Neural Sign Reenactor: Deep Photorealistic Sign Language Retargeting
This enables applications like sign language anonymization and production, addressing accessibility needs for the deaf and hard-of-hearing community, though it is an incremental improvement over existing methods.
The paper tackles the problem of transferring sign language movements and expressions from a source to a target video using a neural rendering pipeline, achieving photo-realistic results as demonstrated through qualitative and quantitative evaluations.
In this paper, we introduce a neural rendering pipeline for transferring the facial expressions, head pose, and body movements of one person in a source video to another in a target video. We apply our method to the challenging case of Sign Language videos: given a source video of a sign language user, we can faithfully transfer the performed manual (e.g., handshape, palm orientation, movement, location) and non-manual (e.g., eye gaze, facial expressions, mouth patterns, head, and body movements) signs to a target video in a photo-realistic manner. Our method can be used for Sign Language Anonymization, Sign Language Production (synthesis module), as well as for reenacting other types of full body activities (dancing, acting performance, exercising, etc.). We conduct detailed qualitative and quantitative evaluations and comparisons, which demonstrate the particularly promising and realistic results that we obtain and the advantages of our method over existing approaches.