解决3D高斯点云的漂浮伪影问题，提升重建质量
Low-Frequency First: Eliminating Floating Artifacts in 3D Gaussian Splatting
- 从频率域分析伪影成因，定位低优化高斯点为根源
- 优先优化低频信息，动态调整高斯点扩展策略，减少伪影
- 在真实与合成数据上均显著提升质量，适合3D重建应用
3D高斯点云（3DGS）是一种高效且强大的三维重建表示方法。尽管其优势明显，但常产生脱离真实几何结构的漂浮伪影，严重降低视觉质量。本文从频域角度探究伪影成因，发现低质量初始化下未充分优化的高斯点是主要来源。为此提出EFA-GS方法，通过选择性扩展低优化高斯点，优先保证低频信息学习。同时引入基于深度和尺度的辅助策略，动态优化高斯点扩展，有效缓解细节丢失。在合成与真实数据集上的大量实验表明，EFA-GS显著减少漂浮伪影，同时保留高频细节，在我们的RWLQ数据集上相比基线方法PSNR提升1.68 dB。此外，该方法在下游3D编辑任务中也展现出良好效果。
原文摘要 · Abstract (English)
3D Gaussian Splatting (3DGS) is a powerful and computationally efficient representation for 3D reconstruction. Despite its strengths, 3DGS often produces floating artifacts, which are erroneous structures detached from the actual geometry and significantly degrade visual fidelity. The underlying mechanisms causing these artifacts, particularly in low-quality initialization scenarios, have not been fully explored. In this paper, we investigate the origins of floating artifacts from a frequency-domain perspective and identify under-optimized Gaussians as the primary source. Based on our analysis, we propose \textit{Eliminating-Floating-Artifacts} Gaussian Splatting (EFA-GS), which selectively expands under-optimized Gaussians to prioritize accurate low-frequency learning. Additionally, we introduce complementary depth-based and scale-based strategies to dynamically refine Gaussian expansion, effectively mitigating detail erosion. Extensive experiments on both synthetic and real-world datasets demonstrate that EFA-GS substantially reduces floating artifacts while preserving high-frequency details, achieving an improvement of 1.68 dB in PSNR over baseline method on our RWLQ dataset. Furthermore, we validate the effectiveness of our approach in downstream 3D editing tasks. Project Website: https://jcwang-gh.github.io/EFA-GS
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。