SpatialGuard: Harness-Guided Verifiable Spatial Reasoning for Text-to-Image Generation
2026-09-01 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed SpatialGuard to help computers create 3D images from text in a way that keeps the spatial arrangement accurate. Their system breaks down text into 3D layouts, generates images based on these layouts, and checks to make sure the images match both the text and layout. They also created a method to keep these layouts stable and fix errors during the image creation process. Their experiments show this approach is better at maintaining complex spatial relationships than previous methods.
3D spatial text-to-image generationlayout-conditioned generationvisual alignmentprompt parsingspatial layoutimage synthesisocclusioncamera constraintsfeedback loopstructured generation
Authors
Ziyun Qian, Zizhi Chen, Yizhou Liu, Mingyang Sun, Dingkang Yang, Lihua Zhang
Abstract
Complex 3D spatial text to image generation requires models to convert natural language into stable visual geometry, not merely semantic appearance. Existing prompt-driven or layout-conditioned methods improve controllability, but often lack an optimizable and verifiable spatial intermediary before visual sampling. As a result, object relations, occlusion, visibility, and camera constraints can decay during multi-round generation. This paper presents SpatialGuard, a structured layout-guided framework for complex 3D spatial text-to-image generation. SpatialGuard parses prompts into image synthesis-oriented 3D layouts through a Spatial Layout Architect, realizes them as visual conditions and candidate images through a Visual Realizer, and uses a Visual Alignment Critic to validate consistency among prompt, layout, and image. To keep constraints stable across iterations, SpatialGuard introduces a Layout Harness that organizes rule constraints, tool invocation, shared knowledge, and feedback loops around the editable layout state. This design turns complex spatial generation from implicit prompt following into a verifiable process of planning, realization, validation, and repair. Comprehensive experiments show that SpatialGuard achieves state-of-the-art performance in complex 3D spatial layout generation and improves spatial faithfulness over existing text-to-image and layout control baselines.