A lightweight graph attention model amortizes inverse kinematics to produce animation-ready rotations from sparse joint positions at over 650 FPS on CPU.
et al.Quater-GCN: Enhancing 3D Human Pose Estimation with Orientation and Semi-supervised Training
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Amortized Inverse Kinematics via Graph Attention for Real-Time Human Avatar Animation
A lightweight graph attention model amortizes inverse kinematics to produce animation-ready rotations from sparse joint positions at over 650 FPS on CPU.