TSPE-GS: Probabilistic Depth Extraction for Semi-Transparent Surface Reconstruction via 3D Gaussian Splatting
This addresses a specific bottleneck in 3D reconstruction for semi-transparent objects, offering an incremental improvement to existing Gaussian-based methods.
The paper tackles the problem of reconstructing semi-transparent surfaces in 3D Gaussian Splatting, which struggles with multiple visible surfaces per pixel, by proposing TSPE-GS to model multi-modal opacity and depth distributions, resulting in significant improvements in semi-transparent geometry reconstruction while maintaining performance on opaque scenes.
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.