Official implementation of “GaussianTalker: Real-Time High-Fidelity Talking Head Synthesis with Audio-Driven 3D Gaussian Splatting” by Kyusun Cho, Joungbin Lee, Heeji Yoon, Yeobin Hong, Jaehoon Ko, Sangjun Ahn and Seungryong Kim
That's a great question! Wav2vec 2.0 and HuBERT are powerful models for audio processing, and they could potentially improve the rendered results. Unfortunately, we don't have immediate plans to add wav2vec and HuBERT support to the project.
The good news is, integrating them might be achievable! The ER-NeRF project provides some relevant code that you can potentially adapt for your use case. Feel free to ask any specific questions you have while working with the ER-NeRF code, and I'll do my best to assist!
That's a great question! Wav2vec 2.0 and HuBERT are powerful models for audio processing, and they could potentially improve the rendered results. Unfortunately, we don't have immediate plans to add wav2vec and HuBERT support to the project. The good news is, integrating them might be achievable! The ER-NeRF project provides some relevant code that you can potentially adapt for your use case. Feel free to ask any specific questions you have while working with the ER-NeRF code, and I'll do my best to assist!