Search papers, labs, and topics across Lattice.
This paper introduces a method for geometry-controlled high-resolution satellite image synthesis using pre-trained diffusion models to address the scarcity of such images. The approach leverages skip connection features with windowed cross-attention modules to control the synthesis process based on geometric input. Results show comparable performance to existing control techniques with improved alignment to the geometry control map, while also highlighting limitations in current evaluation metrics.
Synthesizing high-resolution satellite imagery with geometric precision is now more efficient, thanks to a windowed cross-attention method that rivals existing techniques while better respecting geometric constraints.
High-resolution satellite images are often scarce and costly, especially for remote areas or infrequent events. This shortage hampers the development and testing of machine learning models for land-cover classification, change detection, and disaster monitoring. In this paper, we tackle the problem of geometry-controlled high-resolution satellite image synthesis by adding control over existing pre-trained diffusion models. We propose a simple yet efficient method for controlling the synthesis process by leveraging only skip connection features using windowed cross-attention modules. Several previously established control techniques are compared, indicating that our method achieves comparable performance while leading to a better alignment with the geometry control map. We also discuss the limitations in current evaluation approaches, amplifying the necessity of a consistent alignment assessment.