RMD improves text-to-motion generation by decomposing prompts with an LLM, retrieving and recombining body-part motions, and refining them with a pretrained diffusion model, all without additional training.
Retrieval-augmented diffusion models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
RMD: A Simple Baseline for More General Human Motion Generation via Training-free Retrieval-Augmented Motion Diffuse
RMD improves text-to-motion generation by decomposing prompts with an LLM, retrieving and recombining body-part motions, and refining them with a pretrained diffusion model, all without additional training.