发表机构
Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences; University of Chinese Academy of Sciences; Chinese Academy of Sciences（中国科学院长春光学精密机械与物理研究所; 中国科学院大学; 中国科学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出LVS框架，通过相对位姿引导复用先前视图替代重复场景渲染，结合几何变形与轻量多尺度网络，在GS-render上使PSNR提升0.72分贝，可实现低延迟的交互式场景探索，适用于AR/VR。
AI 中文摘要
交互式场景探索需要频繁的视图更新，尽管微小的相机运动能保留大部分可见内容。然而，传统的3D高斯溅射（3D Gaussian Splatting）仍会渲染每个目标视图，未利用这种图像重叠。复用渲染图像是一种替代方案，但仅几何变形无法恢复新暴露的内容，且对深度误差敏感。我们提出一种针对每个场景的框架，用相对位姿引导的RGB-D图像复用替代对邻近视图的重复场景渲染：几何变形利用深度和相对位姿传输源内容，轻量多尺度网络预测RGB残差以校正伪影并推断缺失外观，缓存的源特征进一步减少重复计算。在GS-render数据集上，残差细化相比纯变形将峰值信噪比（PSNR）提升了0.72分贝；对真实捕获和渲染场景的评估显示其查询延迟较低。这种将场景渲染与局部视图更新分离的方式支持响应式场景探索，在增强现实和虚拟现实领域具有潜在应用。
英文摘要
Interactive scene exploration requires frequent view updates, although small camera motions preserve much of the visible content. Conventional 3D Gaussian Splatting nevertheless renders each target view, leaving this image overlap unexploited. Reusing rendered images offers an alternative. Geometric warping alone cannot recover newly exposed content and remains sensitive to depth errors. We propose a per-scene framework that replaces repeated scene rendering for nearby views with relative-pose-guided RGB-D image reuse. Geometric warping uses depth and relative pose to transport source content, while a lightweight multiscale network predicts RGB residuals to correct artifacts and infer missing appearance. Cached source features further reduce repeated computation. On GS-render, residual refinement improves PSNR by 0.72~dB over pure warping; evaluations on captured and rendered scenes demonstrate low query latency. This separation of scene rendering from local view updates supports responsive scene exploration, with potential applications in augmented and virtual reality.
