For each sample pose:

The canonical method.

You can carry thousands of anatomical references on a tablet or laptop, making it easy to practice at a cafe or studio without needing a physical book.

Neural networks (Neural Pose Space, 2021–2024) replace RBFs. A small MLP takes ( \mathbfq ) and outputs per-vertex deltas. Trained on < 1000 pose examples. Compact, smooth, and handles high-DOF poses without explosion.

$$w_j(p) = \exp\left( - \frac^22\sigma^2 \right)$$