Realistic Full-Body Tracking from Sparse Observations via Joint-Level Modeling
About
To bridge the physical and virtual worlds for rapidly developed VR/AR applications, the ability to realistically drive 3D full-body avatars is of great significance. Although real-time body tracking with only the head-mounted displays (HMDs) and hand controllers is heavily under-constrained, a carefully designed end-to-end neural network is of great potential to solve the problem by learning from large-scale motion data. To this end, we propose a two-stage framework that can obtain accurate and smooth full-body motions with the three tracking signals of head and hands only. Our framework explicitly models the joint-level features in the first stage and utilizes them as spatiotemporal tokens for alternating spatial and temporal transformer blocks to capture joint-level correlations in the second stage. Furthermore, we design a set of loss terms to constrain the task of a high degree of freedom, such that we can exploit the potential of our joint-level modeling. With extensive experiments on the AMASS motion dataset and real-captured data, we validate the effectiveness of our designs and show our proposed method can achieve more accurate and smooth motion compared to existing approaches.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Full-body motion generation | GORP (Real MC) | MPJPE5.97 | 16 | |
| Motion generation from hand-tracking signal | GORP (Real HT) | MPJPE6.62 | 16 | |
| Full-body motion generation | GORP (Simulated MC) | MPJPE4.81 | 8 | |
| Full-body Avatar Reconstruction | AMASS Setting S1 (test) | MPJRE2.9 | 8 | |
| Full-body Avatar Reconstruction | AMASS (S1) | MPJRE2.4 | 8 | |
| Full-body motion estimation (Hand Tracking) | A-P2 (test) | MPJRE5.71 | 8 | |
| Motion generation from hand-tracking signal | GORP Simulated HT | MPJPE6.19 | 8 | |
| Hand Tracking (HT) | A-P1 v1 (test) | MPJRE4.18 | 8 | |
| Motion Controllers (MC) Tracking | A-P1 v1 (test) | MPJRE3.39 | 8 | |
| Full-body motion estimation (Motion Controllers) | A-P2 (test) | MPJRE5.21 | 8 |