Research map / 3D vision / Face and shape
Linear Shape Deformation Models With Local Support Using Graph-Based Structured Matrix Factorisation
Florian Bernard, Peter Gemmar, Frank Hertel, Jorge Goncalves, Johan Thunberg
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 |
|---|---|---|---|
| Use graph-based structured matrix factorisation with sparse, smooth local-support factors instead of SPLOCS | Brain structures · Brain structures | generalisation error | Improved |
| Use graph-based structured matrix factorisation with sparse, smooth local-support factors instead of SPLOCS | Brain structures · Brain structures | sparse reconstruction error | Improved |
| Use graph-based smoothness regularisation in addition to sparsity | Human body shape deformation factors · Human body shapes | deformation realism | Improved |
| Use the proposed method rather than existing methods | Human body shapes · Human body shapes | quantitative performance | No clear effect |
| Use the proposed method rather than PCA, Varimax, or ICA | Brain shape models · Brain structures | generalisation error | Improved |
| Assume smooth deformations and use the proposed method | Shape deformation modelling · Articulated motions | ability to model deformation | Hurt |
Closest papers by meaning
- Variational Autoencoders for Localized Mesh Deformation Component Analysis (TPAMI 2021 · similarity 0.88)
- Geo-SIC: Learning Deformable Geometric Shapes in Deep Image Classifiers (NeurIPS 2022 · similarity 0.86)
- Mesh-Based Autoencoders for Localized Deformation Component Analysis (AAAI 2018 · similarity 0.86)
- Composite Shape Modeling via Latent Space Factorization (ICCV 2019 · similarity 0.85)
- NPMs: Neural Parametric Models for 3D Deformable Shapes (ICCV 2021 · similarity 0.85)
- $\texttt{NAISR}$: A 3D Neural Additive Model for Interpretable Shape Representation (ICLR 2024 · similarity 0.84)
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.
