SceneNAT：基于语言引导的室内场景合成的掩码生成模型
SceneNAT: Masked Generative Modeling for Language-Guided Indoor Scene Synthesis
AI总结：
SceneNAT通过掩码非自回归Transformer实现语言引导的室内场景合成，提升性能与效率，同时降低计算成本。
摘要：
我们提出了SceneNAT，一种单阶段的掩码非自回归Transformer，仅通过少数并行解码步骤即可从自然语言指令合成完整的3D室内场景，相较于先前最先进的方法，在性能和效率上均有提升。SceneNAT通过掩码建模来训练，使用完全离散化的语义和空间属性表示。通过在属性层面和实例层面应用掩码策略，模型能够更好地捕捉物体内部和物体之间的结构。为了增强关系推理，SceneNAT采用专门的三元组预测器，通过将一组可学习的关系查询映射到稀疏的符号三元组（主体，谓词，客体）来建模场景的布局和物体关系。在3D-FRONT数据集上的大量实验表明，SceneNAT在语义符合性和空间排列准确性方面均优于最先进的自回归和扩散基线，同时计算成本显著降低。
英文摘要：
We present SceneNAT, a masked non-autoregressive Transformer for 3D indoor scene synthesis from natural language instructions. It generates complete scenes in a few parallel decoding passes, improving both quality and efficiency over prior methods. SceneNAT is trained via masked modeling over fully discretized representations of both semantic and spatial attributes. By applying a masking strategy at both the attribute level and the instance level, the model can better capture intra-object and inter-object structure. To boost relational reasoning, SceneNAT employs a relational reasoning module (RRM) that captures implicit spatial constraints. By formulating relation modeling as a set prediction task, it extracts structure-aware features to guide the layout generation without explicit sequential parsing. Extensive experiments on 3D-FRONT show that SceneNAT outperforms state-of-the-art autoregressive and diffusion baselines in both semantic compliance and spatial arrangement accuracy while using substantially lower computational cost, enabling high-throughput generation of diverse scenes at scale.
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。
