GaussianEmoTalker is an audio-driven framework for real-time emotional talking head synthesis using 3D Gaussian Splatting with neutral-to-emotional residual deformation via GaussianBlendshapes and a spatial-audio-emotion attention module.
Gaussianspeech: Audio-driven gaussian avatars,
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
FFAvatar uses a Transformer-based 3D Gaussian model with alternating attention and sparse-to-dense learning to enable feed-forward, incremental reconstruction of animatable 4D head avatars from sparse portrait images.
citing papers explorer
-
GaussianEmoTalker: Real-Time Emotional Talking Head Synthesis with Audio-Driven and Blendshape-Based 3D Gaussian Splatting
GaussianEmoTalker is an audio-driven framework for real-time emotional talking head synthesis using 3D Gaussian Splatting with neutral-to-emotional residual deformation via GaussianBlendshapes and a spatial-audio-emotion attention module.
-
FFAvatar: Feed-Forward 4D Head Avatar Reconstruction from Sparse Portrait Images
FFAvatar uses a Transformer-based 3D Gaussian model with alternating attention and sparse-to-dense learning to enable feed-forward, incremental reconstruction of animatable 4D head avatars from sparse portrait images.