轻量级网络提升建筑图像超分质量，兼顾精度与效率
A super-resolution reconstruction method for lightweight building images based on an expanding feature modulation network
- 用扩张可分离调制单元捕捉多尺度特征，实现高效全局建模
- 引入重参数化局部增强模块，推理无额外计算开销
- 在保持轻量化前提下显著提升建筑图像超分效果
本文提出一种基于扩张上下文特征调制网络（DCFMN）的轻量级建筑图像超分辨率方法。通过获取高分辨率图像并下采样为低分辨率，对低分辨率图像进行增强，构建并训练轻量级网络模型，最终生成超分辨率输出。针对建筑图像中常见的规则纹理和长程依赖问题，DCFMN融合扩张可分离调制单元与局部特征增强模块。前者采用多扩张卷积模拟大核，高效聚合多尺度特征，并结合简单注意力机制实现自适应；后者编码局部特征、混合通道信息，通过重参数化设计在推理阶段零额外开销。该方法有效克服现有轻量级超分网络建模长程依赖能力弱的问题，在不增加计算成本前提下实现精准高效的全局特征建模，显著提升建筑图像超分辨率的重建质量和轻量化效率。
原文摘要 · Abstract (English)
This study proposes a lightweight method for building image super-resolution using a Dilated Contextual Feature Modulation Network (DCFMN). The process includes obtaining high-resolution images, down-sampling them to low-resolution, enhancing the low-resolution images, constructing and training a lightweight network model, and generating super-resolution outputs. To address challenges such as regular textures and long-range dependencies in building images, the DCFMN integrates an expansion separable modulation unit and a local feature enhancement module. The former employs multiple expansion convolutions equivalent to a large kernel to efficiently aggregate multi-scale features while leveraging a simple attention mechanism for adaptivity. The latter encodes local features, mixes channel information, and ensures no additional computational burden during inference through reparameterization. This approach effectively resolves the limitations of existing lightweight super-resolution networks in modeling long-range dependencies, achieving accurate and efficient global feature modeling without increasing computational costs, and significantly improving both reconstruction quality and lightweight efficiency for building image super-resolution 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。