Papers › HP-GAN: Probabilistic 3D human motion prediction via GAN

HP-GAN: Probabilistic 3D human motion prediction via GAN

27 Nov 2017arXiv:1711.09561archive 2025-07-28

Emad Barsoum, John Kender, Zicheng Liu

Predicting and understanding human motion dynamics has many applications, such as motion synthesis, augmented reality, security, and autonomous vehicles. Due to the recent success of generative adversarial networks (GAN), there has been much interest in probabilistic estimation and synthetic data generation using deep neural network architectures and learning algorithms. We propose a novel sequence-to-sequence model for probabilistic human motion prediction, trained with a modified version of improved Wasserstein generative adversarial networks (WGAN-GP), in which we use a custom loss function designed for human motion prediction. Our model, which we call HP-GAN, learns a probability density function of future human poses conditioned on previous poses. It predicts multiple sequences of possible future human poses, each from the same input sequence but a different vector z drawn from a random distribution. Furthermore, to quantify the quality of the non-deterministic predictions, we simultaneously train a motion-quality-assessment model that learns the probability that a given skeleton sequence is a real human motion. We test our algorithm on two of the largest skeleton datasets: NTURGB-D and Human3.6M. We train our model on both single and multiple action types. Its predictive power for long-term motion estimation is demonstrated by generating multiple plausible futures of more than 30 frames from just 10 frames of input. We show that most sequences generated from the same input have more than 50\% probabilities of being judged as a real human sequence. We will release all the code used in this paper to Github.

Paper PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

Djmcflush/Funky-Movement mentioned on GitHubpytorch report

ThomasDupiereux/hpgan mentioned on GitHubtf report

ebarsoum/hpgan mentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Autonomous Vehicles Human Pose Forecasting Human motion prediction Motion Estimation Motion Synthesis Prediction Synthetic Data Generation motion prediction

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Human Pose Forecasting	Human3.6M	HP-GAN	ADE	858	#28 of 33	Archive leaderboard	report
Human Pose Forecasting	Human3.6M	HP-GAN	APD	7214	#28 of 33	Archive leaderboard	report
Human Pose Forecasting	Human3.6M	HP-GAN	FDE	867	#28 of 33	Archive leaderboard	report
Human Pose Forecasting	Human3.6M	HP-GAN	MMADE	847	#28 of 33	Archive leaderboard	report
Human Pose Forecasting	Human3.6M	HP-GAN	MMFDE	858	#28 of 33	Archive leaderboard	report
Human Pose Forecasting	HumanEva-I	HP-GAN	ADE@2000ms	772	#9 of 11	Archive leaderboard	report
Human Pose Forecasting	HumanEva-I	HP-GAN	APD@2000ms	1139	#9 of 11	Archive leaderboard	report
Human Pose Forecasting	HumanEva-I	HP-GAN	FDE@2000ms	749	#9 of 11	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections