Research map / 3D vision / Depth and stereo
HelixSurf: A Robust and Efficient Neural Implicit Surface Learning of Indoor Scenes With Iterative Intertwined Regularization
Zhihao Liang, Zhangjin Huang, Changxing Ding, Kui Jia
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 |
|---|---|---|---|
| Combine iterative MVS and neural implicit surface regularization (ablation) | HelixSurf · ScanNet | F-score: 0.291 -> 0.755 | Improved |
| Add ordinary MVS regularization (ablation) | Neural implicit surface learning · ScanNet | F-score: 0.291 -> 0.632 | Improved |
| Use neural-surface predictions to regularize MVS (ablation) | HelixSurf · ScanNet | F-score: 0.632 -> 0.679 | Improved |
| Add textureless-area handling using superpixel normal smoothness (ablation) | HelixSurf with ordinary MVS regularization · ScanNet | F-score: 0.632 -> 0.735 | Improved |
| Add textureless-area handling (ablation) | HelixSurf with regularized MVS · ScanNet | F-score: 0.679 -> 0.755 | Improved |
| Use neural implicit surface predictions as priors for MVS (ablation) | MVS · ScanNet | Abs Diff: 0.067 -> 0.053 | Improved |
| Use neural implicit surface predictions as priors for MVS (ablation) | MVS · ScanNet | Mean normal error: 35.5$^{\circ}$ -> 27.8$^{\circ}$ | Improved |
| Guide ray sampling with dynamic occupancy grids (ablation) | HelixSurf · ScanNet | training time (minutes): 393.4 -> 33.2 | Improved |
| Use HelixSurf instead of MonoSDF | ScanNet reconstruction · ScanNet | F-score: 0.733 -> 0.755 | Improved |
Later papers that compared with this method
4 later accepted papers report HelixSurf as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.
- DebSDF: Delving Into the Details and Bias of Neural Indoor Scene Reconstruction (TPAMI 2024 · better on 2 of 2 shared results)
- NC-SDF: Enhancing Indoor Scene Reconstruction Using Neural SDFs with View-Dependent Normal Compensation (CVPR 2024 · better on 1 of 1 shared result)
- H2O-SDF: Two-phase Learning for 3D Indoor Reconstruction using Object Surface Fields (ICLR 2024 · better on 1 of 1 shared result)
- Ray-Distance Volume Rendering for Neural Scene Reconstruction (ECCV 2024 · 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
- DebSDF: Delving Into the Details and Bias of Neural Indoor Scene Reconstruction (TPAMI 2024 · similarity 0.90)
- Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstruction (NeurIPS 2022 · similarity 0.89)
- ND-SDF: Learning Normal Deflection Fields for High-Fidelity Indoor Reconstruction (ICLR 2025 · similarity 0.88)
- NeAT: Learning Neural Implicit Surfaces With Arbitrary Topologies From Multi-View Images (CVPR 2023 · similarity 0.88)
- NC-SDF: Enhancing Indoor Scene Reconstruction Using Neural SDFs with View-Dependent Normal Compensation (CVPR 2024 · similarity 0.87)
- Sparis: Neural Implicit Surface Reconstruction of Indoor Scenes from Sparse Views (AAAI 2025 · similarity 0.87)
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.
