A feed-forward network with iterative feedback and a coupled multi-resolution Gaussians-on-Mesh representation sets state-of-the-art rendering quality for generalizable human avatars from sparse views.
On AIST++, we compare with HumanNeRF (Weng et al., 2022), GoMAvatar (Wen et al., 2024), 3DGS-Avatar (Qian et al., 2024b), iHuman (Paudel et al.,
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
-
LIFe-GoM: Generalizable Human Rendering with Learned Iterative Feedback Over Multi-Resolution Gaussians-on-Mesh
A feed-forward network with iterative feedback and a coupled multi-resolution Gaussians-on-Mesh representation sets state-of-the-art rendering quality for generalizable human avatars from sparse views.