DreamHuman: Animatable 3D Avatars from Text

TL;DR

DreamHuman is a novel method that generates high-quality, animatable 3D human avatars from textual descriptions, integrating text-to-image models, neural radiance fields, and statistical body models for realistic and diverse results.

Contribution

It introduces a new framework combining large text-to-image models, neural radiance fields, and human body models to produce animated 3D avatars from text descriptions.

Findings

Generates diverse, realistic 3D human avatars from text

Outperforms existing text-to-3D methods in visual fidelity

Produces high-quality textures and realistic animations

Abstract

We present DreamHuman, a method to generate realistic animatable 3D human avatar models solely from textual descriptions. Recent text-to-3D methods have made considerable strides in generation, but are still lacking in important aspects. Control and often spatial resolution remain limited, existing methods produce fixed rather than animated 3D human models, and anthropometric consistency for complex structures like people remains a challenge. DreamHuman connects large text-to-image synthesis models, neural radiance fields, and statistical human body models in a novel modeling and optimization framework. This makes it possible to generate dynamic 3D human avatars with high-quality textures and learned, instance-specific, surface deformations. We demonstrate that our method is capable to generate a wide variety of animatable, realistic 3D human models from text. Our 3D models have diverse appearance, clothing, skin tones and body shapes, and significantly outperform both generic text-to-3D approaches and previous text-based 3D avatar generators in visual fidelity. For more results and animations please check our website at https://dream-human.github.io.