Skip to content
Preprint

SpatialGuard: Harness-Guided Verifiable Spatial Reasoning for Text-to-Image Generation

Sep 2026 · 2 citations · 35 references
Computer Science

TL;DR

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.

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.

View source

Similar papers

Preprint Aug 2026

Bridging Language and Spherical Space: Object-Centric Control for Text-to-Panorama Generation

Panoramic image generation is increasingly important for immersive applications such as virtual reality, augmented reality, and 3D content creation. Unlike perspective images, panoramic images represent a viewer-centered $360^\circ$ surrounding space, where directional expressions such as left, right, front, and behind...

De-Rui Li, Qian Qiao, Yuhao Sun et al. · 0 citations
Conference 2026

FlowLess: Controlling Abstract Image Generation

A novel self-supervised framework that enables granular control over image generation through a visual abstraction set that provides a richer, more flexible paradigm for creative design compared to state-of-the-art baselines across diverse styles and compositions is introduced.

Amir Hertz, Noah Snavely · 0 citations
Sep 2026

Planning and Rendering in Concert: DeepFusion of Autoregressive Layouts and Diffusion for Visual Text Generation

DuetGen, an autonomous visual text generator built on DeepFusion, is introduced, which jointly learns autoregressive planning and continuous diffusion rendering and demonstrates the value of jointly learned planning representations and region-specific rendering for autonomous visual text generation.

Guan-Qiao Chen, Jing Tan, Dong-Xing Mao et al. · 0 citations
Preprint Oct 2026

TerraVis: Towards Evaluation of World-Grounded Visual Consistency in Text-to-Image Generation via MLLM Workflows

Recent text-to-image models have made substantial progress in photorealism, aesthetics, and text-image alignment. Yet visually appealing images can still violate real-world plausibility, exhibiting malformed object structures, impossible anatomy, physically implausible interactions, or inconsistent spatial relationship...

Shuai Fu, Jing Gu, Jian Zhou et al. · 0 citations
Preprint Sep 2026

GenPuzzle: Benchmarking Visual Reasoning in Image Generation Models

GenPuzzle provides a testbed for measuring progress from image rendering toward visual problem solving, and uses task-specific evaluation protocols that select the automatic judge by measuring agreement with human reference scores.

Chang-Peng Zhao, Yi-Ren Song, Jin-Peng Wang · 3 citations
#computer vision Preprint Sep 2026

Editable Visual Design

Editable Visual Design is proposed, a new paradigm driven by a Coding Agent that achieves both refined aesthetics and production-grade editability and faithfully reproduces the creative and reasoning trajectory akin to that of professional human designers.

Jun-Yan Ye, Wei Liu, Dongzhi Jiang et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.