ESA-GS: Elongation splitting and assimilation in Gaussian splatting for accurate surface reconstruction

IF 1.3 4区计算机科学 Q3 COMPUTER SCIENCE, SOFTWARE ENGINEERING

Computer Aided Geometric Design Pub Date : 2025-04-17 DOI:10.1016/j.cagd.2025.102434

Yuyang Chen, Wenming Wu, Yusheng Peng, Yue Fei, Liping Zheng

{"title":"ESA-GS: Elongation splitting and assimilation in Gaussian splatting for accurate surface reconstruction","authors":"Yuyang Chen, Wenming Wu, Yusheng Peng, Yue Fei, Liping Zheng","doi":"10.1016/j.cagd.2025.102434","DOIUrl":null,"url":null,"abstract":"<div><div>Recently, 3D Gaussian Splatting (3DGS) has significantly advanced the development of 3D reconstruction by providing efficient and high-quality rendering. 2D Gaussian Splatting (2DGS) introduced two-dimensional surfels as scene primitives to address 3DGS's limitations in surface representation. However, its adaptive control strategy may still result in suboptimal results, especially when dealing with extreme-shaped or large Gaussians on the surface. We propose Elongation Splitting and Assimilation in Gaussian Splatting (ESA-GS) to enhance geometric reconstruction quality by addressing these special Gaussians. Specifically, ESA-GS splits highly elongated Gaussians on the surface into three assimilated Gaussians during the densification process. In addition, ESA-GS adds an opacity degeneration strategy and an additional pruning strategy to remove invalid Gaussians and improve the geometry quality. Experimental results demonstrate that ESA-GS can produce geometrically accurate reconstructed surfaces without sacrificing efficiency in most cases.</div></div>","PeriodicalId":55226,"journal":{"name":"Computer Aided Geometric Design","volume":"119 ","pages":"Article 102434"},"PeriodicalIF":1.3000,"publicationDate":"2025-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computer Aided Geometric Design","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0167839625000238","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, SOFTWARE ENGINEERING","Score":null,"Total":0}

引用次数: 0

Abstract

Recently, 3D Gaussian Splatting (3DGS) has significantly advanced the development of 3D reconstruction by providing efficient and high-quality rendering. 2D Gaussian Splatting (2DGS) introduced two-dimensional surfels as scene primitives to address 3DGS's limitations in surface representation. However, its adaptive control strategy may still result in suboptimal results, especially when dealing with extreme-shaped or large Gaussians on the surface. We propose Elongation Splitting and Assimilation in Gaussian Splatting (ESA-GS) to enhance geometric reconstruction quality by addressing these special Gaussians. Specifically, ESA-GS splits highly elongated Gaussians on the surface into three assimilated Gaussians during the densification process. In addition, ESA-GS adds an opacity degeneration strategy and an additional pruning strategy to remove invalid Gaussians and improve the geometry quality. Experimental results demonstrate that ESA-GS can produce geometrically accurate reconstructed surfaces without sacrificing efficiency in most cases.

查看原文本刊更多论文

ESA-GS：用于精确表面重建的高斯溅射中的伸长分裂和同化

近年来，三维高斯喷溅技术（3DGS）通过提供高效、高质量的渲染，极大地推动了三维重建的发展。2D高斯喷溅（2DGS）引入二维冲浪作为场景基元，以解决3DGS在表面表示方面的局限性。然而，其自适应控制策略仍然可能导致次优结果，特别是当处理曲面上的极端形状或大高斯分布时。我们提出了高斯溅射（ESA-GS）中的伸长分裂和同化，通过处理这些特殊的高斯分布来提高几何重建质量。具体地说，ESA-GS在致密化过程中将表面上高度拉长的高斯分解为三个同化的高斯。此外，ESA-GS还增加了一种不透明度退化策略和一种额外的剪枝策略，以去除无效高斯分布，提高几何质量。实验结果表明，在大多数情况下，ESA-GS可以在不牺牲效率的情况下产生几何精度的重建表面。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Computer Aided Geometric Design 工程技术-计算机：软件工程

CiteScore

3.50

自引率

13.30%

发文量

审稿时长

60 days

期刊介绍： The journal Computer Aided Geometric Design is for researchers, scholars, and software developers dealing with mathematical and computational methods for the description of geometric objects as they arise in areas ranging from CAD/CAM to robotics and scientific visualization. The journal publishes original research papers, survey papers and with quick editorial decisions short communications of at most 3 pages. The primary objects of interest are curves, surfaces, and volumes such as splines (NURBS), meshes, subdivision surfaces as well as algorithms to generate, analyze, and manipulate them. This journal will report on new developments in CAGD and its applications, including but not restricted to the following: -Mathematical and Geometric Foundations- Curve, Surface, and Volume generation- CAGD applications in Numerical Analysis, Computational Geometry, Computer Graphics, or Computer Vision- Industrial, medical, and scientific applications. The aim is to collect and disseminate information on computer aided design in one journal. To provide the user community with methods and algorithms for representing curves and surfaces. To illustrate computer aided geometric design by means of interesting applications. To combine curve and surface methods with computer graphics. To explain scientific phenomena by means of computer graphics. To concentrate on the interaction between theory and application. To expose unsolved problems of the practice. To develop new methods in computer aided geometry.