A novel method for feature fusion in convolutional neural networks is proposed in this paper. Different feature fusion techniques are suggested to facilitate the flow of information and improve the training of deep neural networks. Some of these techniques as well as the proposed network can be considered a type of Directed Acyclic Graph (DAG) Network, where a layer can receive inputs from other layers and have outputs to other layers. In the proposed general framework of Lattice Fusion Network (LFNet), feature maps of each convolutional layer are passed to other layers based on a lattice graph structure, where nodes are convolutional layers. To evaluate the performance of the proposed architecture, different designs based on the general framework of LFNet are implemented for the task of image denoising. This task is used as an example where training deep convolutional networks is needed. Results are compared with state of the art methods. The proposed network is able to achieve better results with far fewer learnable parameters, which shows the effectiveness of LFNets for training of deep neural networks.
School of Mathematics, Sichuan University（四川大学数学学院）
Deep learning based methods have achieved the state-of-the-art performance in image denoising. In this paper, a deep learning based denoising method is proposed and a module called fusion block is introduced in the convolutional neural network. For this so-called Noise Fusion Convolutional Neural Network (NFCNN), there are two branches in its multi-stage architecture. One branch aims to predict the latent clean image, while the other one predicts the residual image. A fusion block is contained between every two stages by taking the predicted clean image and the predicted residual image as a pa…
FAU Erlangen-Nürnberg（埃尔朗根-纽伦堡大学）；Siemens Healthcare GmbH（西门子医疗有限公司）；Fraunhofer Institute for Ceramic Technologies and Systems IKTS（弗劳恩霍夫陶瓷技术与系统研究所IKTS）；Ewha Womans University（梨花女子大学）
Self-supervised image denoising techniques emerged as convenient methods that allow training denoising models without requiring ground-truth noise-free data. Existing methods usually optimize loss metrics that are calculated from multiple noisy realizations of similar images, e.g., from neighboring tomographic slices. However, those approaches fail to utilize the multiple contrasts that are routinely acquired in medical imaging modalities like MRI or dual-energy CT. In this work, we propose the new self-supervised training scheme Noise2Contrast that combines information from multiple measured …
Jilin University（吉林大学）；University of Trento（特伦托大学）；ETH Zurich（苏黎世联邦理工学院）
Degraded images commonly exist in the general sources of character images, leading to unsatisfactory character recognition results. Existing methods have dedicated efforts to restoring degraded character images. However, the denoising results obtained by these methods do not appear to improve character recognition performance. This is mainly because current methods only focus on pixel-level information and ignore critical features of a character, such as its glyph, resulting in character-glyph damage during the denoising process. In this paper, we introduce a novel generic framework based on g…
The paper proposes a new high spatial resolution hyperspectral (HR-HS) image estimation method based on convex optimization. The method assumes a low spatial resolution HS (LR-HS) image and a guide image as observations, where both observations are contaminated by noise. Our method simultaneously estimates an HR-HS image and a noiseless guide image, so the method can utilize spatial information in a guide image even if it is contaminated by heavy noise. The proposed estimation problem adopts hybrid spatio-spectral total variation as regularization and evaluates the edge similarity between HR-H…
School of Computer and Communication Sciences, EPFL（洛桑联邦理工学院计算机与通信科学学院）
Blind and universal image denoising consists of using a unique model that denoises images with any level of noise. It is especially practical as noise levels do not need to be known when the model is developed or at test time. We propose a theoretically-grounded blind and universal deep learning image denoiser for additive Gaussian noise removal. Our network is based on an optimal denoising solution, which we call fusion denoising. It is derived theoretically with a Gaussian image prior assumption. Synthetic experiments show our network's generalization strength to unseen additive noise levels…
Hipandas: Hyperspectral Image Joint Denoising and Super-Resolution by Image Fusion with the Panchromatic Image
Northwestern Polytechnical University（西北工业大学）；Research & Development Institute of Northwestern Polytechnical University in Shenzhen（西北工业大学深圳研究院）；ETH Zürich（苏黎世联邦理工学院）；Xi’an Jiaotong University（西安交通大学）
提出零样本 Hipandas 框架，通过三网络耦合、两类低秩先验和两阶段训练，联合利用 PAN 图像完成高光谱去噪与超分辨率，性能优于现有方法。
École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）
Image denoising is a classic restoration problem. Yet, current deep learning methods are subject to the problems of generalization and interpretability. To mitigate these problems, in this project, we present a framework that is capable of controllable, confidence-based noise removal. The framework is based on the fusion between two different denoised images, both derived from the same noisy input. One of the two is denoised using generic algorithms (e.g. Gaussian), which make few assumptions on the input images, therefore, generalize in all scenarios. The other is denoised using deep learning…
Beijing University of Posts and Telecommunications（北京邮电大学）；GuangDong TUS-TuWei Technology Co.,Ltd（广东拓思途维科技有限公司）
