Research map / 3D vision / Face and shape
Neural Cages for Detail-Preserving 3D Deformations
Wang Yifan, Noam Aigerman, Vladimir G. Kim, Siddhartha Chaudhuri, Olga Sorkine-Hornung
Check 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 |
|---|---|---|---|
| Set αMVC from 0 to 1 (ablation) | Neural Cages · COSEG vases | CD: 1.64 -> 1.44 | Improved |
| Set αMVC from 0 to 1 (ablation) | Neural Cages · COSEG vases | ΔCotLaplacian: 9.04 -> 8.74 | Improved |
| Increase αMVC from 1 to 10 (ablation) | Neural Cages · COSEG vases | CD and ΔCotLaplacian: CD: 1.44 -> 2.65; ΔCotLaplacian: 8.74 -> 8.27 | Mixed |
| Use point-to-surface plus symmetry instead of Laplacian plus symmetry shape losses (ablation) | Neural Cages · COSEG vases | CD: 5.16 -> 4.86 | Improved |
| Use point-to-surface plus symmetry instead of Laplacian plus symmetry shape losses (ablation) | Neural Cages · COSEG vases | ΔCotLaplacian: 4.75 -> 4.70 | Improved |
| Use normal plus symmetry instead of point-to-surface plus symmetry shape losses (ablation) | Neural Cages · COSEG vases | CD and ΔCotLaplacian: CD: 4.86 -> 5.45; ΔCotLaplacian: 4.70 -> 4.33 | Mixed |
| Add source-specific cage prediction instead of retaining the template cage (ablation) | Neural Cages · COSEG vases | CD and ΔCotLaplacian: CD: 3.27 -> 3.06; ΔCotLaplacian: 5.65 -> 10.45 | Mixed |
| Replace a shared optimized cage with source-specific cage prediction (ablation) | Neural Cages · COSEG vases | CD and ΔCotLaplacian: CD: 3.11 -> 3.06; ΔCotLaplacian: 12.05 -> 10.45 | Improved |
| Remove the negative-MVC penalty (ablation) | Neural Cages · COSEG vases | convergence and alignment error: CD: 1.44 -> 1.64 | Hurt |
Closest papers by meaning
- CageNeRF: Cage-based Neural Radiance Field for Generalized 3D Deformation and Animation (NeurIPS 2022 · similarity 0.89)
- Neural Shape Deformation Priors (NeurIPS 2022 · similarity 0.88)
- CaDeX: Learning Canonical Deformation Coordinate Space for Dynamic Surface Representation via Neural Homeomorphism (CVPR 2022 · similarity 0.87)
- 4Deform: Neural Surface Deformation for Robust Shape Interpolation (CVPR 2025 · similarity 0.86)
- Implicit-ARAP: Efficient Handle-Guided Neural Field Deformation via Local Patch Meshing (NeurIPS 2025 · similarity 0.85)
- ShapeMatcher: Self-Supervised Joint Shape Canonicalization Segmentation Retrieval and Deformation (CVPR 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.
