Tag
SpatialAvatar-0 introduces a multi-stage reconstruction method for high-quality 4D head avatars using a shared FLAME-mesh-bound Gaussian representation, achieving superior performance across benchmarks with reduced iterations.
Avatar V is a production-scale framework for generating behaviorally recognizable avatar videos conditioned on full video references, introducing sparse reference attention and motion representation streams to achieve state-of-the-art identity preservation and lip synchronization.
Un laboratorio chino ha lanzado LongCat-Avatar, una herramienta open source que genera un avatar sincronizado con audio a partir de una foto y un audio, revolucionando la producción de video.