gDNA: Towards Generative Detailed Neural Avatars

Abstract

https://xuchen-ethz.github.io/gdna Figure 1. Generative Detailed Neural Avatars. We propose a method to generate 1) a diverse set of 3D virtual humans of 2) varied identity, gender and shapes, appearing in 3) different clothing styles and poses, with 4) realistic and stochastic details such as wrinkles in garments. Our multi-subject method learns shape, articulation and clothing details from few posed scans without requiring skinning weight supervision. The method is able to synthesize novel identities that are not in the training set and generalizes to unseen poses.

PINA: Learning a Personalized Implicit Neural Avatar from a Single RGB-D Video Sequence

“…Implicit Human Models from 3D Scans Implicit neural representations [14,37,43] can handle topological changes better [10,44] and have been used to reconstruct clothed human shapes [12,26,27,30,48,49,51,52,59]. Typically, based on a learned prior from large-scale datasets, they recover the geometry of clothed humans from images [51,52,59,66] or point clouds [15].…”