PhysHanDI achieves full 3D hand and non-rigid object reconstruction by simulating object deformations from hand-induced forces and refining hand models via inverse physics, outperforming prior methods in reconstruction and prediction.
The MANO parameters are initialized from the fitting results of the initial hand reconstruction stage, with an initial learning rate of2×10 −5 decayed by 0.99 at each iteration
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
PhysHanDI: Physics-Based Reconstruction of Hand-Deformable Object Interactions
PhysHanDI achieves full 3D hand and non-rigid object reconstruction by simulating object deformations from hand-induced forces and refining hand models via inverse physics, outperforming prior methods in reconstruction and prediction.