Hand-4DGS introduces the first feed-forward 3D Gaussian Splatting framework for 4D hand reconstruction from egocentric videos, achieving ~60 FPS inference and generalization on H2O and ARCTIC datasets.
arXiv preprint arXiv:2503.14736 (2025)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
End-to-end neural pipeline extracts hand geometry from unmasked limited-view images and registers it to a personalized tetrahedral model via volumetric offsets, achieving SOTA on over 12,000 sequences.
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.
citing papers explorer
-
Hand-4DGS: Feed-Forward 3D Gaussian Splatting for 4D Hand Reconstruction from Egocentric Videos
Hand-4DGS introduces the first feed-forward 3D Gaussian Splatting framework for 4D hand reconstruction from egocentric videos, achieving ~60 FPS inference and generalization on H2O and ARCTIC datasets.
-
VEPHand: View-Efficient Photometric Hand Performance Capture at Scale
End-to-end neural pipeline extracts hand geometry from unmasked limited-view images and registers it to a personalized tetrahedral model via volumetric offsets, achieving SOTA on over 12,000 sequences.
-
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.