arXiv cs.AI· Qizhou Huo, Xuan Sun, Yongfei Guo, Zhipeng Wang, Yuanhao Gong·· 9 天前AI 评分24
LVS：通过复用先前视图从相对相机位姿实现局部视图合成
LVS: Local View Synthesis from Relative Camera Pose by Reusing Previous Views
AI 导读
针对 3D Gaussian Splatting 对每个目标视图重复渲染、未利用相邻视图图像重叠的问题，研究者提出 LVS 框架，用相对位姿引导的 RGB-D 图像复用替代邻近视图的重复场景渲染。
正文 · 原文
Abstract: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.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Graphics (cs.GR); Multimedia (cs.MM); Image and Video Processing (eess.IV) |
| Cite as: | arXiv:2610.12127 [cs.CV] |
| (or arXiv:2610.12127v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.12127 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yuanhao Gong [view email]
[v1]
Thu, 8 Oct 2026 15:19:58 UTC (4,505 KB)
来源：arXiv cs.AI · arxiv.org