AsymK-Talker: Real-Time and Long-Horizon Talking Head Generation via Asymmetric Kernel Distillation

概要

arXiv:2605.02948v1 Announce Type: cross Abstract: Recent advances in diffusion models have markedly enhanced the visual fidelity of audio-driven talking head generation. Nevertheless, existing methods are constrained by three critical limitations: causal inefficiency that impedes real-time inferenc…