LiP-Flow: Learning Inference-time Priors for Codec Avatars via Normalizing Flows in Latent Space

• Published in: arXiv.org
• Main Authors: Aksan, Emre, Ma, Shugao, Caliskan, Akin, Pidhorskyi, Stanislav, Alexander, Richard, Shih-En Wei, Saragih, Jason, Hilliges, Otmar
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 15.03.2022
• Subjects: Avatars; Cameras; Codec; Coders; Image reconstruction; Inference; Representations; Three dimensional models

Neural face avatars that are trained from multi-view data captured in camera domes can produce photo-realistic 3D reconstructions. However, at inference time, they must be driven by limited inputs such as partial views recorded by headset-mounted cameras or a front-facing camera, and sparse facial l...