ATT-CR: Adaptive Triangular Transformer for Cloud Removal
Researchers have developed ATT-CR, an Adaptive Triangular Transformer model designed for cloud removal in remote sensing images. This new model addresses the computational complexity and interference issues found in existing Transformer-based methods. ATT-CR utilizes Triangular Attention and a Feature Selected Gating Module to efficiently process images and minimize the impact of cloudy pixels, leading to improved performance on cloud removal benchmarks. AI
IMPACT Introduces a more efficient Transformer architecture for image processing tasks, potentially improving performance in remote sensing applications.