Uni-RS: A Spatially Faithful Unified Understanding and Generation Model for Remote Sensing

TL;DR

Uni-RS is a novel remote sensing multimodal model that enhances spatial faithfulness in text-to-image generation by explicitly modeling spatial relations, addressing a key challenge in remote sensing AI.

Contribution

The paper introduces Uni-RS, a unified multimodal model with explicit spatial layout planning and spatial-aware supervision to improve spatial accuracy in remote sensing image generation.

Findings

Significant improvement in spatial faithfulness during text-to-image generation.

Maintains strong performance on understanding tasks like captioning and visual grounding.

Effective systematic spatial transformations enhance model robustness.

Abstract

Unified remote sensing multimodal models exhibit a pronounced spatial reversal curse: Although they can accurately recognize and describe object locations in images, they often fail to faithfully execute the same spatial relations during text-to-image generation, where such relations constitute core semantic information in remote sensing. Motivated by this observation, we propose Uni-RS, the first unified multimodal model tailored for remote sensing, to explicitly address the spatial asymmetry between understanding and generation. Specifically, we first introduce explicit Spatial-Layout Planning to transform textual instructions into spatial layout plans, decoupling geometric planning from visual synthesis. We then impose Spatial-Aware Query Supervision to bias learnable queries toward spatial relations explicitly specified in the instruction. Finally, we develop Image-Caption Spatial Layout Variation to expose the model to systematic geometry-consistent spatial transformations. Extensive experiments across multiple benchmarks show that our approach substantially improves spatial faithfulness in text-to-image generation, while maintaining strong performance on multimodal understanding tasks like image captioning, visual grounding, and VQA tasks.