Uni3D-LLM: Unifying Point Cloud Perception, Generation and Editing with Large Language Models

TL;DR

Uni3D-LLM introduces a unified framework utilizing a Large Language Model to perform 3D perception, generation, and editing of point cloud scenes through natural language commands, enhancing flexibility and control.

Contribution

This work presents the first LLM-based unified system for 3D point cloud perception, generation, and editing, enabling natural language-guided manipulation of 3D scenes.

Findings

Effective integration of perception, generation, and editing tasks.

High accuracy in 3D object instantiation and modification.

Demonstrated practical potential in interactive 3D design.

Abstract

In this paper, we introduce Uni3D-LLM, a unified framework that leverages a Large Language Model (LLM) to integrate tasks of 3D perception, generation, and editing within point cloud scenes. This framework empowers users to effortlessly generate and modify objects at specified locations within a scene, guided by the versatility of natural language descriptions. Uni3D-LLM harnesses the expressive power of natural language to allow for precise command over the generation and editing of 3D objects, thereby significantly enhancing operational flexibility and controllability. By mapping point cloud into the unified representation space, Uni3D-LLM achieves cross-application functionality, enabling the seamless execution of a wide array of tasks, ranging from the accurate instantiation of 3D objects to the diverse requirements of interactive design. Through a comprehensive suite of rigorous experiments, the efficacy of Uni3D-LLM in the comprehension, generation, and editing of point cloud has been validated. Additionally, we have assessed the impact of integrating a point cloud perception module on the generation and editing processes, confirming the substantial potential of our approach for practical applications.