1 code implementation • 24 Apr 2024 • Kyusun Cho, Joungbin Lee, Heeji Yoon, Yeobin Hong, Jaehoon Ko, Sangjun Ahn, Seungryong Kim
A key insight is to encode the 3D Gaussian attributes into a shared implicit feature representation, where it is merged with audio features to manipulate each Gaussian attribute.
1 code implementation • 29 Mar 2024 • Jaehoon Ko, Kyusun Cho, Joungbin Lee, Heeji Yoon, Sangmin Lee, Sangjun Ahn, Seungryong Kim
Given the personalized 3D generative model, we present a novel audio-guided attention U-Net architecture that predicts the dynamic face variations in the NeRF space driven by audio.