Repurposing 3D Generative Model for Autoregressive Layout Generation

TL;DR

LaviGen is a novel framework that repurposes 3D generative models for autoregressive 3D layout generation, explicitly modeling geometric and physical relations to produce coherent scenes.

Contribution

It introduces a new autoregressive approach with an adapted 3D diffusion model and a dual-guidance distillation mechanism, achieving superior performance and efficiency.

Findings

19% higher physical plausibility than the state of the art

65% faster computation

Effective in generating coherent 3D scenes

Abstract

We introduce LaviGen, a framework that repurposes 3D generative models for 3D layout generation. Unlike previous methods that infer object layouts from textual descriptions, LaviGen operates directly in the native 3D space, formulating layout generation as an autoregressive process that explicitly models geometric relations and physical constraints among objects, producing coherent and physically plausible 3D scenes. To further enhance this process, we propose an adapted 3D diffusion model that integrates scene, object, and instruction information and employs a dual-guidance self-rollout distillation mechanism to improve efficiency and spatial accuracy. Extensive experiments on the LayoutVLM benchmark show LaviGen achieves superior 3D layout generation performance, with 19% higher physical plausibility than the state of the art and 65% faster computation. Our code is publicly available at https://github.com/fenghora/LaviGen.