RegGS：基于3DGS配准的无位姿稀疏视图高斯溅射
RegGS: Unposed Sparse Views Gaussian Splatting with 3DGS Registration
AI总结：
RegGS提出基于3D高斯配准的无位姿稀疏视图重建框架，通过熵正则化Sinkhorn求解MW₂距离并结合光度与深度约束，实现局部高斯到全局一致表示的精确对齐。
摘要：
3D高斯溅射（3DGS）已展现出从无位姿图像重建场景的潜力。然而，基于优化的3DGS方法由于先验知识有限，在稀疏视图下表现不佳。同时，前馈高斯方法受输入格式限制，难以融入更多输入视图。为解决这些挑战，我们提出RegGS，一个基于3D高斯配准的框架，用于重建无位姿稀疏视图。RegGS将前馈网络生成的局部3D高斯对齐到全局一致的3D高斯表示中。技术上，我们实现了熵正则化Sinkhorn算法，以高效求解最优传输混合2-Wasserstein（MW₂）距离，该距离作为Sim(3)空间中高斯混合模型（GMMs）的对齐度量。此外，我们设计了一个联合3DGS配准模块，整合了MW₂距离、光度一致性和深度几何。这使得配准过程能够由粗到细进行，同时准确估计相机位姿并对齐场景。在RE10K和ACID数据集上的实验表明，RegGS能够以高保真度有效配准局部高斯，实现精确的位姿估计和高质量的新视角合成。项目页面：https://3dagentworld.github.io/reggs/。
英文摘要：
3D Gaussian Splatting (3DGS) has demonstrated its potential in reconstructing scenes from unposed images. However, optimization-based 3DGS methods struggle with sparse views due to limited prior knowledge. Meanwhile, feed-forward Gaussian approaches are constrained by input formats, making it challenging to incorporate more input views. To address these challenges, we propose RegGS, a 3D Gaussian registration-based framework for reconstructing unposed sparse views. RegGS aligns local 3D Gaussians generated by a feed-forward network into a globally consistent 3D Gaussian representation. Technically, we implement an entropy-regularized Sinkhorn algorithm to efficiently solve the optimal transport Mixture 2-Wasserstein $(\text{MW}_2)$ distance, which serves as an alignment metric for Gaussian mixture models (GMMs) in $\mathrm{Sim}(3)$ space. Furthermore, we design a joint 3DGS registration module that integrates the $\text{MW}_2$ distance, photometric consistency, and depth geometry. This enables a coarse-to-fine registration process while accurately estimating camera poses and aligning the scene. Experiments on the RE10K and ACID datasets demonstrate that RegGS effectively registers local Gaussians with high fidelity, achieving precise pose estimation and high-quality novel-view synthesis. Project page: https://3dagentworld.github.io/reggs/.
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。
