Uni-RS：面向遥感的空间忠实统一理解与生成模型

View PDF HTML (experimental)

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.

Subjects:	Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
Cite as:	arXiv:2601.17673 [cs.CV]
	(or arXiv:2601.17673v2 [cs.CV] for this version)
	https://doi.org/10.48550/arXiv.2601.17673 arXiv-issued DOI via DataCite

Submission history

From: Weiyu Zhang [view email]
[v1] Sun, 25 Jan 2026 03:22:26 UTC (11,026 KB)
[v2] Tue, 13 Oct 2026 03:36:12 UTC (13,819 KB)