Given a single portrait image, a speech audio clip, and optionally a set of other control signals, our approach produces a high-quality lifelike talking face video of 512× 512 resolution at up to 40 FPS. The method is generic and robust, and the generated talking faces can faithfully mimic human facial expressions and head movements, reaching a high level of realism and liveliness. (All the photorealistic portrait images in this paper are virtual, non-existing identities.). Credit: arXiv (2024). DOI: 10.48550/arxiv.2404.10667
A team of AI researchers at Microsoft Research Asia has developed an AI application that converts a still image of a person and an audio track into an animation that accurately portrays the individual speaking or singing the audio track with appropriate facial ...
Recent Comments