SDesc3D：面向布局感知的短描述驱动的3D室内场景生成
SDesc3D: Towards Layout-Aware 3D Indoor Scene Generation from Short Descriptions
AI总结：
本文提出SDesc3D框架，通过多视角结构先验和区域功能暗示实现短描述驱动的3D室内场景生成，提升物理合理性和细节丰富度。
摘要：
基于短文本描述的3D室内场景生成为构建交互式3D环境提供了新途径，无需人工密集布局指定。尽管近期在文本条件3D场景生成方面取得进展，现有方法在语义压缩情况下存在物理合理性差和细节不足的问题，主要由于依赖显式语义线索。为此，我们提出SDesc3D框架，利用多视角结构先验和区域功能暗示实现3D布局推理。具体而言，我们引入多视角场景先验增强，通过聚合多视角结构知识丰富未指定文本输入，从不可达的语义关系线索转向多视角关系先验聚合。在此基础上，我们设计功能感知的布局定位，利用区域功能定位隐式空间锚点，并进行层次布局推理以增强场景组织和语义合理性。此外，采用迭代反思-校正方案进行渐进结构合理性校正。大量实验表明，我们的方法在短文本条件3D室内场景生成中优于现有方法。代码将公开提供。
英文摘要：
3D indoor scene generation conditioned on short textual descriptions provides a promising avenue for interactive 3D environment construction without the need for labor-intensive layout specification. Despite recent progress in text-conditioned 3D scene generation, existing works suffer from poor physical plausibility and insufficient detail richness in such semantic condensation cases, largely due to their reliance on explicit semantic cues about compositional objects and their spatial relationships. This limitation highlights the need for enhanced 3D reasoning capabilities, particularly in terms of prior integration and spatial anchoring. Motivated by this, we propose SDesc3D, a short-text conditioned 3D indoor scene generation framework, that leverages multi-view structural priors and regional functionality implications to enable 3D layout reasoning under sparse textual guidance. Specifically, we introduce a Multi-view scene prior augmentation that enriches underspecified textual inputs with aggregated multi-view structural knowledge, shifting from inaccessible semantic relation cues to multi-view relational prior aggregation. Building on this, we design a Functionality-aware layout grounding, employing regional functionality grounding for implicit spatial anchors and conducting hierarchical layout reasoning to enhance scene organization and semantic plausibility. Furthermore, an Iterative reflection-rectification scheme is employed for progressive structural plausibility refinement via self-rectification. Extensive experiments show that our method outperforms existing approaches on short-text conditioned 3D indoor scene generation. Code will be publicly available.
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。
