Research map / 3D vision / Gaussian splatting
TSPE-GS: Probabilistic Depth Extraction for Semi-Transparent Surface Reconstruction via 3D Gaussian Splatting
Zhiyuan Xu, Min Nan, Yuhang Guo, Tong Wei
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add TSPE depth extraction | RaDeGS · αSurf | Chamfer distance: 0.97 -> 0.82 | Improved |
| add TSPE depth extraction | 2DGS · αSurf | Chamfer distance: 2.06 -> 1.08 | Improved |
| add TSPE depth extraction | RaDeGS · Bottleship | Chamfer distance: 1.71 -> 0.88 | Improved |
| add TSPE depth extraction | RaDeGS · BlendedMVS | Chamfer distance: 0.81 -> 0.81 | No clear effect |
| add TSPE depth extraction | 2DGS · BlendedMVS | Chamfer distance: 1.48 -> 0.89 | Improved |
| vary peak threshold coefficient (ablation) | TSPE-GS · αSurf and opaque scenes | Chamfer distance | No clear effect |
| apply TSPE to a base method that fits geometry poorly (2DGS on bottleship) | 2DGS · Bottleship | Chamfer distance | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- NeuS — NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction (NeurIPS 2021) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- TranSplat: Generalizable 3D Gaussian Splatting from Sparse Multi-View Images with Transformers (AAAI 2025 · similarity 0.89)
- FatesGS: Fast and Accurate Sparse-View Surface Reconstruction Using Gaussian Splatting with Depth-Feature Consistency (AAAI 2025 · similarity 0.89)
- AtlasGS: Atlanta-world Guided Surface Reconstruction with Implicit Structured Gaussians (NeurIPS 2025 · similarity 0.88)
- VA-GS: Enhancing the Geometric Representation of Gaussian Splatting via View Alignment (NeurIPS 2025 · similarity 0.88)
- Sparse2DGS: Geometry-Prioritized Gaussian Splatting for Surface Reconstruction from Sparse Views (CVPR 2025 · similarity 0.88)
- Evolving High-Quality Rendering and Reconstruction in a Unified Framework with Contribution-Adaptive Regularization (CVPR 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
