Controllable motion in-betweening conditioned on target poses or semantic actions.
Conditional Motion In-betweening generates natural intermediate skeletal motion between start and target poses. A unified model supports both pose-conditioned and semantic-conditioned in-betweening, with motion augmentation based on smooth trajectory distributions. (Kim et al., 2022)
@article{kim2022conditional,title={Conditional Motion In-betweening},author={Kim, Jihoon and Byun, Taehyun and Shin, Seungyoun and Won, Jungdam and Choi, Sungjoon},journal={Pattern Recognition},volume={132},pages={108894},month=dec,year={2022},publisher={Elsevier},doi={10.1016/j.patcog.2022.108894},}
