通过智能选择区域提升3D高斯点云的分辨率，解决多视角不一致问题。
SplatSuRe: Selective Super-Resolution for Multi-view Consistent 3D Gaussian Splatting
- 基于相机位姿与场景几何关系，仅在欠采样区域应用超分
- 在Tanks & Temples等数据集上显著提升细节清晰度和视觉质量
- 特别适合需要局部高细节的前景区域渲染，如物体主体
3D高斯点云（3DGS）实现了高质量的新视角合成，激发了对生成比训练时更高分辨率图像的兴趣。一种自然策略是将超分辨率（SR）应用于低分辨率（LR）输入视图，但独立增强每张图像会引入多视角不一致性，导致画面模糊。现有方法通过学习神经组件、时间一致视频先验或联合优化LR与SR视图来缓解该问题，但均对所有图像统一应用超分。本文提出关键洞察：近距离的低分辨率视图可能包含远距离视图也覆盖区域的高频信息，可利用相机位姿相对于场景几何的关系判断是否添加超分内容。基于此，我们提出SplatSuRe，仅在缺乏高频监督的欠采样区域选择性地添加超分内容，从而获得更锐利且一致的结果。在Tanks & Temples、Deep Blending和Mip-NeRF 360数据集上，本方法在保真度和感知质量上均优于基线，尤其在需要高细节的局部前景区域表现突出。
原文摘要 · Abstract (English)
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 on 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.
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。