Research map / 3D vision / Face and shape
HF-NeuS: Improved Surface Reconstruction Using High-Frequency Details
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 high-frequency positional encoding directly (ablation) | NeuS · NeRF-synthetic | Chamfer distance (1e-2): 2.51 -> 3.61 | Hurt |
| add high-frequency positional encoding directly (ablation) | NeuS · BlendedMVS | Chamfer distance: 0.43 -> fail | Hurt |
| add high-frequency positional encoding directly (ablation) | NeuS · DTU | PSNR: 31.77 -> 32.73 | Helped |
| add coarse-to-fine positional encoding (Base+C2F vs Base+H) (ablation) | NeuS · BlendedMVS | Chamfer distance: fail -> 0.63 | Helped |
| coarse-to-fine alone (ablation) | NeuS · NeRF-synthetic | Chamfer distance (1e-2): 2.51 -> 2.95 | Hurt |
| add implicit displacement function to coarse-to-fine (IDF+C2F vs Base+C2F) (ablation) | NeuS · NeRF-synthetic | Chamfer distance (1e-2): 2.95 -> 1.35 | Helped |
| add position-adaptive s / adaptive transparency (FULL vs IDF+C2F) (ablation) | HF-NeuS · NeRF-synthetic | Chamfer distance (1e-2): 1.35 -> 0.91 | Helped |
| add position-adaptive s (FULL vs IDF+C2F) (ablation) | HF-NeuS · DTU | Chamfer distance: 0.89 -> 0.78 | Helped |
| add position-adaptive s (FULL vs IDF+C2F) (ablation) | HF-NeuS · DTU | PSNR: 32.13 -> 32.49 | Helped |
| full HF-NeuS vs NeuS baseline (ablation) | NeuS · BlendedMVS | Chamfer distance: 0.43 -> 0.38 | Helped |
| use HF-NeuS instead of NeuS | NeuS · NeRF-synthetic | PSNR: 28.05 -> 28.66 | Mixed |
| remove Eikonal regularization on the base SDF (ablation) | HF-NeuS · qualitative | reconstruction quality | Hurt |
Closest papers by meaning
- NeuRodin: A Two-stage Framework for High-Fidelity Neural Surface Reconstruction (NeurIPS 2024 · similarity 0.90)
- Sharpening Neural Implicit Functions with Frequency Consolidation Priors (AAAI 2025 · similarity 0.89)
- SC-NeuS: Consistent Neural Surface Reconstruction from Sparse and Noisy Views (AAAI 2024 · similarity 0.89)
- Neural Signed Distance Function Inference through Splatting 3D Gaussians Pulled on Zero-Level Set (NeurIPS 2024 · similarity 0.89)
- NeuSurf: On-Surface Priors for Neural Surface Reconstruction from Sparse Input Views (AAAI 2024 · similarity 0.89)
- From Transparent to Opaque: Rethinking Neural Implicit Surfaces with $\alpha$-NeuS (NeurIPS 2024 · similarity 0.89)
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.