用几何监督提升2D高斯点云,让反光物体重建更快更准
GS-2DGS: Geometrically Supervised 2DGS for Reflective Object Reconstruction
- 在2D高斯点云中引入几何约束,结合基础模型增强表面信息
- 重建速度比SDF方法快10倍,精度接近顶尖水平
- 适合需要快速高保真重建反光物体的工业与科研场景
高反射物体的3D建模因视角依赖性外观而极具挑战。现有基于SDF的方法虽能生成高质量网格,但计算耗时且易产生过平滑表面。相比之下,3D高斯溅射(3DGS)具备高速和实时渲染优势,但缺乏几何约束导致表面提取噪声较大。为此,我们提出一种基于2D高斯溅射(2DGS)的新重建方法——GS-2DGS,融合高斯溅射的快速渲染能力与基础模型提供的几何先验信息。在合成与真实数据集上的实验表明,该方法在重建与再照明性能上显著优于现有高斯基方法,同时达到与SDF方法相当的精度,且速度提升一个数量级。代码已开源:https://github.com/hirotong/GS2DGS
原文摘要 · Abstract (English)
3D modeling of highly reflective objects remains challenging due to strong view-dependent appearances. While previous SDF-based methods can recover high-quality meshes, they are often time-consuming and tend to produce over-smoothed surfaces. In contrast, 3D Gaussian Splatting (3DGS) offers the advantage of high speed and detailed real-time rendering, but extracting surfaces from the Gaussians can be noisy due to the lack of geometric constraints. To bridge the gap between these approaches, we propose a novel reconstruction method called GS-2DGS for reflective objects based on 2D Gaussian Splatting (2DGS). Our approach combines the rapid rendering capabilities of Gaussian Splatting with additional geometric information from foundation models. Experimental results on synthetic and real datasets demonstrate that our method significantly outperforms Gaussian-based techniques in terms of reconstruction and relighting and achieves performance comparable to SDF-based methods while being an order of magnitude faster. Code is available at https://github.com/hirotong/GS2DGS
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。