VectorSynth: Fine-Grained Satellite Image Synthesis with Structured Semantics

TL;DR

VectorSynth is a diffusion-based framework for satellite image synthesis that uses polygonal geographic annotations and semantic attributes for pixel-accurate, spatially grounded image editing and generation.

Contribution

It introduces a novel cross-modal correspondence learning approach that aligns imagery with semantic vector geometry for fine-grained, spatially aware satellite image synthesis.

Findings

Outperforms prior methods in semantic fidelity and realism

Supports interactive spatial edits and map-informed content generation

Demonstrates effective fine-grained spatial grounding with a vision language model

Abstract

We introduce VectorSynth, a diffusion-based framework for pixel-accurate satellite image synthesis conditioned on polygonal geographic annotations with semantic attributes. Unlike prior text- or layout-conditioned models, VectorSynth learns dense cross-modal correspondences that align imagery and semantic vector geometry, enabling fine-grained, spatially grounded edits. A vision language alignment module produces pixel-level embeddings from polygon semantics; these embeddings guide a conditional image generation framework to respect both spatial extents and semantic cues. VectorSynth supports interactive workflows that mix language prompts with geometry-aware conditioning, allowing rapid what-if simulations, spatial edits, and map-informed content generation. For training and evaluation, we assemble a collection of satellite scenes paired with pixel-registered polygon annotations spanning diverse urban scenes with both built and natural features. We observe strong improvements over prior methods in semantic fidelity and structural realism, and show that our trained vision language model demonstrates fine-grained spatial grounding. The code and data are available at https://github.com/mvrl/VectorSynth.