While deep Convolutional Neural Networks (CNNs) have shown extraordinary capability of modelling specific noise and denoising, they still perform poorly on real-world noisy images. The main reason is that the real-world noise is more sophisticated and diverse. To tackle the issue of blind denoising, in this paper, we propose a novel pyramid real image denoising network (PRIDNet), which contains three stages. First, the noise estimation stage uses channel attention mechanism to recalibrate the channel importance of input noise. Second, at the multi-scale denoising stage, pyramid pooling is util…
Fingerprint image denoising is a very important step in fingerprint identification. to improve the denoising effect of fingerprint image,we have designs a fingerprint denoising algorithm based on deep encoder-decoder network,which encoder subnet to learn the fingerprint features of noisy images.the decoder subnet reconstructs the original fingerprint image based on the features to achieve denoising, while using the dilated convolution in the network to increase the receptor field without increasing the complexity and improve the network inference speed. In addition, feature fusion at different…
Fraunhofer Heinrich Hertz Institute（弗劳恩霍夫海因里希·赫兹研究所）
In low light or short-exposure photography the image is often corrupted by noise. While longer exposure helps reduce the noise, it can produce blurry results due to the object and camera motion. The reconstruction of a noise-less image is an ill posed problem. Recent approaches for image denoising aim to predict kernels which are convolved with a set of successively taken images (burst) to obtain a clear image. We propose a deep neural network based approach called Multi-Kernel Prediction Networks (MKPN) for burst image denoising. MKPN predicts kernels of not just one size but of varying sizes…
École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）
The development of neural networks has greatly improved the performance in various computer vision tasks. In the filed of image denoising, convolutional neural network based methods such as DnCNN break through the limits of classical methods, achieving better quantitative results. However, the epistemic uncertainty existing in neural networks limits further improvements in their performance over denoising tasks. Therefore, we develop and study different solutions to minimize uncertainty and further improve the removal of noise. From the perspective of ensemble learning, we implement manipulati…
Complementary Advantages: Exploiting Cross-Field Frequency Correlation for NIR-Assisted Image Denoising
School of Computer Science and Technology, Beijing Institute of Technology（北京理工大学计算机科学与技术学院）；School of Artificial Intelligence, Beijing Normal University（北京师范大学人工智能学院）；Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院空天信息研究院）
Computer Vision Lab, ETH Zurich（苏黎世联邦理工学院计算机视觉实验室）
We propose a deep reparametrization of the maximum a posteriori formulation commonly employed in multi-frame image restoration tasks. Our approach is derived by introducing a learned error metric and a latent representation of the target image, which transforms the MAP objective to a deep feature space. The deep reparametrization allows us to directly model the image formation process in the latent space, and to integrate learned image priors into the prediction. Our approach thereby leverages the advantages of deep learning, while also benefiting from the principled multi-frame fusion provide…
College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）；State Key Laboratory of Integrated Services Networks, Xidian University（西安电子科技大学综合业务网理论及关键技术国家重点实验室）；School of New Media and Communication, Tianjin University（天津大学新媒体与传播学院）
Instituto de Telecomunicações（电信研究所）；Instituto Superior Técnico（高等技术学院）
The recently proposed plug-and-play (PnP) framework allows leveraging recent developments in image denoising to tackle other, more involved, imaging inverse problems. In a PnP method, a black-box denoiser is plugged into an iterative algorithm, taking the place of a formal denoising step that corresponds to the proximity operator of some convex regularizer. While this approach offers flexibility and excellent performance, convergence of the resulting algorithm may be hard to analyze, as most state-of-the-art denoisers lack an explicit underlying objective function. In this paper, we propose a …
Institute of Applied Computing and Community Code (IAC3)（应用计算与社区代码研究所（IAC3））；Universitat de les Illes Balears（巴利阿里群岛大学）
Multi-exposure fusion (MEF) is a technique for combining different images of the same scene acquired with different exposure settings into a single image. All the proposed MEF algorithms combine the set of images, somehow choosing from each one the part with better exposure. We propose a novel multi-exposure image fusion chain taking into account noise removal. The novel method takes advantage of DCT processing and the multi-image nature of the MEF problem. We propose a joint fusion and denoising strategy taking advantage of spatio-temporal patch selection and collaborative 3D thresholding. Th…
BiEvLight: Bi-level Learning of Task-Aware Event Refinement for Low-Light Image Enhancement
College of Computer and Data Science, Fuzhou University（福州大学计算机与数据科学学院）；College of Computer Science and Technology, Shandong Technology and Business University（山东科技职业大学计算机科学与技术学院）
Hybrid Convolutional and Attention Network for Hyperspectral Image Denoising
School of Computer Science and Technology, Ocean University of China（中国海洋大学计算机科学与技术学院）；Department of Electrical and Computer Engineering, Mississippi State University（密西西比州立大学电气与计算机工程系）
University of Bristol（布里斯托大学）；New York University（纽约大学）
