“…In recent years, neural fields have emerged as the leading approach for scene representation [52], yielding remarkable results in novel view synthesis [26,28,33,39,46] and 3D reconstruction [30,41,53,56]. These techniques have found practical applications in modeling full head avatars [11,33,35,59]. By leveraging surface priors [31] and surface rendering [53], neural fields enable highly accurate 3D reconstructions of the full head, encompassing intricate details such as hair and shoulders [41,59].…”