-
Notifications
You must be signed in to change notification settings - Fork 30
Open
Description
The segments we trained are all 4s long, and it is difficult to generalize to arbitrary length gestures by positional encoding alone.
MDM-based models that require time-awareness (arbitrarily long inference) require a smooth transition between the generated sequences. The following practices can be referred to:
- Our approach is to add seed poses for smooth transitions.
- Its follow-up work PriorMDM uses DoubleTake for long motion generation.
- EDGE enforces temporal consistency between multiple sequences.
Metadata
Metadata
Assignees
Labels
No labels