Research map / 3D vision / Face and shape
Frame Averaging for Equivariant Shape Space Learning
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 |
|---|---|---|---|
| Add Frame Averaging for global Euclidean equivariance | Graph autoencoder · DFaust, aligned and rotated test sets | MSE: 5.16 -> 4.39; 5.86 -> 4.35; 5.12 -> 4.66 | Helped |
| Add Frame Averaging for global Euclidean equivariance | VAE implicit shape autoencoder · CommonObject3D teddy bear | symmetric Chamfer distance: 0.421 -> 0.451 | Hurt |
| Add Frame Averaging for global Euclidean equivariance | VAE implicit shape autoencoder · CommonObject3D bottle | symmetric Chamfer distance: 0.334 -> 0.129 | Helped |
| Add Frame Averaging for global Euclidean equivariance | VAE implicit shape autoencoder · CommonObject3D suitcase | symmetric Chamfer distance: 0.218 -> 0.086 | Helped |
| Add Frame Averaging for global Euclidean equivariance | VAE implicit shape autoencoder · CommonObject3D banana | symmetric Chamfer distance: 0.087 -> 0.074 | Helped |
| Use piecewise Euclidean Frame Averaging | Mesh autoencoder · DFaust random, unseen random pose, and unseen pose | MSE: 4.52 -> 1.68; 7.77 -> 1.89; 3.38 -> 1.90 | Helped |
| Use piecewise Euclidean Frame Averaging | Mesh autoencoder · SMAL | MSE: 6.68 -> 2.44 | Helped |
| Use piecewise Euclidean Frame Averaging | Mesh autoencoder · MANO | MSE: 1.15 -> 0.86 | Helped |
Closest papers by meaning
- Neural Isometries: Taming Transformations for Equivariant ML (NeurIPS 2024 · similarity 0.89)
- Probing Equivariance and Symmetry Breaking in Convolutional Networks (NeurIPS 2025 · similarity 0.88)
- A Canonicalization Perspective on Invariant and Equivariant Learning (NeurIPS 2024 · similarity 0.88)
- Learning Generalizable Shape Completion with SIM(3) Equivariance (NeurIPS 2025 · similarity 0.87)
- Approximately Piecewise E(3) Equivariant Point Networks (ICLR 2024 · similarity 0.87)
- Equivariance via Minimal Frame Averaging for More Symmetries and Efficiency (ICML 2024 · 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.