SplatSuRe：面向多视图一致三维高斯泼溅的选择性超分辨率
SplatSuRe: Selective Super-Resolution for Multi-view Consistent 3D Gaussian Splatting
把相机位姿与场景几何结合，判断哪些区域缺少高频监督，只在这些欠采样区域注入超分辨率内容，从而避免逐图独立 SR 带来的多视图不一致；这一「按几何可见性选择性增强」的思路可直接迁移到 3DGS/NeRF 的高分辨率重建与训练视图增密流程。
原文依据 we propose SplatSuRe, a method that selectively applies SR content only in undersampled regions lacking high-frequency supervision
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论三维高斯泼溅（3DGS）能够实现高质量的新视角合成，这促使人们希望生成比训练时可用分辨率更高的渲染结果。一种自然的策略是对低分辨率输入视图施加超分辨率，但逐图独立增强会引入多视图不一致，导致渲染结果模糊。已有方法试图通过学习式神经组件、时序一致的视频先验，或在低分辨率与超分辨率视图上联合优化来缓解这些不一致，但它们都对每张图像统一施加超分辨率。相比之下，本文的关键洞见在于：近距离的低分辨率视图可能包含某些区域的高频信息，而这些区域同时也被更远的视图所捕获；并且我们可以利用相机相对于场景几何的位姿来判断应在何处添加超分辨率内容。基于这一洞见，我们提出 SplatSuRe，该方法仅在缺乏高频监督的欠采样区域选择性地施加超分辨率内容，从而获得更锐利、更一致的结果。在 Tanks & Temples、Deep Blending 和 Mip-NeRF 360 上，我们的方法在保真度和感知质量两方面均优于基线。值得注意的是，我们的增益在需要更高细节的局部前景区域最为显著。
英文原文摘要 1260 字符
3D Gaussian Splatting (3DGS) enables high-quality novel view synthesis, motivating interest in generating higher-resolution renders than those available during training. A natural strategy is to apply super-resolution (SR) to low-resolution (LR) input views, but independently enhancing each image introduces multi-view inconsistencies, leading to blurry renders. Prior methods attempt to mitigate these inconsistencies through learned neural components, temporally consistent video priors, or joint optimization on LR and SR views, but all uniformly apply SR across every image. In contrast, our key insight is that close-up LR views may contain high-frequency information for regions also captured in more distant views, and that we can use the camera pose relative to scene geometry to inform where to add SR content. Building from this insight, we propose SplatSuRe, a method that selectively applies SR content only in undersampled regions lacking high-frequency supervision, yielding sharper and more consistent results. Across Tanks & Temples, Deep Blending and Mip-NeRF 360, our approach surpasses baselines in both fidelity and perceptual quality. Notably, our gains are most significant in localized foreground regions where higher detail is desired.