{"ID":2842050,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.09944","arxiv_id":"2511.09944","title":"TSPE-GS: Probabilistic Depth Extraction for Semi-Transparent Surface Reconstruction via 3D Gaussian Splatting","abstract":"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.","short_abstract":"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 unifo...","url_abs":"https://arxiv.org/abs/2511.09944","url_pdf":"https://arxiv.org/pdf/2511.09944v1","authors":"[\"Zhiyuan Xu\",\"Nan Min\",\"Yuhang Guo\",\"Tong Wei\"]","published":"2025-11-13T04:18:59Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}