TSPE-GS: Probabilistic Depth Extraction for Semi-Transparent Surface Reconstruction via 3D Gaussian Splatting
By: Zhiyuan Xu , Nan Min , Yuhang Guo and more
Potential Business Impact:
Creates realistic 3D models of see-through objects.
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.
Similar Papers
TSGS: Improving Gaussian Splatting for Transparent Surface Reconstruction via Normal and De-lighting Priors
CV and Pattern Recognition
Makes computers see clear objects accurately.
Moment-Based 3D Gaussian Splatting: Resolving Volumetric Occlusion with Order-Independent Transmittance
CV and Pattern Recognition
Renders see-through objects perfectly, no matter how they overlap.
DET-GS: Depth- and Edge-Aware Regularization for High-Fidelity 3D Gaussian Splatting
CV and Pattern Recognition
Makes 3D pictures look real from few photos.