In research (such as by learned geometric modelling groups), models are trained to take a 2D image of a face and output a 3D Voxel grid or a mesh.
To understand the file, we must first dissect its naming convention: vox-cpk.pth.tar
| Checkpoint | Dataset | Focus | Audio Input | |------------|---------|-------|--------------| | vox-cpk.pth.tar | VoxCeleb | Lip-sync + jaw | Mel-spectrogram | | wav2lip_gan.pth | LRS2 | Lip-sync only | Raw audio | | facevid2vid_ckpt.pth | VoxCeleb | Full face + pose | Keypoints + audio | In research (such as by learned geometric modelling
Here is a detailed breakdown of the technical components, functionality, and usage of this file. and usage of this file.