Research map / 3D vision / Face and shape
Neural Surface Maps
Check 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 |
|---|---|---|---|
| optimize the composed neural map for isometric distortion (ablation) | Neural surface parameterization · Stanford Bunny | median Dirichlet energy: 7.24 -> 6.03 | Helped |
| optimize the composed neural map for conformal distortion (ablation) | Neural surface parameterization · Stanford Bunny | median conformal energy: 1.29 -> 1.04 | Helped |
| add conformal-distortion optimization to the initial neural map (ablation) | Neural surface parameterization · Surface parameterization | conformal distortion: 1.74 -> 1.52 | Helped |
| add isometric-distortion optimization to the initial neural map (ablation) | Neural surface parameterization · Surface parameterization | median symmetric Dirichlet: 11.58 -> 9.92 | Helped |
| use Softplus rather than LeakyReLU or ReLU (ablation) | Neural surface map · Surface approximation | surface artifact level | Helped |
| use Softplus rather than LeakyReLU or ReLU (ablation) | Neural surface map · Surface approximation | fidelity to fine surface details | Mixed |
| represent and optimize the surface map with neural surface maps | Inter-surface mapping · Bust | triangle flips: 8.58% -> no triangle flips | Helped |
| represent and optimize the surface map with neural surface maps | Inter-surface mapping · Animal | triangle flips: 8.54% -> 0.03% | Helped |
| represent and optimize the surface map with neural surface maps | Inter-surface mapping · Bust | median D_iso: 4.90 -> 7.00 | Mixed |
| represent and optimize the surface map with neural surface maps | Inter-surface mapping · Animal | median D_iso: 7.00 -> 8.56 | Hurt |
| use neural surface maps instead of Mandad et al. | Inter-surface mapping · Bust | median D_iso: 7146 -> 7.00 | Helped |
| use neural surface maps instead of Mandad et al. | Inter-surface mapping · Animal | median D_iso: 10669 -> 8.56 | Helped |
Closest papers by meaning
- Neural Convolutional Surfaces (CVPR 2022 · similarity 0.90)
- Improving Neural Network Surface Processing with Principal Curvatures (NeurIPS 2024 · similarity 0.90)
- Flatten Anything: Unsupervised Neural Surface Parameterization (NeurIPS 2024 · similarity 0.87)
- Small Steps and Level Sets: Fitting Neural Surface Models with Point Guidance (CVPR 2024 · similarity 0.86)
- Dynamic Neural Surfaces for Elastic 4D Shape Representation and Analysis (CVPR 2025 · similarity 0.86)
- CoFie: Learning Compact Neural Surface Representations with Coordinate Fields (NeurIPS 2024 · similarity 0.85)
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.