ScaleMoGen applies next-scale autoregressive prediction to human motion generation with multi-scale skeletal-temporal bitwise token maps, reporting SOTA FID on HumanML3D.
T2m-gpt: Generating human motion from textual descriptions with discrete representations
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
baseline 1
citation-polarity summary
representative citing papers
AnyMo is a masked-modeling framework for any-modality human motion generation trained on the new OmniHuMo dataset of 5,000+ hours of multimodal motion sequences.
SDFlow learns a global transport map via similarity-driven flow matching in VQ latent space, using low-rank manifold decomposition and a categorical posterior to handle discreteness, yielding SOTA long-horizon performance and inference speedups.
MSDformer introduces a multi-scale discrete transformer that tokenizes time series at multiple scales and models them autoregressively in discrete space, claiming superior performance over prior DTM methods with rate-distortion theoretical support.
HTD-Refine uses a temporal transformer (PVA-Net) to predict high-order dynamics and refines HMR outputs via optimization for more natural motion.
citing papers explorer
-
ScaleMoGen: Autoregressive Next-Scale Prediction for Human Motion Generation
ScaleMoGen applies next-scale autoregressive prediction to human motion generation with multi-scale skeletal-temporal bitwise token maps, reporting SOTA FID on HumanML3D.
-
AnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling
AnyMo is a masked-modeling framework for any-modality human motion generation trained on the new OmniHuMo dataset of 5,000+ hours of multimodal motion sequences.
-
SDFlow: Similarity-Driven Flow Matching for Time Series Generation
SDFlow learns a global transport map via similarity-driven flow matching in VQ latent space, using low-rank manifold decomposition and a categorical posterior to handle discreteness, yielding SOTA long-horizon performance and inference speedups.
-
MSDformer: Multi-scale Discrete Transformer For Time Series Generation
MSDformer introduces a multi-scale discrete transformer that tokenizes time series at multiple scales and models them autoregressively in discrete space, claiming superior performance over prior DTM methods with rate-distortion theoretical support.
-
Natural Human Motion Recovery by Aligning High-Order Temporal Dynamics from Monocular Videos
HTD-Refine uses a temporal transformer (PVA-Net) to predict high-order dynamics and refines HMR outputs via optimization for more natural motion.
- ExpertEdit: Learning Skill-Aware Motion Editing from Expert Videos