GDiT: A graph-prior-guided diffusion transformer for semantic-controllable remote sensing image synthesis

Semantic image synthesis (SIS) is essential for remote sensing, particularly in generating high-quality training data for scarce annotated datasets. While existing SIS methods have advanced pixel-wise mappings between semantic maps and images, they often overlook spatial priors, such as relationships between geographic objects (e.g., road-building adjacency), leading to structural inconsistencies in synthesized images. To address this, we propose the graph-prior diffusion transformer (GDiT) for semantically controllable remote sensing image synthesis. We first convert semantic maps into semantic graphs, encoding geographic objects as nodes with structured spatial interactions. To capture spatial and semantic relationships, we propose the Geometric-Semantic Aware Module (GSAM), which integrates CLIP-extracted semantics and geometric attributes for a more context-aware representation. Furthermore, we design the Graph Diffusion Transformer (GDiT) Block, which employs graph-to-image cross-attention to refine spatial structures, ensuring topological coherence and semantic fidelity in synthesized images. Experiments on the landcover and landuse dataset show that GDiT achieves competitive performance by incorporating text prompts to enable multilevel control across global, object and pixel dimensions, generating high-fidelity images while using only 38.9% of the parameters compared to GeoSynth, significantly improving efficiency and accuracy. The code and dataset will be released at https://github.com/whudk/GDiT . • Graph-prior guided diffusion transformer enables multilevel semantic control. • Achieves high-fidelity land-cover and land-use image synthesis with fewer parameters. • Supports semantic editing and hierarchical generation for practical remote sensing applications.