SSD-Poser reconstructs full-body SMPL poses from three sparse HMD signals with a hybrid state-space/attention encoder and frequency-aware decoder, reporting state-of-the-art accuracy at real-time speed on AMASS.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SSD-Poser: Avatar Pose Estimation with State Space Duality from Sparse Observations
SSD-Poser reconstructs full-body SMPL poses from three sparse HMD signals with a hybrid state-space/attention encoder and frequency-aware decoder, reporting state-of-the-art accuracy at real-time speed on AMASS.