AvatarGen: a 3D Generative Model for Animatable Human Avatars

by   Jianfeng Zhang, et al.

Unsupervised generation of clothed virtual humans with various appearance and animatable poses is important for creating 3D human avatars and other AR/VR applications. Existing methods are either limited to rigid object modeling, or not generative and thus unable to synthesize high-quality virtual humans and animate them. In this work, we propose AvatarGen, the first method that enables not only non-rigid human generation with diverse appearance but also full control over poses and viewpoints, while only requiring 2D images for training. Specifically, it extends the recent 3D GANs to clothed human generation by utilizing a coarse human body model as a proxy to warp the observation space into a standard avatar under a canonical space. To model non-rigid dynamics, it introduces a deformation network to learn pose-dependent deformations in the canonical space. To improve geometry quality of the generated human avatars, it leverages signed distance field as geometric representation, which allows more direct regularization from the body model on the geometry learning. Benefiting from these designs, our method can generate animatable human avatars with high-quality appearance and geometry modeling, significantly outperforming previous 3D GANs. Furthermore, it is competent for many applications, e.g., single-view reconstruction, reanimation, and text-guided synthesis. Code and pre-trained model will be available.


Neural Actor: Neural Free-view Synthesis of Human Actors with Pose Control

We propose Neural Actor (NA), a new method for high-quality synthesis of...

DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Models

We present DreamAvatar, a text-and-shape guided framework for generating...

3D-Aware Semantic-Guided Generative Model for Human Synthesis

Generative Neural Radiance Field (GNeRF) models, which extract implicit ...

DreamHuman: Animatable 3D Avatars from Text

We present DreamHuman, a method to generate realistic animatable 3D huma...

AG3D: Learning to Generate 3D Avatars from 2D Image Collections

While progress in 2D generative models of human appearance has been rapi...

USR: Unsupervised Separated 3D Garment and Human Reconstruction via Geometry and Semantic Consistency

Dressed people reconstruction from images is a popular task with promisi...

Lifting AutoEncoders: Unsupervised Learning of a Fully-Disentangled 3D Morphable Model using Deep Non-Rigid Structure from Motion

In this work we introduce Lifting Autoencoders, a generative 3D surface-...

Please sign up or login with your details

Forgot password? Click here to reset