无COLMAP的3D Gaussian Splatting
COLMAP-Free 3D Gaussian Splatting
AI总结：
本文提出一种无需SfM预处理的3D Gaussian Splatting方法，利用显式几何表示与视频流连续性，顺序处理输入帧并逐步扩展3D高斯集合，在大幅运动变化下显著提升了新视角合成与相机位姿估计性能。
摘要：
尽管神经渲染在场景重建和新视角合成方面取得了令人瞩目的进展，但它严重依赖于准确预计算的相机位姿。为了放宽这一约束，已有许多研究致力于在不预处理相机位姿的情况下训练Neural Radiance Fields (NeRFs)。然而，NeRFs的隐式表示为同时优化3D结构和相机位姿带来了额外的挑战。另一方面，最近提出的3D Gaussian Splatting因其显式的点云表示提供了新的机遇。本文结合显式的几何表示与输入视频流的连续性，在无需任何SfM预处理的情况下进行新视角合成。我们以顺序方式处理输入帧，每次取一帧输入图像来逐步扩展3D Gaussians集合，无需预计算相机位姿。在运动变化较大的情况下，我们的方法在新视角合成和相机位姿估计方面显著优于以往方法。项目主页为https://oasisyang.github.io/colmap-free-3dgs
英文摘要：
While neural rendering has led to impressive advances in scene reconstruction and novel view synthesis, it relies heavily on accurately pre-computed camera poses. To relax this constraint, multiple efforts have been made to train Neural Radiance Fields (NeRFs) without pre-processed camera poses. However, the implicit representations of NeRFs provide extra challenges to optimize the 3D structure and camera poses at the same time. On the other hand, the recently proposed 3D Gaussian Splatting provides new opportunities given its explicit point cloud representations. This paper leverages both the explicit geometric representation and the continuity of the input video stream to perform novel view synthesis without any SfM preprocessing. We process the input frames in a sequential manner and progressively grow the 3D Gaussians set by taking one input frame at a time, without the need to pre-compute the camera poses. Our method significantly improves over previous approaches in view synthesis and camera pose estimation under large motion changes. Our project page is https://oasisyang.github.io/colmap-free-3dgs
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。
