LongSplat：面向日常长视频的鲁棒无姿态3D高斯溅射技术

LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos

August 19, 2025

作者: Chin-Yang Lin, Cheng Sun, Fu-En Yang, Min-Hung Chen, Yen-Yu Lin, Yu-Lun Liu

cs.AI

摘要

LongSplat针对从非专业拍摄的长视频中进行新颖视角合成（NVS）所面临的关键挑战，这些视频通常具有不规则的相机运动、未知的相机姿态以及广阔的场景。现有方法常受困于姿态漂移、几何初始化不准确及严重的内存限制。为解决这些问题，我们提出了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，同步优化相机姿态与3D高斯分布，避免局部最优并确保全局一致性；（2）基于学习到的3D先验的鲁棒姿态估计模块；（3）高效的八叉树锚点生成机制，依据空间密度将稠密点云转化为锚点。在多个具有挑战性的基准测试上的广泛实验表明，LongSplat实现了业界领先的结果，在渲染质量、姿态精度及计算效率方面较之前方法均有显著提升。项目页面：https://linjohnss.github.io/longsplat/

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/