Introduces BIP framework and GapGen generator to allocate and synthesize millions of non-colliding virtual face identities within gaps of the real face manifold.
Huang, Manu Ramesh, Tamara Berg, and Erik Learned-Miller
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
A feature-space method that erases usable identity information from face images via learnable perturbations and a Face Revive Generator, rendering them ineffective for deepfake swapping while preserving visual quality.
citing papers explorer
-
Non-Colliding Biometric Identities for Digital Entities: Geometry, Capacity, and Million-Scale Virtual Identity Provisioning
Introduces BIP framework and GapGen generator to allocate and synthesize millions of non-colliding virtual face identities within gaps of the real face manifold.
-
ID-Eraser: Proactive Defense Against Face Swapping via Identity Perturbation
A feature-space method that erases usable identity information from face images via learnable perturbations and a Face Revive Generator, rendering them ineffective for deepfake swapping while preserving visual quality.