鲁棒且高保真的3D高斯泼溅：融合位姿先验与几何约束以处理纹理匮乏的户外场景
Robust and High-Fidelity 3D Gaussian Splatting: Fusing Pose Priors and Geometry Constraints for Texture-Deficient Outdoor Scenes
AI总结：
针对纹理匮乏户外场景中3DGS位姿不稳定和表示失真的问题，本文融合LiDAR-IMU先验位姿与法向量及有效秩几何约束，在保证精度的同时将位姿优化时间缩短至三分之一，并显著提升场景表示质量。
摘要：
3D高斯泼溅（3DGS）因其在效率与视觉质量之间的良好平衡，已成为数字资产创建中的关键渲染管线。针对大型户外场景中因弱纹理或重复纹理导致的几何纹理不一致，进而引发位姿估计不稳定和场景表示失真的问题，我们从位姿估计和场景表示两个方面入手。在位姿估计方面，我们利用LiDAR-IMU里程计为大规模环境中的相机提供先验位姿。这些先验位姿约束被纳入COLMAP的三角化过程中，并通过光束法平差进行位姿优化。确保像素数据关联与先验位姿之间的一致性，有助于同时保持鲁棒性和准确性。在场景表示方面，我们引入法向量约束和有效秩正则化，以强制高斯原语在方向和形状上保持一致。这些约束与现有的光度损失联合优化，以提升地图质量。我们使用公开数据集和自采数据集对方法进行评估。在位姿优化方面，我们的方法仅需三分之一的时间，同时在两个数据集上保持了准确性和鲁棒性。在场景表示方面，结果表明我们的方法显著优于传统3DGS管线。值得注意的是，在具有弱纹理或重复纹理特征的自采数据集上，我们的方法展现出增强的可视化能力，并取得了更优的整体性能。代码和数据将在 https://github.com/justinyeah/normal_shape.git 公开发布。
英文摘要：
3D Gaussian Splatting (3DGS) has emerged as a key rendering pipeline for digital asset creation due to its balance between efficiency and visual quality. To address the issues of unstable pose estimation and scene representation distortion caused by geometric texture inconsistency in large outdoor scenes with weak or repetitive textures, we approach the problem from two aspects: pose estimation and scene representation. For pose estimation, we leverage LiDAR-IMU Odometry to provide prior poses for cameras in large-scale environments. These prior pose constraints are incorporated into COLMAP's triangulation process, with pose optimization performed via bundle adjustment. Ensuring consistency between pixel data association and prior poses helps maintain both robustness and accuracy. For scene representation, we introduce normal vector constraints and effective rank regularization to enforce consistency in the direction and shape of Gaussian primitives. These constraints are jointly optimized with the existing photometric loss to enhance the map quality. We evaluate our approach using both public and self-collected datasets. In terms of pose optimization, our method requires only one-third of the time while maintaining accuracy and robustness across both datasets. In terms of scene representation, the results show that our method significantly outperforms conventional 3DGS pipelines. Notably, on self-collected datasets characterized by weak or repetitive textures, our approach demonstrates enhanced visualization capabilities and achieves superior overall performance. Codes and data will be publicly available at https://github.com/justinyeah/normal_shape.git.
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。
