3DDFA is an AI model developed by Chinese Academy of Sciences and Michigan State University (China and United States), first published in November 2015. It works in the vision domain, on tasks such as face detection and 3d reconstruction.
Epoch AI has no training-compute estimate for this model. The model has 5,355,584 parameters. It was trained on roughly 293.9K datapoints.
Access: Unreleased. Its weights are not openly released. Epoch AI rates the confidence of this record as confident.