Papers › MT-VAE: Learning Motion Transformations to Generate Multimodal Human Dynamics
MT-VAE: Learning Motion Transformations to Generate Multimodal Human Dynamics
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.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 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