The 3-D total variation (3DTV) is a powerful regularization term, which encodes the local smoothness prior structure underlying a hyper-spectral image (HSI), for general HSI processing tasks. This term is calculated by assuming identical and independent sparsity structures on all bands of gradient maps calculated along spatial and spectral HSI modes. This, however, is always largely deviated from the real cases, where the gradient maps are generally with different while correlated sparsity structures across all their bands. Such deviation tends to hamper the performance of the related method by adopting such prior term. To this is- sue, this paper proposes an enhanced 3DTV (E-3DTV) regularization term beyond conventional 3DTV. Instead of imposing sparsity on gradient maps themselves, the new term calculated sparsity on the subspace bases on the gradient maps along their bands, which naturally encode the correlation and difference across these bands, and more faithfully reflect the insightful configurations of an HSI. The E-3DTV term can easily replace the previous 3DTV term and be em- bedded into an HSI processing model to ameliorate its performance. The superiority of the proposed methods is substantiated by extensive experiments on two typical related tasks: HSI denoising and compressed sensing, as compared with state-of-the-arts designed for both tasks.
Improved tissue sodium concentration quantification in breast cancer by reducing partial volume effects: a preliminary study
Danube Private University（多瑙河私立大学）；Karl Landsteiner Society（卡尔·兰德施泰纳学会）；Medical University of Vienna（维也纳医科大学）；Lausanne University Hospital（洛桑大学医院）；University of Lausanne（洛桑大学）；Aix-Marseille University（艾克斯-马赛大学）；CNRS（法国国家科学研究中心）；APHM（马赛公共医院援助）；Hôpital Universitaire Timone（蒂莫内大学医院）；Stanford University（斯坦福大学）；Heidelberg University（海德堡大学）；Medical Faculty Mannheim（曼海姆医学院）
JPEG image compression algorithm is a widely used technique for image size reduction in edge and cloud computing settings. However, applying such lossy compression on images processed by deep neural networks can lead to significant accuracy degradation. Inspired by the curriculum learning paradigm, we propose a training approach called curriculum pre-training (CPT) for crowd counting on compressed images, which alleviates the drop in accuracy resulting from lossy compression. We verify the effectiveness of our approach by extensive experiments on three crowd counting datasets, two crowd counti…
Cornell Tech（康奈尔理工学院）；Weill Cornell Medical School（威尔康奈尔医学院）；Massachusetts Institute of Technology（麻省理工学院）；Massachusetts General Hospital（麻省总医院）
Deep learning based techniques achieve state-of-the-art results in a wide range of image reconstruction tasks like compressed sensing. These methods almost always have hyperparameters, such as the weight coefficients that balance the different terms in the optimized loss function. The typical approach is to train the model for a hyperparameter setting determined with some empirical or theoretical justification. Thus, at inference time, the model can only compute reconstructions corresponding to the pre-determined hyperparameter values. In this work, we present a hypernetwork-based approach, ca…
RIKEN Center for Advanced Intelligence Project (AIP)（理化学研究所先进智能项目中心）；Department of Electronic Engineering, Tsinghua University（清华大学电子工程系）；Paradigm Inc.（第四范式有限公司）；Graduate School of Frontier Sciences, The University of Tokyo（东京大学前沿科学研究生院）；LISMARS, Wuhan University（武汉大学测绘遥感信息工程国家重点实验室）
Non-local low-rank tensor approximation has been developed as a state-of-the-art method for hyperspectral image (HSI) restoration, which includes the tasks of denoising, compressed HSI reconstruction and inpainting. Unfortunately, while its restoration performance benefits from more spectral bands, its runtime also substantially increases. In this paper, we claim that the HSI lies in a global spectral low-rank subspace, and the spectral subspaces of each full band patch group should lie in this global low-rank subspace. This motivates us to propose a unified paradigm combining the spatial and …
Hyperspectral images, which record the electromagnetic spectrum for a pixel in the image of a scene, often store hundreds of channels per pixel and contain an order of magnitude more information than a typical similarly-sized color image. Consequently, concomitant with the decreasing cost of capturing these images, there is a need to develop efficient techniques for storing, transmitting, and analyzing hyperspectral images. This paper develops a method for hyperspectral image compression using implicit neural representations where a multilayer perceptron network $Φ_θ$ with sinusoidal activatio…
FCA2: Frame Compression-Aware Autoencoder for Modular and Fast Compressed Video Super-Resolution
State Key Laboratory of Integrated Services Networks, School of Electronic Engineering, Xidian University（信息服务网络国家重点实验室，电子工程学院，西安电子科技大学）；Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University（协同智能系统重点实验室，教育部，西安电子科技大学）；School of Electronic Engineering, Xidian University（电子工程学院，西安电子科技大学）；Chongqing Key Laboratory of Image Cognition, Chongqing University of Posts and Telecommunications（重庆图像认知重点实验室，重庆邮电大学）
A blind compressive sensing algorithm is proposed to reconstruct hyperspectral images from spectrally-compressed measurements.The wavelength-dependent data are coded and then superposed, mapping the three-dimensional hyperspectral datacube to a two-dimensional image. The inversion algorithm learns a dictionary {\em in situ} from the measurements via global-local shrinkage priors. By using RGB images as side information of the compressive sensing system, the proposed approach is extended to learn a coupled dictionary from the joint dataset of the compressed measurements and the corresponding RG…
