ATT-CR: Adaptive Triangular Transformer for Cloud Removal

Yang Wu

doi:10.1109/JSTARS.2025.3596856

ATT-CR: Adaptive Triangular Transformer for Cloud Removal

2025-01-01

0

OA

AI

DOI：10.1109/JSTARS.2025.3596856

Original

Original request for help

Save

Abstract

En 中文

Cloud removal aims to accurately reconstruct the ground objects obscured by clouds in remote sensing images. Existing transformer-based methods utilizing self-attention have shown impressive results by effectively modeling long-range dependencies in cloudy images. However, they suffer from the following issues: 1) the high computational complexity of self-attention limits scalability; 2) treating both cloudy and clean pixels as valid within the attention computation brings disturbances in subsequent layers, leading to suboptimal performance. To address these challenges, we propose the adaptive triangular transformer for cloud removal (ATT-CR), a model that effectively reduces computational costs and mitigates interference from cloudy pixels. Specifically, it consists of two core components: Triangular attention (TAN) and feature selected gating module (FSGM). TAN employs lower and upper triangular matrices to approximate softmax attention with $\mathcal {O}(N)$ computational complexity, significantly reducing the computational costs. The FSGM, on the other hand, integrates with TAN to adaptively distinguish between cloudy and clean features, which minimizes the introduction of invalid information into subsequent layers. Extensive experiments on cloud removal benchmarks demonstrate that ATT-CR delivers superior performance compared to existing methods.

Keywords:

Adaptive feature selection

cloud removal

image reconstruction

remote sensing images

triangular attention (TAN)

ATT-CR: Adaptive Triangular Transformer for Cloud Removal

Abstract

Journal

Organization