-
AD-NeRF dataset
The AD-NeRF dataset is used for talking head generation. -
LRS2 and HDTF datasets
The LRS2 and HDTF datasets are used for face attributes disentanglement and audio to lip synchronization tasks. -
GRID dataset
The GRID dataset was introduced by [5] as a corpus for tasks such as speech perception and speech recognition. GRID contains 33 unique speakers, articulating 1000 word sequences... -
LSP dataset
LSP dataset: A dataset for human pose estimation and tracking in videos.