Pruned local linear blendshapes on Gaussians capture pose-dependent appearance changes to deliver high-quality mobile avatars at 120 FPS from multi-view video without pretrained models.
Expres- sive gaussian human avatars from monocular rgb video.Ad- vances in Neural Information Processing Systems, 37:5646– 5660
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
SFGS reconstructs expressive full-body 3D avatars from monocular video using structure-aware Gaussian splatting with spatial triplanes, time-aware hexplanes, and hand-specific residual refinement.
citing papers explorer
-
High-Fidelity Mobile Avatars with Pruned Local Blendshapes
Pruned local linear blendshapes on Gaussians capture pose-dependent appearance changes to deliver high-quality mobile avatars at 120 FPS from multi-view video without pretrained models.
-
Structure-Aware Fine-Grained Gaussian Splatting for Expressive Avatar Reconstruction
SFGS reconstructs expressive full-body 3D avatars from monocular video using structure-aware Gaussian splatting with spatial triplanes, time-aware hexplanes, and hand-specific residual refinement.