Research map / 3D vision / Face and shape
PSDF Fusion: Probabilistic Signed Distance Function for On-the-fly 3D Data Fusion and Scene Reconstruction
Wei Dong, Qiuyuan Wang, Xin Wang, Hongbin Zha
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 |
|---|---|---|---|
| replace TSDF weighted-average fusion with PSDF (SDF plus inlier probability) | TSDF mesh pipeline · livingroom2 (noisy) | mean distance to ground truth (m): 0.022556 -> 0.011692 | Improved |
| replace TSDF with PSDF | TSDF mesh pipeline · livingroom2 (noisy) | std of distance (m): 0.076120 -> 0.015702 | Improved |
| replace TSDF with PSDF | TSDF mesh pipeline · frei1_xyz | mesh vertex count: 352444 -> 212840 | Improved |
| replace TSDF with PSDF | TSDF mesh pipeline · lounge | mesh vertex count: 955218 -> 821360 | Improved |
| replace TSDF with PSDF | TSDF mesh pipeline · livingroom1 | mesh vertex count: 518885 -> 529305 | Hurt |
| replace TSDF with PSDF | TSDF mesh pipeline · frei1_xyz | meshing time (ms): 71.670 -> 45.163 | Improved |
| replace TSDF with PSDF | TSDF mesh pipeline · burghers | meshing time (ms): 38.907 -> 39.691 | Hurt |
| replace TSDF with PSDF | TSDF mapping stage · lounge | mapping time (ms): 0.881 -> 1.331 | Hurt |
| use truncated SDF observation in PSDF update | PSDF fusion · all scenes | reconstruction quality | Improved |
| use PSDF mesh instead of ray-casting for visualization | PSDF meshing · frei3_long_office | time (ms): 26.545 -> 159.417 | Hurt |
Closest papers by meaning
- Learning Scene-Level Signed Directional Distance Function With Ellipsoidal Priors and Neural Residuals (TPAMI 2026 · similarity 0.88)
- Sensing Surface Patches in Volume Rendering for Inferring Signed Distance Functions (AAAI 2025 · similarity 0.86)
- Details Enhancement in Unsigned Distance Field Learning for High-fidelity 3D Surface Reconstruction (AAAI 2025 · similarity 0.85)
- Neural Signed Distance Function Inference through Splatting 3D Gaussians Pulled on Zero-Level Set (NeurIPS 2024 · similarity 0.85)
- ProbeSDF: Light Field Probes For Neural Surface Reconstruction (CVPR 2025 · similarity 0.85)
- DUDF: Differentiable Unsigned Distance Fields with Hyperbolic Scaling (CVPR 2024 · similarity 0.85)
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.
