Comp4D: LLM-Guided Compositional 4D Scene Generation

TL;DR

Comp4D introduces a novel framework for compositional 4D scene generation that constructs individual objects separately and employs LLMs and diffusion models to produce high-quality, dynamic 4D content from text prompts.

Contribution

The paper presents a new compositional approach for 4D scene generation using LLMs and diffusion models, enabling object-wise construction and trajectory-based scene synthesis.

Findings

Outperforms prior methods in visual quality and motion fidelity.

Demonstrates effective object interaction and scene dynamics.

Achieves versatile 4D content creation across multiple domains.

Abstract

Recent advancements in diffusion models for 2D and 3D content creation have sparked a surge of interest in generating 4D content. However, the scarcity of 3D scene datasets constrains current methodologies to primarily object-centric generation. To overcome this limitation, we present Comp4D, a novel framework for Compositional 4D Generation. Unlike conventional methods that generate a singular 4D representation of the entire scene, Comp4D innovatively constructs each 4D object within the scene separately. Utilizing Large Language Models (LLMs), the framework begins by decomposing an input text prompt into distinct entities and maps out their trajectories. It then constructs the compositional 4D scene by accurately positioning these objects along their designated paths. To refine the scene, our method employs a compositional score distillation technique guided by the pre-defined trajectories, utilizing pre-trained diffusion models across text-to-image, text-to-video, and text-to-3D domains. Extensive experiments demonstrate our outstanding 4D content creation capability compared to prior arts, showcasing superior visual quality, motion fidelity, and enhanced object interactions.