Human Pose Forecasting
8 papers with code • 3 benchmarks • 4 datasets
Human pose forecasting is the task of detecting and predicting future human poses.
( Image credit: EgoPose )
In this paper, we propose a simple feed-forward deep network for motion prediction, which takes into account both temporal smoothness and spatial dependencies among human body joints.
The proposed method is generic and principled as it can be used for transforming any spatio-temporal graph through employing a certain set of well defined steps.
We consider the problem of image-to-video translation, where an input image is translated into an output video containing motions of a single object.
We propose the use of a proportional-derivative (PD) control based policy learned via reinforcement learning (RL) to estimate and forecast 3D human pose from egocentric videos.
To obtain samples from a pretrained generative model, most existing generative human motion prediction methods draw a set of independent Gaussian latent codes and convert them to motion samples.
To quantitatively evaluate performance on transitions and generalizations to longer time horizons, we present well-defined in-betweening benchmarks on a subset of the widely used Human3. 6M dataset and on LaFAN1, a novel high quality motion capture dataset that is more appropriate for transition generation.
For the first time, STS-GCN models the human pose dynamics only with a graph convolutional network (GCN), including the temporal evolution and the spatial joint interaction within a single-graph framework, which allows the cross-talk of motion and spatial correlations.