Practical Compact Deep Compressed Sensing

计算机科学 压缩传感 人工智能 计算机视觉 模式识别(心理学)
作者
Bin Chen,Jian Zhang
出处
期刊:IEEE Transactions on Pattern Analysis and Machine Intelligence [IEEE Computer Society]
卷期号:47 (3): 1610-1626 被引量:15
标识
DOI:10.1109/tpami.2024.3504490
摘要

Recent years have witnessed the success of deep networks in compressed sensing (CS), which allows for a significant reduction in sampling cost and has gained growing attention since its inception. In this paper, we propose a new practical and compact network dubbed PCNet for general image CS. Specifically, in PCNet, a novel collaborative sampling operator is designed, which consists of a deep conditional filtering step and a dual-branch fast sampling step. The former learns an implicit representation of a linear transformation matrix into a few convolutions and first performs adaptive local filtering on the input image, while the latter then uses a discrete cosine transform and a scrambled block-diagonal Gaussian matrix to generate under-sampled measurements. Our PCNet is equipped with an enhanced proximal gradient descent algorithm-unrolled network for reconstruction. It offers flexibility, interpretability, and strong recovery performance for arbitrary sampling rates once trained. Additionally, we provide a deployment-oriented extraction scheme for single-pixel CS imaging systems, which allows for the convenient conversion of any linear sampling operator to its matrix form to be loaded onto hardware like digital micro-mirror devices. Extensive experiments on natural image CS, quantized CS, and self-supervised CS demonstrate the superior reconstruction accuracy and generalization ability of PCNet compared to existing state-of-the-art methods, particularly for high-resolution images. Code is available at https://github.com/Guaishou74851/PCNet.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
郑睿涛发布了新的文献求助10
刚刚
1秒前
1秒前
1秒前
jing发布了新的文献求助10
2秒前
2秒前
3419549959完成签到,获得积分10
3秒前
3秒前
3秒前
AAA发布了新的文献求助10
4秒前
4秒前
香蕉觅云的应助被特仑苏采纳,获得10
5秒前
爱吃秋刀鱼的大脸猫完成签到,获得积分10
5秒前
NiNi发布了新的文献求助10
6秒前
黑米粥发布了新的文献求助200
7秒前
7秒前
8秒前
桃子汽水发布了新的文献求助10
8秒前
苏小满关注了科研通微信公众号
9秒前
彭泽阳完成签到,获得积分10
9秒前
干就完发布了新的文献求助10
9秒前
9秒前
不开花花发布了新的文献求助10
10秒前
10秒前
李元发布了新的文献求助10
11秒前
11秒前
12秒前
12秒前
13秒前
13秒前
13秒前
Even完成签到,获得积分10
13秒前
Seorina发布了新的文献求助20
13秒前
13秒前
14秒前
14秒前
14秒前
领导范儿的应助被xiaoqiao采纳,获得30
15秒前
田様的应助被夏目采纳,获得10
15秒前
15秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Improving the wear resistance of vehicle gear oil by oil soluble LaF3 nanoparticles and typical additives of gear oil 500
Boundaries and Bodhisattvas 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8183880
求助须知:如何正确求助?哪些是违规求助? 9573054
关于积分的说明 21828982
捐赠科研通 7780959
什么是DOI,文献DOI怎么找? 3434134
关于科研通互助平台的介绍 2558315
邀请新用户注册赠送积分活动 2480634