Repurposing 3D Generative Model for Autoregressive Layout Generation

2026-04-17

AI Summary

Existing approaches struggle to generate 3D scene layouts that simultaneously satisfy physical plausibility and structural coherence. This work proposes a native 3D autoregressive layout generation method that integrates scene context, object geometry, and textual instructions through a 3D diffusion model. To explicitly model inter-object geometric relationships and physical constraints, the approach introduces a dual-guided self-unfolding distillation mechanism. Evaluated on the LayoutVLM benchmark, the proposed method achieves a 19% improvement in physical plausibility and a 65% acceleration in inference speed, significantly outperforming current state-of-the-art methods.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Planning, Routing, and Scheduling: Planning with Language Models
• Natural Language Processing: Generation

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

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.

Problem

• 3D layout generation
• autoregressive generation
• physical plausibility
• geometric relations
• 3D generative models

Innovation

• autoregressive layout generation
• 3D generative model repurposing
• geometric relations modeling
• dual-guidance distillation
• physically plausible 3D scenes