AvatarVerse: High-quality & Stable 3D Avatar Creation from Text and Pose

TL;DR

AvatarVerse introduces a novel pipeline that generates high-quality, expressive 3D avatars from text and pose guidance, utilizing a 2D diffusion model conditioned on DensePose for view consistency and a progressive synthesis strategy.

Contribution

The paper presents a zero-shot 3D avatar creation method combining DensePose-conditioned diffusion and progressive high-resolution synthesis, improving quality and stability over prior approaches.

Findings

Outperforms previous methods in avatar fidelity and expressiveness.

Achieves stable, view-consistent 3D avatar generation from text and pose.

User studies confirm superior quality and realism.

Abstract

Creating expressive, diverse and high-quality 3D avatars from highly customized text descriptions and pose guidance is a challenging task, due to the intricacy of modeling and texturing in 3D that ensure details and various styles (realistic, fictional, etc). We present AvatarVerse, a stable pipeline for generating expressive high-quality 3D avatars from nothing but text descriptions and pose guidance. In specific, we introduce a 2D diffusion model conditioned on DensePose signal to establish 3D pose control of avatars through 2D images, which enhances view consistency from partially observed scenarios. It addresses the infamous Janus Problem and significantly stablizes the generation process. Moreover, we propose a progressive high-resolution 3D synthesis strategy, which obtains substantial improvement over the quality of the created 3D avatars. To this end, the proposed AvatarVerse pipeline achieves zero-shot 3D modeling of 3D avatars that are not only more expressive, but also in higher quality and fidelity than previous works. Rigorous qualitative evaluations and user studies showcase AvatarVerse's superiority in synthesizing high-fidelity 3D avatars, leading to a new standard in high-quality and stable 3D avatar creation. Our project page is: https://avatarverse3d.github.io