SDGScenes: User-intent driven indoor scene generation via semantic dependency graph

3D indoor scene generation aims to generate scenes that are physically plausible, consistent with common sense, and well-aligned with user intent. However, existing methods struggle to effectively capture user intent, as coarse-grained instruction methods yield plausible but intent-missing layouts, while fine-grained instruction methods reflect user intent but rely on manually defined relationships that burden users and compromise physical plausibility in complex scenes. To address this challenge, we propose SDGScenes, a novel framework that automatically infers and synthesizes complete indoor scenes from user intent and commonsense knowledge. Our approach firstly encodes scene requirements using a Semantic Dependency Graph (SDG), a representation that captures both user-intent and module relationships. Sequentially, guided by the SDG, a Vision-Language Model (VLM) infers spatial constraints through commonsense reasoning. Finally, an optimization solver is applied to optimize object placement based on SDG-guided spatial constraints, including collision avoidance, boundary compliance, and reachability. Both quantitative and qualitative experimental results demonstrate that SDGScenes outperforms state-of-the-art methods in satisfying user intent.