ReSpace：基于文本的自回归3D室内场景合成与编辑
ReSpace: Text-Driven Autoregressive 3D Indoor Scene Synthesis and Editing
AI总结：
ReSpace通过自回归方法实现文本驱动的3D室内场景合成与编辑，具备明确房间边界和资产无关部署能力，支持通过自然语言添加、移除和交换物体，实验在物体添加和完整场景合成质量上超越现有方法。
摘要：
场景合成与编辑已成为计算机图形学中的有前景方向。当前训练的3D室内场景生成方法要么通过一热类编码简化物体语义（如'椅子'或'桌子'），要么需要掩码扩散进行编辑，忽略房间边界，或依赖平面渲染无法捕捉复杂布局。基于LLM的方法通过自然语言实现更丰富的语义，但缺乏编辑功能，受限于矩形布局，或依赖隐式世界模型的弱空间推理。我们引入ReSpace，一种生成框架，用于自回归文本驱动的3D室内场景合成与编辑。我们的方法特征是紧凑的结构化场景表示，具有显式房间边界，能够实现资产无关部署，并将场景操控作为下一个token预测任务，支持通过自然语言添加、移除和交换物体。我们采用监督微调与偏好对齐阶段训练专门的对象添加语言模型，考虑用户指令、空间几何、物体语义和场景级组成。我们进一步引入基于体素的评估指标，捕捉超过3D包围盒的细粒度几何违规。实验在物体添加上超越了现有方法，并在完整场景合成应用中实现了更优的人感知质量，尽管未在该任务上进行训练。
英文摘要：
Scene synthesis and editing has emerged as a promising direction in computer graphics. Current trained approaches for 3D indoor scene generation either oversimplify object semantics through one-hot class encodings (e.g., 'chair' or 'table'), require masked diffusion for editing, ignore room boundaries, or rely on floor plan renderings that fail to capture complex layouts. LLM-based methods enable richer semantics via natural language, but lack editing functionality, are limited to rectangular layouts, or rely on weak spatial reasoning from implicit world models. We introduce ReSpace, a generative framework for autoregressive text-driven 3D indoor scene synthesis and editing. Our approach features a compact structured scene representation with explicit room boundaries that enables asset-agnostic deployment and frames scene manipulation as a next-token prediction task, supporting object addition, removal, and swapping via natural language. We employ supervised fine-tuning with a preference alignment stage to train a specialized language model for object addition that accounts for user instructions, spatial geometry, object semantics, and scene-level composition. We further introduce a voxelization-based evaluation metric capturing fine-grained geometric violations beyond 3D bounding boxes. Experiments surpass state-of-the-art on object addition and achieve superior human-perceived quality on the application of full scene synthesis, despite not being trained on it.
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。
