让随意拍摄的长视频也能精准重建3D场景。
LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos
- 边重建边优化相机位姿和3D高斯，避免误差累积
- 在复杂运动下仍保持高精度位姿与高质量渲染
- 适合处理长时序、无固定轨迹的日常视频
LongSplat 解决了从随意拍摄的长视频中进行新视角合成（NVS）的关键挑战，包括不规则相机运动、未知相机位姿和大范围场景。现有方法常因位姿漂移、几何初始化不准和内存限制而失效。本文提出 LongSplat 框架，包含：(1) 增量联合优化，同时优化相机位姿与3D高斯，避免局部极小值并保证全局一致性；(2) 基于学习的3D先验的鲁棒位姿估计模块；(3) 基于空间密度的高效八叉树锚点生成机制，将稠密点云转化为锚点。在多个挑战性基准上实验表明，LongSplat 在渲染质量、位姿精度和计算效率方面均达到当前最优水平。
原文摘要 · Abstract (English)
LongSplat addresses critical challenges in novel view synthesis (NVS) from casually captured long videos characterized by irregular camera motion, unknown camera poses, and expansive scenes. Current methods often suffer from pose drift, inaccurate geometry initialization, and severe memory limitations. To address these issues, we introduce LongSplat, a robust unposed 3D Gaussian Splatting framework featuring: (1) Incremental Joint Optimization that concurrently optimizes camera poses and 3D Gaussians to avoid local minima and ensure global consistency; (2) a robust Pose Estimation Module leveraging learned 3D priors; and (3) an efficient Octree Anchor Formation mechanism that converts dense point clouds into anchors based on spatial density. Extensive experiments on challenging benchmarks demonstrate that LongSplat achieves state-of-the-art results, substantially improving rendering quality, pose accuracy, and computational efficiency compared to prior approaches. Project page: https://linjohnss.github.io/longsplat/
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。