Timo Bolkart

FaMoS

FaMoS is a dynamic 3D head dataset from 95 subjects, each performing 28 motion sequences. The sequences comprise of six prototypical expressions (i.e., Anger, Disgust, Fear, Happiness, Sadness, and Surprise), two head rotations (left/right and up/down), and diverse facial motions, including extreme and asymmetric expressions. Each sequence is recorded at 60 fps. In total, FaMoS contains around 600K 3D head meshes (i.e., ~225 frames per sequence). For each frame, we compute a registration in FLAME mesh topology, which are downloadable here for research purposes. You must sign up and agree to the license to download the data.

VOCASET

VOCASET is a large collection of audio-4D scan pairs captured from 6 female and 6 male subjects. For each subject, we collect 40 sequences of a sentence spoken in English, each of length three to five seconds. You find the raw scanner data (i.e. raw audio-4D scan pairs), the registered data (i.e. in FLAME topology), and the unposed data (i.e. registered data where effects of global rotation, translation, and head rotation around the neck are removed).

CoMA dataset

The CoMA dataset consists of 12 classes of extreme expressions from 12 different subjects. These expressions are complex and asymmetric. The expression sequences in our dataset are – bareteeth, cheeks in, eyebrow, high smile, lips back, lips up, mouth down, mouth extreme, mouth middle, mouth side and mouth up. You find the registered data (i.e. in FLAME topology) of the 20,466 scans of the dataset.

D3DFACS registrations

The publicly available D3DFACS datset consists of 3D facial expression sequences of 10 subjects. We provide temporal registrations (i.e. in FLAME topology) of the D3DFACS database.