TSPE-GS: Probabilistic Depth Extraction for Semi-Transparent Surface Reconstruction via 3D Gaussian Splatting
Zhiyuan Xu, Nan Min, Yuhang Guo, Tong Wei
3D高斯电镀提供了强大的速度质量权衡,但难以重建半透明表面,因为大多数方法假设每个像素的单个深度,当多个表面可见时就会失败。 我们提出了TSPE-GS(用于高斯飞溅的透明表面概率提取),它均匀地采样透射率,以模拟像素的不透明度和深度的多模态分布,取代先前的单峰假设并解决跨表面深度模糊。 通过逐步融合截断的签名距离功能,TSPE-GS在统一框架内单独重建外部和内部表面。 该方法将其扩展到其他基于高斯的重建管道,而无需额外的训练开销。 对公共和自收集的半透明且不透明数据集进行的广泛实验表明,TSPE-GS显著改善了半透明几何重建,同时保持不透明场景的性能。
3D Gaussian Splatting offers a strong speed-quality trade-off but struggles to reconstruct semi-transparent surfaces because most methods assume a single depth per pixel, which fails when multiple surfaces are visible. We propose TSPE-GS (Transparent Surface Probabilistic Extraction for Gaussian Splatting), which uniformly samples transmittance to model a pixel-wise multi-modal distribution of opacity and depth, replacing the prior single-peak assumption and resolving cross-surface depth ambigui...