MDC-Net patches 90-frame gaps between motion clips using a DCT-domain diffusion model, reporting small ADE/FDE/MMADE gains over HumanMAC on Human3.6M with a smaller model.
Humanmac: Masked motion completion for human motion prediction
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
REJECT 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
Diffusion Model-based Activity Completion for AI Motion Capture from Videos
MDC-Net patches 90-frame gaps between motion clips using a DCT-domain diffusion model, reporting small ADE/FDE/MMADE gains over HumanMAC on Human3.6M with a smaller model.