A multi-view feed-forward transformer provides initial poses and geometry from calibrated videos, followed by physics-aware Gaussian optimization with tetrahedral and collision constraints to produce robust 4D hand-object reconstructions.
arXiv preprint arXiv:2603.23997 (2026)
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
-
High-Fidelity 4D Hand-Object Capture via Multi-View Spatiotemporal Tracking and Physics-Aware Gaussians
A multi-view feed-forward transformer provides initial poses and geometry from calibrated videos, followed by physics-aware Gaussian optimization with tetrahedral and collision constraints to produce robust 4D hand-object reconstructions.