Research map / 3D vision / Face and shape
HiNeuS: High-fidelity Neural Surface Mitigating Low-texture and Reflective Ambiguity
Yida Wang, Xueyang Zhang, Kun Zhan, Peng Jia, Xianpeng Lang
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 rendering-prioritized Eikonal weighting omega(x) (ablation) | HiNeuS · NeRF-Synthetic | PSNR (dB): 32.94 -> 35.00 | Improved |
| add rendering-prioritized Eikonal weighting omega(x) (ablation) | HiNeuS · Mip-NeRF 360 | PSNR (dB): 28.20 -> 29.50 | Improved |
| add rendering-prioritized Eikonal weighting omega(x) (ablation) | HiNeuS · DTU | Chamfer distance (mm): 0.61 -> 0.43 | Improved |
| add ambiguity factor (ablation) | HiNeuS · GlossySynthetic | Chamfer distance (mm): 0.0044 -> 0.0038 | Improved |
| add ambiguity weighting (ablation) | HiNeuS · Mip-NeRF 360 | PSNR (dB): 28.08 -> 29.50 | Improved |
| add ambiguity weighting (ablation) | HiNeuS · DTU | Chamfer distance (mm): 0.63 -> 0.43 | Improved |
| add reflection compensation (ablation) | HiNeuS · GlossySynthetic | Chamfer distance (mm): 0.0041 -> 0.0038 | Improved |
| use SDF visibility instead of mesh-based visibility (ablation) | HiNeuS · GlossySynthetic | Chamfer distance (mm): 0.0042 -> 0.0038 | Improved |
| use SDF visibility instead of mesh-based visibility (ablation) | HiNeuS · Mip-NeRF 360 | PSNR (dB): 28.72 -> 29.50 | Improved |
| add planar-conformal regularization L_planar (ablation) | HiNeuS · Mip-NeRF 360 | PSNR (dB): 29.05 -> 29.50 | Improved |
| add planar-conformal regularization L_planar (ablation) | HiNeuS · DTU | Chamfer distance (mm): 0.48 -> 0.43 | Improved |
| reduce training time by 75% (2h vs 8h) (ablation) | HiNeuS · GlossySynthetic | Chamfer distance (mm): 0.0038 -> 0.0057 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 5 of 5 on most shared results.
- NeuS — NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction (NeurIPS 2021) · better on 2 of 2 shared results
- RefNeuS — Ref-NeuS: Ambiguity-Reduced Neural Implicit Surface Learning for Multi-View Reconstruction with Reflection (ICCV 2023) · better on 1 of 1 shared result
- Mip-NeRF 360 — Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields (CVPR 2022) · better on 1 of 1 shared result
- HF-NeuS — HF-NeuS: Improved Surface Reconstruction Using High-Frequency Details (NeurIPS 2022) · better on 1 of 1 shared result
- Mip-NeRF — Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields (ICCV 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 Neural Surface Refinement for Modeling Transparent Objects (CVPR 2024 · similarity 0.88)
- UniSDF: Unifying Neural Representations for High-Fidelity 3D Reconstruction of Complex Scenes with Reflections (NeurIPS 2024 · similarity 0.88)
- GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction (NeurIPS 2025 · similarity 0.87)
- MAtCha Gaussians: Atlas of Charts for High-Quality Geometry and Photorealism From Sparse Views (CVPR 2025 · similarity 0.87)
- From Transparent to Opaque: Rethinking Neural Implicit Surfaces with $\alpha$-NeuS (NeurIPS 2024 · similarity 0.87)
- Normal-NeRF: Ambiguity-Robust Normal Estimation for Highly Reflective Scenes (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.
