# Global Graph-Validated Optimization for VLM-based 3D Indoor Scene Generation

arXiv: https://arxiv.org/abs/2608.03064 · HTML: https://mlsanity.com/paper/2608.03064/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 42 references that are in the map.
- First posted on arXiv 4 Aug 2026.

## Builds on (most cited first, 8 of 8)

- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior](https://mlsanity.com/paper/2402.04717/) (2024)
- [Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation](https://mlsanity.com/paper/2505.02836/) (2025)
- [Open-Universe Indoor Scene Generation using LLM Program Synthesis and Uncurated Object Databases](https://mlsanity.com/paper/2403.09675/) (2024)
- [Mixed Diffusion for 3D Indoor Scene Synthesis](https://mlsanity.com/paper/2405.21066/) (2024)
- [HSM: Hierarchical Scene Motifs for Multi-Scale Indoor Scene Generation](https://mlsanity.com/paper/2503.16848/) (2025)
- [SceneSeer: 3D Scene Design with Natural Language](https://mlsanity.com/paper/1703.00050/) (2017)
- [CHOrD: Generation of Collision-Free, House-Scale, and Organized Digital Twins for 3D Indoor Scenes with Controllable Floor Plans and Optimal Layouts](https://mlsanity.com/paper/2503.11958/) (2025)

## Built on by (most cited first, 1 of 1)

- [VIGOR: Verifiable Industrial Geometry Optimization and Repair in Scene Programs](https://mlsanity.com/paper/2610.13145/) (2026)

## Abstract (arXiv)

We study open-vocabulary 3D indoor layout generation, which synthesizes diverse and physically plausible scenes from unlabeled 3D assets using free-form language instructions. Recent methods leverage large language models (LLMs) and vision-language models (VLMs) to generate structured scenes from text. However, most model inter-asset relations implicitly or rely on local pairwise constraints and local optimization. These formulations are poorly aligned with the global, highly non-convex layout space, often yielding locally plausible yet globally inconsistent or physically infeasible scenes. We address this problem with a graph-based intermediate representation that separates semantic coherence from physical feasibility, together with a hybrid search-and-refinement strategy. First, Global Semantic Verification (GSV) represents scenes as structured graphs and enforces semantic constraints through rule-based verification. This explicit validation removes contradictory configurations and produces a globally consistent semantic scaffold. Second, Global Physical Feasibility Search (GPFS) combines evolutionary search for global exploration with gradient-based refinement for local exploitation. It reduces dependence on VLM-proposed initialization and improves robustness in non-convex and discontinuous feasible spaces. Together, GSV and GPFS move layout generation beyond local relational modeling and initialization-sensitive optimization toward globally consistent reasoning and search. Experiments show that our method achieves state-of-the-art performance in open-vocabulary 3D indoor layout generation, improving both semantic consistency and physical plausibility.