A Z-order transformer organizes unstructured Gaussians for sparse attention, enabling feed-forward prediction of high-quality 3D splats with fewer primitives.
Decoupled weight de- cay regularization
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2verdicts
UNVERDICTED 2representative citing papers
GeoPredict improves VLA manipulation accuracy by adding predictive kinematic trajectories and 3D Gaussian workspace geometry as training-time depth-rendering supervision.
citing papers explorer
-
Z-Order Transformer for Feed-Forward Gaussian Splatting
A Z-order transformer organizes unstructured Gaussians for sparse attention, enabling feed-forward prediction of high-quality 3D splats with fewer primitives.
-
GeoPredict: Leveraging Predictive Kinematics and 3D Gaussian Geometry for Precise VLA Manipulation
GeoPredict improves VLA manipulation accuracy by adding predictive kinematic trajectories and 3D Gaussian workspace geometry as training-time depth-rendering supervision.