MV-SSM models the joint spatial sequence with state-space layers plus projective attention and bidirectional token scanning, improving multi-view 3D pose accuracy and generalization to unseen camera setups.
3d pictorial structures for multiple human pose estimation
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
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
MV-SSM: Multi-View State Space Modeling for 3D Human Pose Estimation
MV-SSM models the joint spatial sequence with state-space layers plus projective attention and bidirectional token scanning, improving multi-view 3D pose accuracy and generalization to unseen camera setups.