Research map / 3D vision / Face and shape
Ref-NeuS: Ambiguity-Reduced Neural Implicit Surface Learning for Multi-View Reconstruction with Reflection
Wenhang Ge, Tao Hu, Haoyu Zhao, Shu Liu, Ying-Cong Chen
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 reflection-aware photometric loss with reflection score (no visibility) (ablation) | NeuS · Shiny Blender | Chamfer accuracy / MAE: 1.69 -> 1.17 Acc, 1.77 -> 1.43 MAE | Improved |
| add visibility identification to the reflection score (ablation) | NeuS w/ RS · Shiny Blender | Chamfer accuracy: 1.17 -> 0.80 | Improved |
| replace view-direction radiance with reflection-direction radiance only (ablation) | NeuS · Shiny Blender | Chamfer accuracy: 1.69 -> 1.36 mean Acc; coffee 1.42 -> 3.87 | Mixed |
| add reflection direction-dependent radiance on top of reflection score and visibility (ablation) | Ref-NeuS w/o Ref · Shiny Blender | Chamfer accuracy / MAE: 0.80 -> 0.46 Acc, 1.21 -> 0.91 MAE | Improved |
| use Ref-NeuS instead of NeuS on reflective objects | NeuS · Shiny Blender | Chamfer accuracy: 1.69 -> 0.46 | Improved |
| add reflection score on non-reflective DTU scenes (ablation) | NeuS · DTU 6 scenes | Chamfer distance: scan83 1.45 -> 1.27; scan118 0.45 -> 0.46 | No clear effect |
| use Ref-NeuS rendering with accurate normals vs Ref-NeRF | Ref-NeuS · Shiny Blender | PSNR: mean 30.10 -> 30.20 | Mixed |
| estimate reflection score and visibility | NeuS · training time | hours: 7 -> 7.5 | Hurt |
Later papers that compared with this method
7 later accepted papers report Ref-NeuS as a baseline in their results tables; 6 of them report a better number on most of the results they share with it.
- Normal-NeRF: Ambiguity-Robust Normal Estimation for Highly Reflective Scenes (AAAI 2025 · better on 2 of 2 shared results)
- AniSDF: Fused-Granularity Neural Surfaces with Anisotropic Encoding for High-Fidelity 3D Reconstruction (ICLR 2025 · better on 2 of 2 shared results)
- HiNeuS: High-fidelity Neural Surface Mitigating Low-texture and Reflective Ambiguity (ICCV 2025 · better on 1 of 1 shared result)
- GNeRP: Gaussian-guided Neural Reconstruction of Reflective Objects with Noisy Polarization Priors (ICLR 2024 · better on 4 of 4 shared results)
- PISR: Polarimetric Neural Implicit Surface Reconstruction for Textureless and Specular Objects (ECCV 2024 · better on 2 of 2 shared results)
- Rethinking Directional Parameterization in Neural Implicit Surface Reconstruction (ECCV 2024 · better on 2 of 2 shared results)
- UniSDF: Unifying Neural Representations for High-Fidelity 3D Reconstruction of Complex Scenes with Reflections (NeurIPS 2024 · better on 0 of 1 shared result)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- NeuS — NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction (NeurIPS 2021) · better on 6 of 7 shared results
- Ref-NeRF — Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields (CVPR 2022) · better on 2 of 2 shared results
- Geo-NeuS — Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstruction (NeurIPS 2022) · 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
- NeRSP: Neural 3D Reconstruction for Reflective Objects with Sparse Polarized Images (CVPR 2024 · similarity 0.91)
- Differentiable Neural Surface Refinement for Modeling Transparent Objects (CVPR 2024 · similarity 0.90)
- UniSDF: Unifying Neural Representations for High-Fidelity 3D Reconstruction of Complex Scenes with Reflections (NeurIPS 2024 · similarity 0.89)
- From Transparent to Opaque: Rethinking Neural Implicit Surfaces with $\alpha$-NeuS (NeurIPS 2024 · similarity 0.88)
- SC-NeuS: Consistent Neural Surface Reconstruction from Sparse and Noisy Views (AAAI 2024 · similarity 0.88)
- Normal-NeRF: Ambiguity-Robust Normal Estimation for Highly Reflective Scenes (AAAI 2025 · similarity 0.88)
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.
