解决3D高斯点阵在半透明表面重建中的深度模糊问题
TSPE-GS: Probabilistic Depth Extraction for Semi-Transparent Surface Reconstruction via 3D Gaussian Splatting
- 通过均匀采样透光率，建模像素级多模态深度与不透明度分布
- 在统一框架内分别重建内外表面，提升半透明物体几何精度
- 无需额外训练，可适配其他高斯重建流程，适合复杂材质建模
3D高斯点阵在速度与质量间表现优异，但难以重建半透明表面，因多数方法假设每像素仅有一个深度，无法处理多重可见表面。本文提出TSPE-GS（基于高斯点阵的半透明表面概率提取），通过均匀采样透光率，建模像素级多模态不透明度与深度分布，取代原有单峰假设，解决跨表面深度歧义。通过逐步融合截断有符号距离函数，TSPE-GS在统一框架内分别重建外部与内部表面。该方法可泛化至其他基于高斯的重建流程，无需额外训练开销。在公开及自采集的半透明与不透明数据集上的大量实验表明，TSPE-GS显著提升半透明几何重建效果，同时保持对不透明场景的性能。
原文摘要 · Abstract (English)
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 ambiguity. By progressively fusing truncated signed distance functions, TSPE-GS reconstructs external and internal surfaces separately within a unified framework. The method generalizes to other Gaussian-based reconstruction pipelines without extra training overhead. Extensive experiments on public and self-collected semi-transparent and opaque datasets show TSPE-GS significantly improves semi-transparent geometry reconstruction while maintaining performance on opaque scenes.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。