AI RESEARCH
MARRS: Masked Autoregressive Unit-based Reaction Synthesis
arXiv CS.CV
•
ArXi:2505.11334v3 Announce Type: replace This work aims at a challenging task: human action-reaction synthesis, i.e., generating human reactions conditioned on the action sequence of another person. Currently, autoregressive modeling approaches with vector quantization (VQ) have achieved remarkable performance in motion generation tasks. However, VQ has inherent disadvantages, including quantization information loss, low codebook utilization, etc. In addition, while dividing the body into separate units can be beneficial, the computational complexity needs to be considered.