Make-Your-3D: Fast and Consistent Subject-Driven 3D Content Generation

TL;DR

Make-Your-3D is a fast, subject-specific 3D content generation method that personalizes high-fidelity 3D models from a single image and text prompt within 5 minutes, ensuring consistency and diversity.

Contribution

The paper introduces a novel co-evolution framework that harmonizes multi-view diffusion and 2D generative models for personalized 3D content creation from minimal input.

Findings

Produces high-quality, consistent 3D models from a single image.

Enables text-driven modifications of 3D content unseen in the original image.

Generates subject-specific 3D content within 5 minutes.

Abstract

Recent years have witnessed the strong power of 3D generation models, which offer a new level of creative flexibility by allowing users to guide the 3D content generation process through a single image or natural language. However, it remains challenging for existing 3D generation methods to create subject-driven 3D content across diverse prompts. In this paper, we introduce a novel 3D customization method, dubbed Make-Your-3D that can personalize high-fidelity and consistent 3D content from only a single image of a subject with text description within 5 minutes. Our key insight is to harmonize the distributions of a multi-view diffusion model and an identity-specific 2D generative model, aligning them with the distribution of the desired 3D subject. Specifically, we design a co-evolution framework to reduce the variance of distributions, where each model undergoes a process of learning from the other through identity-aware optimization and subject-prior optimization, respectively. Extensive experiments demonstrate that our method can produce high-quality, consistent, and subject-specific 3D content with text-driven modifications that are unseen in subject image.