Research map / 3D vision / NeRF and radiance fields
SNeS: Learning Probably Symmetric Neural Surfaces from Incomplete Data
Eldar Insafutdinov, Dylan Campbell, João F. Henriques, Andrea Vedaldi
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 learned symmetry (SNeS) to NeuS | NeuS · CO3D cars, random split | MAE depth: 0.108 -> 0.086 | Improved |
| add learned symmetry (SNeS) to NeuS | NeuS · CO3D cars, random split | IoU mask: 0.523 -> 0.787 | Improved |
| add learned symmetry (SNeS) to NeuS | NeuS · CO3D cars, random split | PSNR: 23.3 -> 23.3 | No clear effect |
| add learned symmetry (SNeS) to NeuS | NeuS · CO3D cars, structured split | MAE depth: 0.105 -> 0.077 | Improved |
| add learned symmetry (SNeS) to NeuS | NeuS · CO3D cars, structured split | IoU mask: 0.566 -> 0.906 | Improved |
| add learned symmetry (SNeS) to NeuS | NeuS · CO3D cars, structured split | PSNR: 13.4 -> 14.1 | Improved |
| add learned symmetry (SNeS) to NeuS | NeuS · CO3D cars, structured split | LPIPS: 0.556 -> 0.503 | Improved |
| add symmetric lighting loss (ablation) | SNeS · CO3D cars, structured split subset | PSNR: 14.3 -> 13.7 | Hurt |
| add symmetric lighting loss (ablation) | SNeS · CO3D cars, structured split subset | LPIPS: 0.564 -> 0.585 | Hurt |
| add symmetric lighting loss (ablation) | SNeS · CO3D cars, structured split subset | IoU mask: 0.894 -> 0.914 | Improved |
| add diffuse colour loss (ablation) | SNeS · CO3D cars, structured split subset | MAE depth: 0.0722 -> 0.0706 | Improved |
| add diffuse colour loss (ablation) | SNeS · CO3D cars, structured split subset | IoU mask: 0.917 -> 0.894 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- NeuS — NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction (NeurIPS 2021) · better on 7 of 8 shared results
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
- NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wild (NeurIPS 2021 · similarity 0.89)
- Symmetry Strikes Back: From Single-Image Symmetry Detection to 3D Generation (CVPR 2025 · similarity 0.89)
- From Transparent to Opaque: Rethinking Neural Implicit Surfaces with $\alpha$-NeuS (NeurIPS 2024 · similarity 0.89)
- UniSDF: Unifying Neural Representations for High-Fidelity 3D Reconstruction of Complex Scenes with Reflections (NeurIPS 2024 · similarity 0.88)
- GNeRP: Gaussian-guided Neural Reconstruction of Reflective Objects with Noisy Polarization Priors (ICLR 2024 · similarity 0.88)
- NeRFPrior: Learning Neural Radiance Field as a Prior for Indoor Scene Reconstruction (CVPR 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.
