通过正则化提升3D高斯点云的表面一致性与视觉质量
ARGS: Advanced Regularization on Aligning Gaussians over the Surface
- 引入秩正则化抑制细长高斯形态，促进扁平碟状分布
- 融合神经SDF与Eikonal损失，构建全局连续表面先验
- 适合追求高质量3D重建与表面一致性的图形研究者
从3D高斯喷溅（3DGS）中重建高质量3D网格与视觉效果仍是计算机图形学的核心挑战。尽管现有模型如SuGaR在渲染方面表现良好，但在视觉保真度和场景一致性上仍有提升空间。本文在SuGaR基础上提出两种互补正则化策略：第一，引入有效秩正则化，受近期高斯基元结构研究启发，抑制极端各向异性（即“针状”形态），偏好更平衡的“碟状”形式，以利于稳定表面重建；第二，将神经符号距离函数（SDF）集成到优化过程中，通过Eikonal损失对SDF进行正则化，保持正确的距离属性，并提供连续的全局表面先验，引导高斯体更好地对齐底层几何结构。这两种正则化共同提升单个高斯基元的保真度及其整体表面行为。最终模型可从3DGS数据中生成更准确、更连贯的视觉结果。
原文摘要 · Abstract (English)
Reconstructing high-quality 3D meshes and visuals from 3D Gaussian Splatting(3DGS) still remains a central challenge in computer graphics. Although existing models such as SuGaR offer effective solutions for rendering, there is is still room to improve improve both visual fidelity and scene consistency. This work builds upon SuGaR by introducing two complementary regularization strategies that address common limitations in both the shape of individual Gaussians and the coherence of the overall surface. The first strategy introduces an effective rank regularization, motivated by recent studies on Gaussian primitive structures. This regularization discourages extreme anisotropy-specifically, "needle-like" shapes-by favoring more balanced, "disk-like" forms that are better suited for stable surface reconstruction. The second strategy integrates a neural Signed Distance Function (SDF) into the optimization process. The SDF is regularized with an Eikonal loss to maintain proper distance properties and provides a continuous global surface prior, guiding Gaussians toward better alignment with the underlying geometry. These two regularizations aim to improve both the fidelity of individual Gaussian primitives and their collective surface behavior. The final model can make more accurate and coherent visuals from 3DGS data.
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。