发表机构
Peking University（北京大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出 Manifold-GS，将外观不透明度与几何质量分离，导出可认证开放表面面片，在 DTU 场景上实现零编辑泄漏、高 PSNR 且碰撞浮点数面积更低，是精度与覆盖率的权衡方案。
AI 中文摘要
3D高斯溅射（3DGS）可实现高质量的新视图合成，但其自适应辐射基元无法直接作为结构化资产使用：不透明度并非可加面积度量，优化会改变诱导几何，且 watertight 网格提取可能在未观测区域生成幻觉碰撞表面。我们提出 Manifold-GS，一种用于高斯场景的可认证混合资产层，该方法将外观不透明度与几何正交质量分离，将类表面高斯表示为离散无定向变分，仅导出置信度可认证的开放表面面片，同时将未认证内容保留为残差溅射。它提供优化保守质量传输、局部可实现性诊断、源保留面片绑定和保守碰撞候选。在三个 DTU 场景上的冻结资产基准测试显示，面片定义的编辑泄漏为零，纹理往返峰值信噪比（PSNR）为 30.1/35.3/33.7 dB，且所有场景中碰撞浮点数面积均低于官方 2DGS 网格，两个场景差距显著。该结果是精度-覆盖率的权衡，而非通用重建主张。外部区域注释、幻影碰撞探测和 5k 面简化进一步支持可认证资产解释，仅 RGB 实验表明局部可实现性不足以实现稀疏视图表面可识别性。
英文摘要
3D Gaussian Splatting (3DGS) gives high-quality novel-view synthesis, but its adaptive radiance primitives are not directly usable as structured assets: opacity is not an additive area measure, refinement can change the induced geometry, and watertight mesh extraction can hallucinate collision surfaces in unobserved regions. We introduce Manifold-GS, a certified hybrid asset layer for Gaussian scenes. The method separates appearance opacity from geometric quadrature mass, represents surface-like Gaussians as a discrete unoriented varifold, and exports only confidence-certified open surface patches while retaining uncertified content as residual splats. It provides refinement-conservative mass transport, local realizability diagnostics, source-preserving patch bindings, and conservative collision candidates. On three DTU scenes, a frozen asset benchmark shows zero patch-defined edit leakage, texture round-trip PSNR of 30.1/35.3/33.7 dB, and lower collision floater area than official 2DGS meshes on all scenes, with large gaps on two scenes. The result is a precision-coverage tradeoff rather than a universal reconstruction claim. External-region annotations, phantom-collision probes, and 5k-face simplification further support the certified asset interpretation, while RGB-only experiments show that local realizability is not sufficient for sparse-view surface identifiability.
Comments9 pages, 2 figures
