Research map / 3D vision / Gaussian splatting
Hermite Radial Basis Function for Surface Reconstruction via Differentiable Rendering
Hugo Blanc, Jean-Emmanuel Deschaud, Alexis Paljic
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 |
|---|---|---|---|
| use Objects as Volumes density instead of NeuS density (ablation) | HRBF implicit field · BlendedMVS | mean Chamfer distance: 0.55 -> 0.52 | Improved |
| use Gaussian RBF instead of Wendland C2 (ablation) | HRBF implicit field · BlendedMVS | mean Chamfer distance: 0.58 -> 0.52 | Improved |
| use positive constant polynomial offset p0 (0.5) instead of p0 = 0 (ablation) | HRBF implicit field · BlendedMVS | mean Chamfer distance | Improved |
| HRBF implicit field vs PGSR / Fast Dipole Sums | HRBF implicit field · DTU (15 scenes) | mean Chamfer distance: 0.58 -> 0.54 | Improved |
| HRBF implicit field vs Fast Dipole Sums | HRBF implicit field · BlendedMVS | mean Chamfer distance: 0.65 -> 0.52 | Improved |
| HRBF implicit field vs Fast Dipole Sums | HRBF implicit field · BlendedMVS | training time (min): 45 -> 15 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.
- NeuS2 — NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstruction (ICCV 2023) · better on 2 of 4 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
- Differentiable Inverse Rendering with Interpretable Basis BRDFs (CVPR 2025 · similarity 0.87)
- ProbeSDF: Light Field Probes For Neural Surface Reconstruction (CVPR 2025 · similarity 0.86)
- GVKF: Gaussian Voxel Kernel Functions for Highly Efficient Surface Reconstruction in Open Scenes (NeurIPS 2024 · similarity 0.86)
- DySurface: Consistent 4D Surface Reconstruction via Bridging Explicit Gaussians and Implicit Functions (NeurIPS 2026 · similarity 0.86)
- HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis (NeurIPS 2025 · similarity 0.85)
- GaussianUDF: Inferring Unsigned Distance Functions through 3D Gaussian Splatting (CVPR 2025 · 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.
