Search papers, labs, and topics across Lattice.
University of New South Wales (UNSW)
3
0
4
Traditional frame-wise evaluation fails to capture the nuances of speech-driven facial motion, but a new sequence-alignment approach reveals clearer trade-offs in generative model performance.
Stop identity drift in your talking-head generators without retraining: a simple feedback loop between the generator and encoder stabilizes identity and motion.
Modeling relationships between image patches with graph neural networks substantially improves blind image quality assessment for ultra-high-definition images, achieving state-of-the-art results.
