提出双掩码自适应卷积，高效提升遥感图像融合质量
DMAConv: Dual Mask-Adaptive Convolution for Remote Sensing Pansharpening
- 通过软硬掩码动态分配计算资源，分两路处理不同特征
- 在多个基准上达顶尖性能，参数量和计算开销均最低
- 适合需要高效高质遥感图像融合的科研与工程应用
pansharpening 目标是将高分辨率全色图像与低分辨率多光谱图像融合。现有深度学习方法，包括近期自适应卷积，难以应对遥感图像中的区域异质性，且常伴随高昂计算成本。为此，本文提出双掩码自适应卷积（DMAConv），一种新型算子，可依据特征特性动态分配计算资源。DMAConv 首先通过轻量模块生成软掩码与硬掩码：硬掩码将特征分为紧凑分支（全局处理冗余信息）与聚焦分支（对复杂异质区域投入更多计算）。软掩码则预先调制两分支输入特征。这种双分支、掩码自适应设计显著增强特征表达，同时最小化计算开销。大量实验表明，该方法在多种定量基准上达到最先进水平，参数量显著更少，且在自适应卷积模型中计算成本最低。
原文摘要 · Abstract (English)
Pansharpening aims to fuse a high-resolution panchromatic image with a low-resolution multispectral image. Existing deep learning methods, including recent adaptive convolutions, struggle with regional heterogeneity in remote sensing images and often incur prohibitive computational costs. To address these challenges, we propose Dual Mask-Adaptive Convolution (DMAConv), a novel operator that dynamically allocates computational resources based on feature characteristics. DMAConv first employs a lightweight module to generate soft and hard masks. The hard mask separates features into a compact branch for processing redundant information globally and a focused branch that models complex, heterogeneous regions with greater computational investment. The soft mask then preliminarily modulates the input features for both branches. This dual-branch, mask-adaptive design significantly enhances feature representation while minimizing computational overhead. Extensive experiments demonstrate that our method achieves SOTA on a broad array of quantitative benchmarks, with substantially lower parameter counts and the minimal computational cost among adaptive convolution models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。