Micro-Expression-Aware Avatar Fingerprinting via Inter-Frame Feature Differencing

ArXi:2604.23247v1 Announce Type: new Avatar fingerprinting, i.e., verifying who drives a synthetic talking-head video rather than whether it is real, is a critical safeguard for authorized use of face-reenactment technology. Existing methods rely on a fixed, non-differentiable landmark extraction stage that prevents the fingerprinting model from being optimized end-to-end from raw pixels.