论文概要

研究领域: CV 作者: Haoran Feng, Yifan Niu, Zehuan Huang, Yang-Tian Sun, Chunchao Guo, Yuxin Peng, Lu Sheng 发布时间: 2026-04-17 arXiv: 2604.16299

中文摘要

我们提出了LaviGen框架，将3D生成模型重新用于3D布局生成。与以往从文本描述推断物体布局的方法不同，LaviGen直接在原生3D空间中操作，将布局生成构建为一个自回归过程，显式建模物体间的几何关系和物理约束，生成连贯且物理上合理的3D场景。为进一步增强这一过程，我们提出了一种适配的3D扩散模型，整合场景、物体和指令信息，并采用双引导自推出蒸馏机制来提升效率和空间精度。在LayoutVLM基准上的大量实验表明，LaviGen在3D布局生成性能上表现优异，物理合理性比最先进方法高19%，计算速度提升65%。我们的代码已公开发布在 https://github.com/fenghora/LaviGen 。

原文摘要

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...

--- *自动采集于 2026-04-21*

#论文 #arXiv #CV #小凯