-scale scenes using 3DGS. GigaGS first applies a partitioning strategy based on the mutual visibility of spatial regions, which effectively grouping cameras for parallel processing. To enhance the quality of the surface, we also propose novel multi-view photometric and geometric consistency constraints based on Level-of-Detail representation. In doing so, our method can reconstruct detailed surface structures. Comprehensive experiments are conducted on various datasets. The consistent improvement demonstrates the superiority of GigaGS.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。