Research map / 3D vision / Face and shape
SOMA: From Surface Observations to Muscle Anatomy
Eduardo Alvarado, Emily Kim, Friedemann Runte, Gerrit Nolte, Mario Botsch, Marc Habermann, Christian Theobalt
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 U-Net instead of linear blendshapes (ablation) | SOMA · SKIM ablation | MPME: 16.52 -> 13.43 | Improved |
| use U-Net instead of MLP (ablation) | SOMA · SKIM ablation | MPME: 14.03 -> 13.43 | Improved |
| use U-Net instead of MLP (ablation) | SOMA · SKIM ablation | subcutaneous volume change (%): 5.74 -> 1.37 | Improved |
| use U-Net instead of linear blendshapes (ablation) | SOMA · SKIM ablation | subcutaneous volume change (%): 3.57 -> 1.37 | Improved |
| add all physical energies (ablation) | SOMA · SKIM ablation | subcutaneous volume change (%): 9.37 -> 1.37 | Improved |
| add all physical energies (ablation) | SOMA · SKIM ablation | MPME: 13.71 -> 13.43 | Improved |
| add vector regularization (E_smooth, E_tan) (ablation) | SOMA · SKIM ablation | subcutaneous volume change (%): 8.27 -> 1.37 | Improved |
| add vector regularization (E_smooth, E_tan) (ablation) | SOMA · SKIM ablation | MPME: 13.46 -> 13.43 | Improved |
| add structural tension terms (E_bi, E_stretch) (ablation) | SOMA · SKIM ablation | subcutaneous volume change (%): 10.54 -> 1.37 | Improved |
| add volume preservation energy E_vol (ablation) | SOMA · SKIM ablation | subcutaneous volume change (%): 8.28 -> 1.37 | Improved |
| add volume preservation energy E_vol (ablation) | SOMA · SKIM ablation | MPME: 13.67 -> 13.43 | Improved |
| use SOMA instead of LBS | SOMA · SKIM unseen sequences | DRE >25 (mm): 134.28 -> 64.52 | Improved |
Closest papers by meaning
- Muscles in Time: Learning to Understand Human Motion In-Depth by Simulating Muscle Activations (NeurIPS 2024 · similarity 0.87)
- 3D Human Pose Estimation with Muscles (NeurIPS 2025 · similarity 0.87)
- Biomechanics-Guided Facial Action Unit Detection Through Force Modeling (CVPR 2023 · similarity 0.87)
- HIT: Estimating Internal Human Implicit Tissues from the Body Surface (CVPR 2024 · similarity 0.85)
- Electromyography-Informed Facial Expression Reconstruction for Physiological-Based Synthesis and Analysis (CVPR 2025 · similarity 0.84)
- MosaicMRI: A Diverse Dataset and Benchmark for Raw Musculoskeletal MRI (NeurIPS 2026 · similarity 0.83)
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.
