Research map / Probabilistic and scientific modeling / Variational and generative sampling
VNC: A Scale-Space Foundation for Learnable 3D Surface Evolution
Baoxing Li, Yong Deng, Xu Zhao
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 |
|---|---|---|---|
| use VNC-soft instead of VNC-hard | VNC operator · Runtime, V=50k | runtime: 3.0 s -> 1.4 s | Improved |
| use VNC-hard instead of CPU baseline | VNC operator · Runtime, V=50k | runtime: 256 s -> 3.0 s | Improved |
| use adaptive-scale VNC-Flow instead of fixed small scale (ablation) | VNC-Flow · Complex human shape (qualitative) | trajectory validity | Improved |
| use adaptive-scale VNC-Flow instead of fixed large scale (ablation) | VNC-Flow · Complex human shape (qualitative) | trajectory validity | Improved |
| use VNC-Flow instead of mean-curvature-flow baselines | VNC-Flow · Complex human shape (qualitative) | intermediate surface validity | Improved |
| use C-VAE-II time-conditioned mapping instead of MeshSDF | surface evolution · THuman2.0 target shape | Chamfer distance (x10^-4): 1.61 -> 1.05 | Improved |
| use C-VAE-II instead of NIE | surface evolution · THuman2.0 target shape | EMD (x10^-2): 3.17 -> 1.94 | Improved |
| use C-VAE-II instead of NMF | surface evolution · THuman2.0 target shape | NCE (rad): 0.518 -> 0.257 | Improved |
| use normalized VNC curvature instead of unnormalized baseline curvature (ablation) | VNC operator · Scale stability | global mean curvature | Improved |
Closest papers by meaning
- Surface Networks (CVPR 2018 · similarity 0.87)
- Neu-PiG: Neural Preconditioned Grids for Fast Dynamic Surface Reconstruction on Long Sequences (CVPR 2026 · similarity 0.87)
- Variational Autoencoders for Deforming 3D Mesh Models (CVPR 2018 · similarity 0.87)
- Flatten Anything: Unsupervised Neural Surface Parameterization (NeurIPS 2024 · similarity 0.87)
- 4Deform: Neural Surface Deformation for Robust Shape Interpolation (CVPR 2025 · similarity 0.86)
- Dynamic Neural Surfaces for Elastic 4D Shape Representation and Analysis (CVPR 2025 · similarity 0.86)
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.
