A feed-forward framework predicts unified 3D Gaussian representations of dynamic humans and static scenes from monocular video in a single forward pass.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
GUSH3R: Everyone Everywhere All at Once as Gaussians
A feed-forward framework predicts unified 3D Gaussian representations of dynamic humans and static scenes from monocular video in a single forward pass.