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.
Due to the explicit nature of the Gaussians-on-Mesh representation, our method produces fewer floaters than NeRF-based ActorNeRF
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.