Autoregressive GAN for Semantic Unconditional Head Motion Generation
This addresses the problem of generating realistic head motions for animation, which is incremental as it builds on existing GAN-based methods for a specific domain.
The paper tackled unconditional head motion generation from a single reference pose to animate still human faces, achieving superior performance compared to state-of-the-art models with smooth trajectories and low error accumulation.
In this work, we address the task of unconditional head motion generation to animate still human faces in a low-dimensional semantic space from a single reference pose. Different from traditional audio-conditioned talking head generation that seldom puts emphasis on realistic head motions, we devise a GAN-based architecture that learns to synthesize rich head motion sequences over long duration while maintaining low error accumulation levels.In particular, the autoregressive generation of incremental outputs ensures smooth trajectories, while a multi-scale discriminator on input pairs drives generation toward better handling of high- and low-frequency signals and less mode collapse.We experimentally demonstrate the relevance of the proposed method and show its superiority compared to models that attained state-of-the-art performances on similar tasks.