| Paper | Code | Average MPJPE (mm) 1000 msec | FDE@1000ms (mm) | FDE@560ms (mm) | FDE@720ms (mm) | FDE@880ms (mm) | ModelName | ReleaseDate |
|---|---|---|---|---|---|---|---|---|
| Space-Time-Separable Graph Convolutional Network for Pose Forecasting | ✓ Link | 42.3 | STS-GCN | 2021-10-09 | ||||
| Towards Accurate Human Motion Prediction via Iterative Refinement | 71 | Sun et al. | 2023-05-08 | |||||
| GCNext: Towards the Unity of Graph Convolutions for Human Motion Prediction | ✓ Link | 72.0 | GCNext | 2023-12-19 | ||||
| Back to MLP: A Simple Baseline for Human Motion Prediction | ✓ Link | 72.2 | siMLPe | 2022-07-04 | ||||
| AnyPose: Anytime 3D Human Pose Forecasting via Neural Ordinary Differential Equations | 84.4 | AnyPose1 | 2023-09-09 | |||||
| Auxiliary Tasks Benefit 3D Skeleton-based Human Motion Prediction | ✓ Link | 107.45 | AuxFormer | 2023-08-17 | ||||
| A generic diffusion-based approach for 3D human pose prediction in the wild | ✓ Link | 73.4 | 55.4 | 61.6 | 67.9 | TCD | 2022-10-11 |