We propose a talking face video compression framework by implicitly transforming the temporal evolution into compact feature representation. More specifically, the temporal evolution of faces, which is complex, non-linear and difficult to extrapolate, is modelled in an end-to-end inference framework based upon very compact features. This enables the high-quality rendering of the face videos, which benefits from the learning of dense motion map with compact feature representation. Therefore, the proposed framework can accommodate ultra-low bandwidth video communication and maintain the quality of the reconstructed videos. Experimental results demonstrate that compared with the state-of-the-art video coding standard Versatile Video Coding (VVC) as well as the latest generative compression scheme Face Video-to-Video Synthesis (Face_vid2vid), the proposed scheme is superior in terms of both objective and subjective quality assessment methods.

Recently, there has been a tremendous demand for high-efficiency face video communications, coinciding with the popularization of the digital human character in numerous applications. This paper demonstrates a new communication paradigm of 3D human digital characters in ultra low-bit-rate application scenarios. The paradigm is grounded on the mild assumption of the consistency and persistence of human ap-pearance, such that only the compact features that determine the pose and expression of the 3D character need to be transmitted. The proposed is also expected to benefit virtual-physical world interaction in Metaverse.