A Transformer-based Image Compression (TIC) approach is developed which reuses the canonical variational autoencoder (VAE) architecture with paired main and hyper encoder-decoders. Both main and hyper encoders are comprised of a sequence of neural transformation units (NTUs) to analyse and aggregate important information for more compact representation of input image, while the decoders mirror the encoder-side operations to generate pixel-domain image reconstruction from the compressed bitstream. Each NTU is consist of a Swin Transformer Block (STB) and a convolutional layer (Conv) to best emb…
Deep-learning-based hyperspectral image (HSI) restoration methods have gained great popularity for their remarkable performance but often demand expensive network retraining whenever the specifics of task changes. In this paper, we propose to restore HSIs in a unified approach with an effective plug-and-play method, which can jointly retain the flexibility of optimization-based methods and utilize the powerful representation capability of deep neural networks. Specifically, we first develop a new deep HSI denoiser leveraging gated recurrent convolution units, short- and long-term skip connecti…
Cornell University（康奈尔大学）；Massachusetts Institute of Technology（麻省理工学院）；Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）
Reconstructing under-sampled k-space measurements in Compressed Sensing MRI (CS-MRI) is classically solved with regularized least-squares. Recently, deep learning has been used to amortize this optimization by training reconstruction networks on a dataset of under-sampled measurements. Here, a crucial design choice is the regularization function(s) and corresponding weight(s). In this paper, we explore a novel strategy of using a hypernetwork to generate the parameters of a separate reconstruction network as a function of the regularization weight(s), resulting in a regularization-agnostic rec…
This work addresses the problem of extracting deeply learned features directly from compressive measurements. There has been no work in this area. Existing deep learning tools only give good results when applied on the full signal, that too usually after preprocessing. These techniques require the signal to be reconstructed first. In this work we show that by learning directly from the compressed domain, considerably better results can be obtained. This work extends the recently proposed framework of deep matrix factorization in combination with blind compressed sensing; hence the term deep bl…
Learned image compression methods generally optimize a rate-distortion loss, trading off improvements in visual distortion for added bitrate. Increasingly, however, compressed imagery is used as an input to deep learning networks for various tasks such as classification, object detection, and superresolution. We propose a recognition-aware learned compression method, which optimizes a rate-distortion loss alongside a task-specific loss, jointly learning compression and recognition networks. We augment a hierarchical autoencoder-based compression network with an EfficientNet recognition model a…
Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院空天信息创新研究院）；University of Chinese Academy of Sciences（中国科学院大学）；International Research Center of Big Data for Sustainable Development Goals（可持续发展大数据国际研究中心）
Owing to the rapid development of sensor technology, hyperspectral (HS) remote sensing (RS) imaging has provided a significant amount of spatial and spectral information for the observation and analysis of the Earth's surface at a distance of data acquisition devices, such as aircraft, spacecraft, and satellite. The recent advancement and even revolution of the HS RS technique offer opportunities to realize the full potential of various applications, while confronting new challenges for efficiently processing and analyzing the enormous HS acquisition data. Due to the maintenance of the 3-D HS …
This paper introduces a novel generative encoder (GE) model for generative imaging and image processing with applications in compressed sensing and imaging, image compression, denoising, inpainting, deblurring, and super-resolution. The GE model consists of a pre-training phase and a solving phase. In the pre-training phase, we separately train two deep neural networks: a generative adversarial network (GAN) with a generator $\G$ that captures the data distribution of a given image set, and an auto-encoder (AE) network with an encoder $\EN$ that compresses images following the estimated distri…
Harbin Institute of Technology（哈尔滨工业大学）；Peng Cheng Lab（鹏城实验室）
By integrating certain optimization solvers with deep neural network, deep unfolding network (DUN) has attracted much attention in recent years for image compressed sensing (CS). However, there still exist several issues in existing DUNs: 1) For each iteration, a simple stacked convolutional network is usually adopted, which apparently limits the expressiveness of these models. 2) Once the training is completed, most hyperparameters of existing DUNs are fixed for any input content, which significantly weakens their adaptability. In this paper, by unfolding the Fast Iterative Shrinkage-Threshol…
Real-Time Compressed Sensing for Joint Hyperspectral Image Transmission and Restoration for CubeSat
