LPMM: Intuitive Pose Control for Neural Talking-Head Model via Landmark-Parameter Morphable Model
This work addresses the problem of user-friendly pose control in talking-head generation for applications like animation and virtual avatars, representing an incremental improvement over existing methods.
The paper tackles the limited pose controllability in neural talking-head models by introducing a landmark-parameter morphable model (LPMM) that enables intuitive rig-like control over head orientation and facial expressions, allowing parameter and image-based inputs without distorting other facial attributes.
While current talking head models are capable of generating photorealistic talking head videos, they provide limited pose controllability. Most methods require specific video sequences that should exactly contain the head pose desired, being far from user-friendly pose control. Three-dimensional morphable models (3DMM) offer semantic pose control, but they fail to capture certain expressions. We present a novel method that utilizes parametric control of head orientation and facial expression over a pre-trained neural-talking head model. To enable this, we introduce a landmark-parameter morphable model (LPMM), which offers control over the facial landmark domain through a set of semantic parameters. Using LPMM, it is possible to adjust specific head pose factors, without distorting other facial attributes. The results show our approach provides intuitive rig-like control over neural talking head models, allowing both parameter and image-based inputs.