TIGER is a tri-prior fusion method for face video restoration using identity, geometry, and generative priors with progressive training to achieve SOTA identity fidelity and temporal stability on a new large-scale dataset.
Voxceleb: Large-scale speaker verification in the wild,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Dual-TIRE extends TiCodec with a second invariant-representation branch, and TiCodec can stream 660ms blocks with minimal degradation.
citing papers explorer
-
TIGER: Taming Identity, Geometry, and Generative Priors for High-Quality Face Video Restoration
TIGER is a tri-prior fusion method for face video restoration using identity, geometry, and generative priors with progressive training to achieve SOTA identity fidelity and temporal stability on a new large-scale dataset.
-
Streaming Neural Speech Codecs through Time-Invariant Representations
Dual-TIRE extends TiCodec with a second invariant-representation branch, and TiCodec can stream 660ms blocks with minimal degradation.