LongSplat：面向随意拍摄长视频的鲁棒无姿态3D高斯溅射
LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos
AI总结：
针对随意拍摄长视频新视角合成中姿态漂移、几何初始化不准和内存限制问题，提出LongSplat框架，通过增量联合优化、鲁棒姿态估计模块和八叉树锚点机制提升渲染质量、姿态精度与计算效率。
摘要：
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，这类视频具有不规则相机运动、未知相机姿态和广阔场景的特点。现有方法常受姿态漂移、几何初始化不准确和严重内存限制的困扰。为解决这些问题，我们提出LongSplat——一个鲁棒的无姿态3D高斯溅射框架，其特点包括：（1）增量联合优化，同时优化相机姿态和3D高斯以避免局部最小值并确保全局一致性；（2）利用学习到的3D先验的鲁棒姿态估计模块；（3）基于空间密度将密集点云转换为锚点的高效八叉树锚点形成机制。在具有挑战性的基准测试上的大量实验表明，LongSplat取得了最先进的结果，与先前方法相比，在渲染质量、姿态精度和计算效率方面有显著提升。项目页面：https://linjohnss.github.io/longsplat/
英文摘要：
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/
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
