SignSplat renders photo-realistic sign language by anchoring Gaussian splats to an SMPL-X body mesh with regularized optimization and adaptive densification, claiming state-of-the-art results on NeuMan, X-Humans, and a private sign-language sequence.
Animatable neural radiance fields from monocular rgb videos, 2021
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SignSplat: Rendering Sign Language via Gaussian Splatting
SignSplat renders photo-realistic sign language by anchoring Gaussian splats to an SMPL-X body mesh with regularized optimization and adaptive densification, claiming state-of-the-art results on NeuMan, X-Humans, and a private sign-language sequence.