Aladdin: Zero-Shot Hallucination of Stylized 3D Assets from Abstract Scene Descriptions

TL;DR

This paper introduces Aladdin, a system leveraging foundation models to generate stylized 3D scene assets from abstract descriptions, enabling open-world creativity and reducing reliance on limited datasets.

Contribution

Aladdin is the first system to translate abstract scene descriptions into stylized 3D assets using foundation models with an interpretable, controllable pipeline.

Findings

Achieves 91% human-rated semantic faithfulness

Uses a multi-model foundation approach for open-world concepts

Introduces novel metrics for stylized 3D asset generation

Abstract

What constitutes the "vibe" of a particular scene? What should one find in "a busy, dirty city street", "an idyllic countryside", or "a crime scene in an abandoned living room"? The translation from abstract scene descriptions to stylized scene elements cannot be done with any generality by extant systems trained on rigid and limited indoor datasets. In this paper, we propose to leverage the knowledge captured by foundation models to accomplish this translation. We present a system that can serve as a tool to generate stylized assets for 3D scenes described by a short phrase, without the need to enumerate the objects to be found within the scene or give instructions on their appearance. Additionally, it is robust to open-world concepts in a way that traditional methods trained on limited data are not, affording more creative freedom to the 3D artist. Our system demonstrates this using a foundation model "team" composed of a large language model, a vision-language model and several image diffusion models, which communicate using an interpretable and user-editable intermediate representation, thus allowing for more versatile and controllable stylized asset generation for 3D artists. We introduce novel metrics for this task, and show through human evaluations that in 91% of the cases, our system outputs are judged more faithful to the semantics of the input scene description than the baseline, thus highlighting the potential of this approach to radically accelerate the 3D content creation process for 3D artists.