Repurposing 3D Generative Model for Autoregressive Layout Generation
Haoran Feng, Yifan Niu, Zehuan Huang, Yang-Tian Sun, Chunchao Guo + 2 more
TLDR
LaviGen repurposes 3D generative models for autoregressive 3D layout generation, achieving superior physical plausibility and speed.
Key contributions
- Introduces LaviGen, repurposing 3D generative models for direct 3D autoregressive layout generation.
- Explicitly models geometric relations and physical constraints for coherent and physically plausible 3D scenes.
- Proposes an adapted 3D diffusion model with dual-guidance self-rollout distillation for efficiency.
- Achieves 19% higher physical plausibility and 65% faster computation than state-of-the-art methods.
Why it matters
This paper introduces LaviGen, a novel framework for 3D layout generation that operates directly in 3D space, unlike previous text-based methods. By explicitly modeling geometric and physical constraints, it produces highly plausible and coherent 3D scenes. Its efficiency and accuracy improvements make it a significant step forward for realistic scene synthesis.
Original 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.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.