TemPoFast3D reconstructs a 3D clothed human from monocular video at up to 12 FPS by propagating a canonical shape across frames and sampling only visible, surface-adjacent regions.
PINA: learning a personalized implicit neural avatar from a single RGB-D video sequence
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Link to the Past: Temporal Propagation for Fast 3D Human Reconstruction from Monocular Video
TemPoFast3D reconstructs a 3D clothed human from monocular video at up to 12 FPS by propagating a canonical shape across frames and sampling only visible, surface-adjacent regions.