Papers › MT-VAE: Learning Motion Transformations to Generate Multimodal Human Dynamics

MT-VAE: Learning Motion Transformations to Generate Multimodal Human Dynamics

14 Aug 2018ECCV 2018 9arXiv:1808.04545archive 2025-07-28

Xinchen Yan, Akash Rastogi, Ruben Villegas, Kalyan Sunkavalli, Eli Shechtman, Sunil Hadap, Ersin Yumer, Honglak Lee

Long-term human motion can be represented as a series of motion modes---motion sequences that capture short-term temporal dynamics---with transitions between them. We leverage this structure and present a novel Motion Transformation Variational Auto-Encoders (MT-VAE) for learning motion sequence generation. Our model jointly learns a feature embedding for motion modes (that the motion sequence can be reconstructed from) and a feature transformation that represents the transition of one motion mode to the next motion mode. Our model is able to generate multiple diverse and plausible motion sequences in the future from the same input. We apply our approach to both facial and full body motion, and demonstrate applications like analogy-based motion transfer and video synthesis.

PaperPDFConference PDFCode

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

Code

xcyan/eccv18_mtvae 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

Human DynamicsHuman Pose Forecastingmotion prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Human Pose Forecasting Human3.6M MT-VAE ADE 457 #33 of 33 Archive leaderboard report
Human Pose Forecasting Human3.6M MT-VAE APD 403 #33 of 33 Archive leaderboard report
Human Pose Forecasting Human3.6M MT-VAE FDE 595 #33 of 33 Archive leaderboard report
Human Pose Forecasting Human3.6M MT-VAE MMADE 716 #33 of 33 Archive leaderboard report
Human Pose Forecasting Human3.6M MT-VAE MMFDE 883 #33 of 33 Archive leaderboard report
Human Pose Forecasting HumanEva-I MT-VAE ADE@2000ms 345 #11 of 11 Archive leaderboard report
Human Pose Forecasting HumanEva-I MT-VAE APD@2000ms 21 #11 of 11 Archive leaderboard report
Human Pose Forecasting HumanEva-I MT-VAE FDE@2000ms 403 #11 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