轻量级图像超分网络，用新模块提升画质同时降低计算开销。
Involution and BSConv Multi-Depth Distillation Network for Lightweight Image Super-Resolution
- 引入多深度的卷积与逆卷积混合块，高效提取特征。
- 参数量减少47.3%，FLOPs降低51.6%，画质仍优于主流模型。
- 适合移动端或边缘设备部署，兼容多种超分框架。
单图像超分辨率（SISR）旨在从低分辨率（LR）输入重建高分辨率（HR）图像。尽管卷积神经网络（CNN）已取得显著进展，但更深的架构常带来过多参数、更高内存占用和计算成本，限制了在资源受限设备上的应用。本文提出轻量级高效的图像超分辨率网络IBMDN，包含基于逆卷积与BSConv的多深度蒸馏块（IBMDB）和对比度与高频注意力块（CHFAB）。IBMDB在不同深度组合使用逆卷积与BSConv，实现高效特征提取并最小化计算复杂度；CHFAB是一种轻量级自注意力机制，专注于增强高频和对比度信息，提升重建图像的感知质量。IBMDB设计灵活，可无缝集成至各类SISR框架，包括基于信息蒸馏、Transformer及GAN的模型。大量实验表明，引入IBMDB显著降低内存使用、参数量和浮点运算量（FLOPs），同时在像素级准确率和视觉质量上均取得提升。源代码见：https://github.com/akramkhatami/IBMDN。
原文摘要 · Abstract (English)
Single-image super-resolution (SISR) is a fundamental problem in computer vision that aims to reconstruct high-resolution (HR) images from low-resolution (LR) inputs. Although convolutional neural networks (CNNs) have achieved substantial advancements, deeper architectures often introduce excessive parameters, higher memory usage, and computational cost, limiting their applicability on resource-constrained devices. Recent research has thus focused on lightweight architectures that preserve accuracy while reducing complexity. This paper presents the Involution and BSConv Multi-Depth Distillation Network (IBMDN), a lightweight and effective architecture for SISR. The proposed IBMDN comprises Involution and BSConv Multi-Depth Distillation Blocks (IBMDB) and a Contrast and High-Frequency Attention Block (CHFAB). IBMDB employs varying combinations of Involution and BSConv at multiple depths to perform efficient feature extraction while minimizing computational complexity. CHFAB, a lightweight self-attention mechanism, focuses on extracting high-frequency and contrast information to enhance perceptual quality in the reconstructed images. The flexible design of IBMDB enables it to be seamlessly integrated into diverse SISR frameworks, including information distillation, transformer-based, and GAN-based models. Extensive experiments demonstrate that incorporating IBMDB significantly reduces memory usage, parameters, and floating-point operations (FLOPs), while achieving improvements in both pixel-wise accuracy and visual quality. The source code is available at: https://github.com/akramkhatami/IBMDN.
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。