复用三维生成模型进行自回归布局生成
Repurposing 3D Generative Model for Autoregressive Layout Generation
把预训练 3D 扩散模型改造为自回归布局生成器，并用双引导自 rollout 蒸馏提升空间精度与推理效率，为 3D 场景合成提供了一条可复用的「生成模型复用 + 蒸馏加速」路线。
原文依据 employ a dual-guidance self-rollout distillation mechanism to improve efficiency and spatial accuracy
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论本文提出 LaviGen，一个将三维生成模型复用于三维布局生成的框架。与以往从文本描述推断物体布局的方法不同，LaviGen 直接在本征三维空间中运行，将布局生成建模为一个自回归过程，显式建模物体之间的几何关系与物理约束，从而生成连贯且物理上合理的三维场景。为进一步增强该过程，我们提出一种改造后的三维扩散模型，用以整合场景、物体与指令信息，并采用双引导自 rollout 蒸馏机制来提升效率与空间精度。在 LayoutVLM 基准上的大量实验表明，LaviGen 取得了更优的三维布局生成性能，物理合理性比当前最优方法高 19%，计算速度快 65%。我们将公开代码。
英文原文摘要 898 字符
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 to integrate scene, object, and instruction information and employ 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. We will release our code publicly.