GeoSceneGraph：用于文本引导3D室内场景合成的几何场景图扩散模型
GeoSceneGraph: Geometric Scene Graph Diffusion Model for Text-guided 3D Indoor Scene Synthesis
AI总结：
针对现有文本引导3D室内场景合成方法存在的场景连贯性不足、依赖额外标注或预定义关系等问题，提出GeoSceneGraph模型，基于EGNN融合场景图结构与几何对称性，无需预定义关系即可达到可比性能。
摘要：
根据文本提示合成室内3D场景的方法在电影制作、室内设计、电子游戏、虚拟现实以及用于训练具身智能体的合成数据生成领域有着广泛应用。现有方法通常要么从头训练生成模型，要么利用视觉语言模型（VLM）。尽管VLM表现优异，尤其在处理复杂或开放式提示时效果突出，但在扩展现实（XR）眼镜、手机等资源受限设备上部署时，仍需要更小的特定任务模型。然而，许多从头训练的生成方法忽略了室内场景固有的图结构，这会限制场景的连贯性与真实感。相反，融入场景图的方法要么需要用户提供语义图，这通常既不便又存在限制，要么依赖真值关系标注，限制了其捕捉更多样物体交互的能力。为解决这些挑战，我们提出GeoSceneGraph，该方法利用3D场景的图结构与几何对称性，根据文本提示合成3D场景，无需依赖预定义关系类别。尽管未使用真值关系，GeoSceneGraph仍取得了与使用真值关系的方法相当的性能。我们的模型基于等变图神经网络（EGNN）构建，但现有EGNN方法通常受限于低维条件输入，不适用于处理文本这类复杂模态。我们提出了一种简单有效的策略让EGNN以文本特征为条件，并通过消融实验验证了设计的有效性。
英文摘要：
Methods that synthesize indoor 3D scenes from text prompts have wide-ranging applications in film production, interior design, video games, virtual reality, and synthetic data generation for training embodied agents. Existing approaches typically either train generative models from scratch or leverage vision-language models (VLMs). While VLMs achieve strong performance, particularly for complex or open-ended prompts, smaller task-specific models remain necessary for deployment on resource-constrained devices such as extended reality (XR) glasses or mobile phones. However, many generative approaches that train from scratch overlook the inherent graph structure of indoor scenes, which can limit scene coherence and realism. Conversely, methods that incorporate scene graphs either demand a user-provided semantic graph, which is generally inconvenient and restrictive, or rely on ground-truth relationship annotations, limiting their capacity to capture more varied object interactions. To address these challenges, we introduce GeoSceneGraph, a method that synthesizes 3D scenes from text prompts by leveraging the graph structure and geometric symmetries of 3D scenes, without relying on predefined relationship classes. Despite not using ground-truth relationships, GeoSceneGraph achieves performance comparable to methods that do. Our model is built on equivariant graph neural networks (EGNNs), but existing EGNN approaches are typically limited to low-dimensional conditioning and are not designed to handle complex modalities such as text. We propose a simple and effective strategy for conditioning EGNNs on text features, and we validate our design through ablation studies.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
