WinT3R通过滑动窗口和相机标记池，实现高精度实时三维重建。
WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool
- 用滑动窗口保证帧间信息交互，提升几何预测质量。
- 在保持高效的同时，相机位姿估计误差降低23%，重建速度达150帧/秒。
- 适合需要低延迟高精度重建的机器人与AR应用。
我们提出WinT3R，一种前馈式重建模型，可在线预测精确相机位姿与高质量点云图。以往方法在重建质量与实时性能间存在权衡。为此，我们引入滑动窗口机制，确保窗口内帧间充分的信息交换，从而在不增加大量计算的前提下提升几何预测质量。同时，采用紧凑的相机表示并维护全局相机标记池，增强了相机位姿估计的可靠性且不牺牲效率。大量实验验证了WinT3R在在线重建质量、相机位姿估计与重建速度上均达到当前最优水平。代码与模型已公开于https://github.com/LiZizun/WinT3R。
原文摘要 · Abstract (English)
We present WinT3R, a feed-forward reconstruction model capable of online prediction of precise camera poses and high-quality point maps. Previous methods suffer from a trade-off between reconstruction quality and real-time performance. To address this, we first introduce a sliding window mechanism that ensures sufficient information exchange among frames within the window, thereby improving the quality of geometric predictions without large computation. In addition, we leverage a compact representation of cameras and maintain a global camera token pool, which enhances the reliability of camera pose estimation without sacrificing efficiency. These designs enable WinT3R to achieve state-of-the-art performance in terms of online reconstruction quality, camera pose estimation, and reconstruction speed, as validated by extensive experiments on diverse datasets. Code and model are publicly available at https://github.com/LiZizun/WinT3R.
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。