可解释性
计算机科学
压缩传感
人工智能
源代码
块(置换群论)
变压器
采样(信号处理)
模式识别(心理学)
代表(政治)
降噪
迭代重建
稀疏矩阵
人工神经网络
重要性抽样
特征提取
图像质量
特征(语言学)
算法
稀疏逼近
噪音(视频)
深度学习
编码(集合论)
领域(数学)
计算机工程
噪声测量
作者
Heping Song,Jingyao Gong,Hongjie Jia,Xiangjun Shen,Jianping Gou,Hongying Meng,Le Wang
标识
DOI:10.1109/tcsvt.2025.3614371
摘要
Deep unrolling networks (DUNs) have attracted substantial attention in the field of image compressed sensing (CS) due to their superior performance and good interpretability by recasting optimization algorithms as deep networks. However, existing DUNs suffer from low sampling efficiency, and the improvement in reconstruction quality heavily relies on large model complexity. To address these issues, we propose a lightweight Representation Sampling and Hybrid Transformer Network (RHT-Net). Firstly, we propose a Representation-CS (RCS) model to extract high-level features to achieve efficient sampling. This sampling strategy leads to highly dense, semantically rich and extremely compact features without observing the original pixels, which also reduces the cross-domain loss during iteration. Secondly, we design a Tri-Scale Sparse Denoising (TSSD) module in the deep unrolling stages to extend sparse proximal projections, leveraging multi-scale auxiliary variables to enhance multi-feature flow and memory effects. Thirdly, we develop a hybrid Transformer module that includes a Global Cross Attention (GCA) block and a Window Local Attention (WLA) block, using the measurements to cross-estimate the reconstruction error, thereby generating finer spatial details and improving local recovery. Experiments demonstrate that RHT-Net enhanced version outperforms the current state-of-the-art methods by up to 1.17dB in PSNR. The lightweight RHT-Net achieves a 0.43dB gain while reducing model parameters by up to 22 times. The code will be released publicly at https://github.com/songhp/RHTNet.
科研通智能强力驱动
Strongly Powered by AbleSci AI