National Cheng Kung University（成功大学）；Institute of Data Science（数据科学研究所）；Miin Wu School of Computing（米润计算机学院）；Department of Statistics（统计学系）；Department of Computer Science（计算机科学系）
This thesis proposes spatio-spectral techniques for hyperspectral image analysis. Adaptive spatio-spectral support and variable exposure hyperspectral imaging is demonstrated to improve spectral reflectance recovery from hyperspectral images. Novel spectral dimensionality reduction techniques have been proposed from the perspective of spectral only and spatio-spectral information preservation. It was found that the joint sparse and joint group sparse hyperspectral image models achieve lower reconstruction error and higher recognition accuracy using only a small subset of bands. Hyperspectral i…
This paper presents a fractional one-dimensional convolutional neural network (CNN) autoencoder for denoising the Electroencephalogram (EEG) signals which often get contaminated with noise during the recording process, mostly due to muscle artifacts (MA), introduced by the movement of muscles. The existing EEG denoising methods make use of decomposition, thresholding and filtering techniques. In the proposed approach, EEG signals are first transformed to orthogonal domain using Tchebichef moments before feeding to the proposed architecture. A new hyper-parameter ($α$) is introduced which refer…
UCLouvain（鲁汶天主教大学）；University of Bologna（博洛尼亚大学）；IMEC（比利时微电子研究中心）；Université Libre de Bruxelles（布鲁塞尔自由大学）
A recently designed hyperspectral imaging device enables multiplexed acquisition of an entire data volume in a single snapshot thanks to monolithically-integrated spectral filters. Such an agile imaging technique comes at the cost of a reduced spatial resolution and the need for a demosaicing procedure on its interleaved data. In this work, we address both issues and propose an approach inspired by recent developments in compressed sensing and analysis sparse models. We formulate our superresolution and demosaicing task as a 3-D generalized inpainting problem. Interestingly, the target spatial…
Compressed Sensing (CS) is suitable for remote acquisition of hyperspectral images for earth observation, since it could exploit the strong spatial and spectral correlations, llowing to simplify the architecture of the onboard sensors. Solutions proposed so far tend to decouple spatial and spectral dimensions to reduce the complexity of the reconstruction, not taking into account that onboard sensors progressively acquire spectral rows rather than acquiring spectral channels. For this reason, we propose a novel progressive CS architecture based on separate sensing of spectral rows and joint re…
HS-Mamba: Full-Field Interaction Multi-Groups Mamba for Hyperspectral Image Classification
College of Mathematics and Informatics, South China Agricultural University（华南农业大学数学与信息学院）；Key Laboratory of Smart Agricultural Technology in Tropical South China, Ministry of Agriculture and Rural Affairs（热带南方智能农业技术重点实验室，农业部）；School of Chemistry and Chemical Engineering, South China University of Technology（华南理工大学化学与化工学院）
Neural Architecture Search for Compressed Sensing Magnetic Resonance Image Reconstruction
Tsinghua University（清华大学）；Center for Biomedical Imaging Research, Department of Biomedical Engineering, School of Medicine, Tsinghua University（清华大学医学院生物医学工程系生物医学影像研究中心）；Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）
本文提出用可微 NAS 在模型驱动 MR 重建流程中自动搜索 cell 结构，以更少算力取得更高 PSNR/SSIM，并验证其超参数敏感性与跨器官泛化性。
Santa Clara University（圣克拉拉大学）；ETH Zürich（苏黎世联邦理工学院）；Westlake University（西湖大学）；Kuaishou Technology（快手科技）
Recently, hyperspectral imaging (HSI) has attracted increasing research attention, especially for the ones based on a coded aperture snapshot spectral imaging (CASSI) system. Existing deep HSI reconstruction models are generally trained on paired data to retrieve original signals upon 2D compressed measurements given by a particular optical hardware mask in CASSI, during which the mask largely impacts the reconstruction performance and could work as a "model hyperparameter" governing on data augmentations. This mask-specific training style will lead to a hardware miscalibration issue, which se…
Tsinghua University（清华大学）；Shenzhen Institute of Future Media Technology（深圳未来媒体技术研究院）；Westlake University（西湖大学）；ETH Zürich（苏黎世联邦理工学院）；University of Würzburg（维尔茨堡大学）
In coded aperture snapshot spectral compressive imaging (CASSI) systems, hyperspectral image (HSI) reconstruction methods are employed to recover the spatial-spectral signal from a compressed measurement. Among these algorithms, deep unfolding methods demonstrate promising performance but suffer from two issues. Firstly, they do not estimate the degradation patterns and ill-posedness degree from the highly related CASSI to guide the iterative learning. Secondly, they are mainly CNN-based, showing limitations in capturing long-range dependencies. In this paper, we propose a principled Degradati…
This paper reviews the second challenge on spectral reconstruction from RGB images, i.e., the recovery of whole-scene hyperspectral (HS) information from a 3-channel RGB image. As in the previous challenge, two tracks were provided: (i) a "Clean" track where HS images are estimated from noise-free RGBs, the RGB images are themselves calculated numerically using the ground-truth HS images and supplied spectral sensitivity functions (ii) a "Real World" track, simulating capture by an uncalibrated and unknown camera, where the HS images are recovered from noisy JPEG-compressed RGB images. A new, …
