SurfelSplat: 学习高效且可泛化的高斯Surfel表示以进行稀疏视图表面重建
SurfelSplat: Learning Efficient and Generalizable Gaussian Surfel Representations for Sparse-View Surface Reconstruction
AI总结：
本文提出SurfelSplat框架，通过稀疏视图图像生成高效且可泛化的高斯Surfel表示，利用Nyquist采样定理解决传统方法在几何属性恢复中的不足，实验表明其在DTU基准上表现优异且速度提升显著。
摘要：
3D高斯散射（3DGS）在3D场景重建中表现出色。除了新视图合成外，它在多视图表面重建中也具有巨大潜力。现有方法采用基于优化的重建流程，实现精确且完整的表面提取。然而，这些方法通常需要密集输入视图和高时间消耗的每场景优化。为了解决这些限制，我们提出SurfelSplat，一种前馈框架，从稀疏视图图像中生成高效且可泛化的像素对齐高斯Surfel表示。我们观察到传统前馈结构难以恢复高斯Surfel的准确几何属性，因为像素对齐原语的空间频率超过奈奎斯特采样率。因此，我们提出基于奈奎斯特采样定理的跨视图特征聚合模块。具体而言，我们首先使用空间采样率引导的低通滤波器调整高斯Surfel的几何形式。然后，我们将过滤后的Surfel投影到所有输入视图以获得跨视图特征相关性。通过处理这些相关性通过专门设计的特征融合网络，我们最终可以回归具有精确几何的高斯Surfel。在DTU重建基准上的广泛实验表明，我们的模型在与最先进方法相当的性能下，预测高斯Surfel在1秒内完成，提供100倍的速度提升，而无需昂贵的每场景训练。
英文摘要：
3D Gaussian Splatting (3DGS) has demonstrated impressive performance in 3D scene reconstruction. Beyond novel view synthesis, it shows great potential for multi-view surface reconstruction. Existing methods employ optimization-based reconstruction pipelines that achieve precise and complete surface extractions. However, these approaches typically require dense input views and high time consumption for per-scene optimization. To address these limitations, we propose SurfelSplat, a feed-forward framework that generates efficient and generalizable pixel-aligned Gaussian surfel representations from sparse-view images. We observe that conventional feed-forward structures struggle to recover accurate geometric attributes of Gaussian surfels because the spatial frequency of pixel-aligned primitives exceeds Nyquist sampling rates. Therefore, we propose a cross-view feature aggregation module based on the Nyquist sampling theorem. Specifically, we first adapt the geometric forms of Gaussian surfels with spatial sampling rate-guided low-pass filters. We then project the filtered surfels across all input views to obtain cross-view feature correlations. By processing these correlations through a specially designed feature fusion network, we can finally regress Gaussian surfels with precise geometry. Extensive experiments on DTU reconstruction benchmarks demonstrate that our model achieves comparable results with state-of-the-art methods, and predict Gaussian surfels within 1 second, offering a 100x speedup without costly per-scene training.
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。
