2Xplat：两个专家胜过一个通才
2Xplat: Decoupling Geometry and Appearance Modeling for Feed-Forward 3D Gaussian Splatting
- Yonsei University（延世大学）
- Sungkyunkwan University（成均馆大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出2Xplat框架，通过分离几何估计与高斯生成，改进3DGS生成效果，证明模块化设计在复杂3D建模中的优势。
AI中文摘要：
无需姿态信息的前馈3D高斯散射（3DGS）方法开创了快速3D建模的新前沿，使高质量的高斯表示能够从未经校准的多视角图像中在单次前向传递中生成。该领域主导的方法采用统一的单体架构，通常基于以几何为中心的3D基础模型，以单个网络内联合估计相机姿态和合成3DGS表示。虽然架构简洁，但此类“一体化”设计可能在高保真3DGS生成中效果欠佳，因为它们将几何推理和外观建模嵌入共享的表示中。在本文中，我们引入了2Xplat，一种基于双专家设计的无姿态前馈3DGS框架，明确将几何估计与高斯生成分离。一个专门的几何专家首先预测相机姿态，这些姿态随后被显式传递给一个强大的外观专家，以合成3D高斯。尽管其概念简单，但此前研究中鲜有探索，所提出的方法证明了其高度有效性。在少于5000次训练迭代中，所提出的双专家流程显著优于之前的无姿态前馈3DGS方法，并实现了与最新姿态方法相当的性能。这些结果挑战了主流统一范式，并表明模块化设计原则在复杂3D几何估计和外观合成任务中的潜在优势。
英文摘要：
Pose-free feed-forward 3D Gaussian Splatting (3DGS) has opened a new frontier for rapid 3D modeling, enabling high-quality Gaussian representations to be generated from uncalibrated multi-view images in a single forward pass. The dominant approach adopts unified monolithic architectures, often built on geometry-centric 3D foundation models, to jointly estimate camera poses and synthesize 3DGS representations within a single network, entangling geometric reasoning and appearance modeling within a shared representation. In this work, we introduce 2Xplat, a pose-free feed-forward 3DGS framework based on a two-experts design that explicitly separates geometry estimation from Gaussian generation: a dedicated geometry expert first predicts camera poses, which are then passed to an appearance expert that synthesizes 3D Gaussians. Despite its conceptual simplicity, and being largely underexplored in prior works, our two-experts pipeline outperforms prior pose-free feed-forward 3DGS approaches in fewer than 5K training iterations, achieving performance on par with state-of-the-art posed methods. These results challenge the prevailing unified paradigm and suggest the potential advantages of modular design for complex 3D geometric estimation and appearance synthesis tasks.
