XNews

Google DeepMind Reconstructs Unfilmed Memory Using Pose Control Models

Google DeepMind Reconstructs Unfilmed Memory Using Pose Control Models

Google DeepMind announced a technique to reconstruct a memory that was never filmed by pairing restored archival photos with pose control models to capture mannerisms and micro-expressions of two individuals, Burt and Ethelle. This was used to animate their first meeting for the documentary 'Love, Rendered' in collaboration with PrimordialSoup and StorySyndicate.

Source posts