Orchestrating Spatial Semantics via a Zone-Graph Paradigm for Intricate Indoor Scene Generation

2026-05-04

AI Summary

Existing methods struggle to simultaneously preserve semantic coherence and geometric plausibility when generating layouts for non-convex, high-density indoor scenes. This work proposes ZoneMaestro, a novel framework that introduces a zone-graph–centric generative paradigm, leveraging high-level semantic intent to produce functional zones and their topological constraints, thereby achieving robust adaptability across diverse architectural forms. We present Zone-Scene-10K, the first large-scale dataset with explicit zone-graph annotations, along with SCALE—a new benchmark task—and introduce Zone-Aware Group Relative Policy Optimization (Z-GRPO) coupled with an internalized zone-graph reasoning mechanism. This approach harmonizes semantic richness and geometric validity without relying on physics engines. Experiments demonstrate that our method significantly outperforms prior art in structural consistency and intent adherence, effectively resolving the tension between safety and plausibility in dense layout generation.

Abstract

Autonomous 3D indoor scene synthesis breaks down in non-convex rooms with tightly coupled spatial constraints. Data-driven generators lack topological priors for long-horizon planning, while iterative agents fragment semantics and become geometrically brittle. We present ZoneMaestro, a unified framework that shifts the paradigm from object-centric synthesis to Zone-Graph Orchestration. By internalizing a novel zone-based logic, ZoneMaestro translates high-level semantic intent into functional zones and topological constraints, enabling robust adaptation to diverse architectural forms. To support this, we construct Zone-Scene-10K, a large-scale dataset enriched with explicit Zone-Graph annotations. We further introduce an Alternating Alignment Strategy that cycles between reasoning internalization and Zone-Aware Group Relative Policy Optimization (Z-GRPO), effectively reconciling the tension between semantic richness and geometric validity without relying on external physics engines. To rigorously evaluate spatial intelligence beyond convex primitives, we formally define the task of Intricate Spatial Orchestration and release SCALE, a stress-test benchmark for irregular indoor scenarios with complex, dense spatial relations. Extensive experiments demonstrate that ZoneMaestro resolves the density-safety dichotomy, significantly outperforming state-of-the-art baselines in both structural coherence and intent adherence.

Problem

• indoor scene generation
• spatial semantics
• non-convex rooms
• topological constraints
• spatial orchestration

Innovation

• Zone-Graph
• Spatial Semantics
• Indoor Scene Generation
• Topological Constraints
• Z-GRPO