面向稀疏视角高斯泼溅的内在几何-外观一致性优化
Intrinsic Geometry-Appearance Consistency Optimization for Sparse-View Gaussian Splatting
针对稀疏视角下 3DGS 的外观过拟合与几何欠约束问题，给出可复用的组合手段：像素级 top-k 多视图光度约束抑制遮挡干扰、边缘感知平滑保结构，以及用循环一致性深度过滤筛出可靠区域合成虚拟视角，把几何正确性注入外观优化。做稀疏视角新视角合成或 3DGS 正则化时可直接借鉴这套几何-外观耦合流程。
原文依据 cycle-consistency depth filtering, which identifies reliable regions to synthesize virtual views that propagate geometric correctness into appearance optimization
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论3D 高斯泼溅（3DGS）通过具有耦合内在属性的基元来表示场景：几何属性（位置、协方差、不透明度）与外观属性（视角相关颜色）。忠实重建需要内在的几何-外观一致性，即几何准确刻画三维结构、外观反映光度信息。然而，稀疏观测会导致外观过拟合与几何欠约束，从而产生严重的新视角伪影。我们提出 ICO-GS（面向 3DGS 的内在几何-外观一致性优化），这是一个通过紧密耦合的几何正则化与外观学习来强制实现该一致性的系统性框架。该方法首先借助基于特征的多视图光度约束对几何进行正则化，采用逐像素 top-k 选择以处理遮挡，并采用边缘感知平滑以保留锐利结构。随后通过循环一致性深度过滤将外观与几何耦合，该过滤识别出可靠区域以合成虚拟视角，从而将几何正确性传播到外观优化中。在 LLFF、DTU 和 Blender 上的实验表明，ICO-GS 持续优于现有的稀疏视角基线，在具有挑战性的弱纹理区域尤为明显。
英文原文摘要 1289 字符
3D Gaussian Splatting (3DGS) represents scenes through primitives with coupled intrinsic properties: geometric attributes (position, covariance, opacity) and appearance attributes (view-dependent color). Faithful reconstruction requires intrinsic geometry-appearance consistency, where geometry accurately captures 3D structure while appearance reflects photometry. However, sparse observations lead to appearance overfitting and underconstrained geometry, causing severe novel-view artifacts. We present ICO-GS (Intrinsic Geometry-Appearance Consistency Optimization for 3DGS), a principled framework that enforces this consistency through tightly coupled geometric regularization and appearance learning. Our approach first regularizes geometry via feature-based multi-view photometric constraints by employing pixel-wise top-k selection to handle occlusions and edge-aware smoothness to preserve sharp structures. Then appearance is coupled with geometry through cycle-consistency depth filtering, which identifies reliable regions to synthesize virtual views that propagate geometric correctness into appearance optimization. Experiments on LLFF, DTU, and Blender show ICO-GS consistently outperforms existing sparse-view baselines, particularly in challenging weakly-textured regions.