发表机构
Seoul National University（首尔大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出场景重定向框架，通过簇级类比迁移跨布局稳定传递语义空间组织，在3D-FRONT数据集上超越现有方法，并支持真实到仿真迁移等下游应用。
AI 中文摘要
具身智能或空间计算应用的交互式模拟建立在支持日常活动的逼真3D场景之上。然而，稀疏、不规则的布局结构施加了场景特定的物理约束，使得难以定义用于生成类似功能上下文的通用框架。我们将场景重定向形式化为跨布局稳定地迁移语义连贯的空间组织，而非依赖文本描述或成对关系。我们的簇级迁移灵活地处理不匹配的物体实例，并适应独特的平面图。我们通过尊重基础特征的空间分布来优化，以保留单个簇的丰富语义上下文。然后，我们可以施加物理约束来细化墙壁接触、成对对齐，或清理通道和开口。我们的框架在3D-FRONT数据集上的布局生成任务中优于最先进的方法，并展示了包括真实到仿真迁移、类比轨迹迁移和多参考组合在内的下游应用。
英文摘要
Interactive simulations of embodied AI or spatial computing applications build on realistic 3D scenes that support daily activities. However, sparse, irregular layout structures impose scene-specific physical constraints, making it hard to define a generalizable framework for generating similar functional context. We formalize Scene Retargeting as stably transferring the semantically coherent spatial organization across layouts, rather than relying on textual descriptions or pairwise relationships. Our cluster-wise transfer flexibly handles mismatched object instances and adapts to distinctive floor plans. We optimize to preserve the rich semantic context of individual clusters by respecting the spatial distribution of foundation features. We can then impose physical constraints to refine wall contacts, pairwise alignment, or clear passageways and openings. Our framework outperforms state-of-the-art methods on layout generation on the 3D-FRONT dataset, and demonstrates downstream applications including real-to-sim transfer, analogical trajectory transfer, and multi-reference composition.
CommentsProject page: https://mkjjang3598.github.io/Scene-Retargeting/
