Head2HeadFS: Video-based Head Reenactment with Few-shot Learning
This addresses the challenge of realistic head reenactment for video applications, offering a more adaptable solution than existing person-specific or landmark-based methods.
The paper tackles the problem of head reenactment by transferring facial expressions and head poses from a source to a target person, achieving high-quality results using a few-shot learning strategy that adapts quickly with only a few samples.
Over the past years, a substantial amount of work has been done on the problem of facial reenactment, with the solutions coming mainly from the graphics community. Head reenactment is an even more challenging task, which aims at transferring not only the facial expression, but also the entire head pose from a source person to a target. Current approaches either train person-specific systems, or use facial landmarks to model human heads, a representation that might transfer unwanted identity attributes from the source to the target. We propose head2headFS, a novel easily adaptable pipeline for head reenactment. We condition synthesis of the target person on dense 3D face shape information from the source, which enables high quality expression and pose transfer. Our video-based rendering network is fine-tuned under a few-shot learning strategy, using only a few samples. This allows for fast adaptation of a generic generator trained on a multiple-person dataset, into a person-specific one.