Guide3D: Create 3D Avatars from Text and Image Guidance

TL;DR

Guide3D is a novel zero-shot 3D avatar generation model that leverages diffusion models and multi-view image features to produce high-quality textured 3D meshes from text and images.

Contribution

It introduces a new framework combining diffusion models with differentiable grids and feature fusion for high-resolution 3D avatar synthesis from text and images.

Findings

Outperforms state-of-the-art in geometry and texture quality

Effectively transfers 2D image features to 3D models

Enhances 3D generation with novel training objectives

Abstract

Recently, text-to-image generation has exhibited remarkable advancements, with the ability to produce visually impressive results. In contrast, text-to-3D generation has not yet reached a comparable level of quality. Existing methods primarily rely on text-guided score distillation sampling (SDS), and they encounter difficulties in transferring 2D attributes of the generated images to 3D content. In this work, we aim to develop an effective 3D generative model capable of synthesizing high-resolution textured meshes by leveraging both textual and image information. To this end, we introduce Guide3D, a zero-shot text-and-image-guided generative model for 3D avatar generation based on diffusion models. Our model involves (1) generating sparse-view images of a text-consistent character using diffusion models, and (2) jointly optimizing multi-resolution differentiable marching tetrahedral grids with pixel-aligned image features. We further propose a similarity-aware feature fusion strategy for efficiently integrating features from different views. Moreover, we introduce two novel training objectives as an alternative to calculating SDS, significantly enhancing the optimization process. We thoroughly evaluate the performance and components of our framework, which outperforms the current state-of-the-art in producing topologically and structurally correct geometry and high-resolution textures. Guide3D enables the direct transfer of 2D-generated images to the 3D space. Our code will be made publicly available.