MultiDreamer3D: Multi-concept 3D Customization with Concept-Aware Diffusion Guidance

TL;DR

MultiDreamer3D introduces a novel approach for multi-concept 3D customization by integrating layout control, selective point cloud generation, and concept-aware diffusion, enabling coherent multi-object 3D content creation.

Contribution

It is the first method to address multi-concept 3D customization, combining large language model-based layout, point cloud generation, and diffusion guidance for detailed control.

Findings

Ensures object presence and concept identity preservation.

Handles complex property changes and interactions.

Achieves coherent multi-concept 3D content generation.

Abstract

While single-concept customization has been studied in 3D, multi-concept customization remains largely unexplored. To address this, we propose MultiDreamer3D that can generate coherent multi-concept 3D content in a divide-and-conquer manner. First, we generate 3D bounding boxes using an LLM-based layout controller. Next, a selective point cloud generator creates coarse point clouds for each concept. These point clouds are placed in the 3D bounding boxes and initialized into 3D Gaussian Splatting with concept labels, enabling precise identification of concept attributions in 2D projections. Finally, we refine 3D Gaussians via concept-aware interval score matching, guided by concept-aware diffusion. Our experimental results show that MultiDreamer3D not only ensures object presence and preserves the distinct identities of each concept but also successfully handles complex cases such as property change or interaction. To the best of our knowledge, we are the first to address the multi-concept customization in 3D.