The L1 norm regularized least squares method is often used for finding sparse approximate solutions and is widely used in 1-D signal restoration. Basis pursuit denoising (BPD) performs noise reduction in this way. However, the shortcoming of using L1 norm regularization is the underestimation of the true solution. Recently, a class of non-convex penalties have been proposed to improve this situation. This kind of penalty function is non-convex itself, but preserves the convexity property of the whole cost function. This approach has been confirmed to offer good performance in 1-D signal denois…
Imaging under photon-scarce situations introduces challenges to many applications as the captured images are with low signal-to-noise ratio and poor luminance. In this paper, we investigate the raw image restoration under low-photon-count conditions by simulating the imaging of quanta image sensor (QIS). We develop a lightweight framework, which consists of a multi-level pyramid denoising network (MPDNet) and a luminance adjustment (LA) module to achieve separate denoising and luminance enhancement. The main component of our framework is the multi-skip attention residual block (MARB), which in…
School of Computer and Communication Sciences, EPFL（洛桑联邦理工学院计算机与通信科学学院）
Deep image denoisers achieve state-of-the-art results but with a hidden cost. As witnessed in recent literature, these deep networks are capable of overfitting their training distributions, causing inaccurate hallucinations to be added to the output and generalizing poorly to varying data. For better control and interpretability over a deep denoiser, we propose a novel framework exploiting a denoising network. We call it controllable confidence-based image denoising (CCID). In this framework, we exploit the outputs of a deep denoising network alongside an image convolved with a reliable filter…
FusionINN: Decomposable Image Fusion for Brain Tumor Monitoring
Technische Universität Dresden（德累斯顿工业大学）；Shandong University of Science and Technology（山东科技大学）；Shanghai Tenth People’s Hospital（上海市第十人民医院）；Tongji University Medical School（同济大学医学院）
Heriot-Watt University（赫瑞-瓦特大学）；The University of Edinburgh（爱丁堡大学）
Three-dimensional imaging plays an important role in imaging applications where it is necessary to record depth. The number of applications that use depth imaging is increasing rapidly, and examples include self-driving autonomous vehicles and auto-focus assist on smartphone cameras. Light detection and ranging (LIDAR) via single-photon sensitive detector (SPAD) arrays is an emerging technology that enables the acquisition of depth images at high frame rates. However, the spatial resolution of this technology is typically low in comparison to the intensity images recorded by conventional camer…
SGDFormer: One-stage Transformer-based Architecture for Cross-Spectral Stereo Image Guided Denoising
College of Information Science and Electronic Engineering, Zhejiang University（浙江大学信息科学与工程学院）；Ningbo Research Institute, Zhejiang University（浙江大学宁波研究院）；Zhejiang GongShang University（浙江工商大学）
University of Isfahan（伊斯法罕大学）；Hunan University（湖南大学）；Isfahan University of Medical Sciences（伊斯法罕医科大学）；Sichuan University（四川大学）
In recent years, there has been a growing interest in applying convolutional neural networks (CNNs) to low-level vision tasks such as denoising and super-resolution. Due to the coherent nature of the image formation process, optical coherence tomography (OCT) images are inevitably affected by noise. This paper proposes a new method named the multi-input fully-convolutional networks (MIFCN) for denoising of OCT images. In contrast to recently proposed natural image denoising CNNs, the proposed architecture allows the exploitation of high degrees of correlation and complementary information amon…
Learning Multi-scale Spatial-frequency Features for Image Denoising
PCA Lab, Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, School of Computer Science and Engineering（计算机科学与工程学院）；School of Intelligence Science and Technology（智能科学与技术学院）
Southeast University（东南大学）；Shanghai United-imaging Healthcare Co., Ltd（上海联影医疗科技股份有限公司）；University of Birmingham（伯明翰大学）
In order to improve speckle noise denoising of block matching 3d filtering (BM3D) method, an image frequency-domain multi-layer fusion enhancement method (MLFE-BM3D) based on nonsubsampled contourlet transform (NSCT) has been proposed. The method designs a NSCT hard threshold denoising enhancement to preprocess the image, then uses fusion enhancement in NSCT domain to fuse the preliminary estimation results of images before and after the NSCT hard threshold denoising, finally, BM3D denoising is carried out with the fused image to obtain the final denoising result. Experiments on natural images…
FS-Diff: Semantic guidance and clarity-aware simultaneous multimodal image fusion and super-resolution
School of Computer Science and Engineering, South China University of Technology（华南理工大学计算机科学与工程学院）；School of Physics and Optoelectronic Engineering, Foshan University（佛山大学物理与光电工程学院）；School of Instrumentation Science and Optelectronics Engineering, Beihang University（北航仪器科学与光电工程学院）；School of Information Engineering and Automation, Kunming University of Science and Technology（昆明理工大学信息工程与自动化学院）
Sichuan University（四川大学）；Institute of High Performance Computing, A*STAR（A*STAR高性能计算研究所）
Multi-scale architectures have shown effectiveness in a variety of tasks thanks to appealing cross-scale complementarity. However, existing architectures treat different scale features equally without considering the scale-specific characteristics, \textit{i.e.}, the within-scale characteristics are ignored in the architecture design. In this paper, we reveal this missing piece for multi-scale architecture design and accordingly propose a novel Multi-Scale Adaptive Network (MSANet) for single image denoising. Specifically, MSANet simultaneously embraces the within-scale characteristics and the…
Also recently, exciting strides forward have been made in the area of image restoration, particularly for image denoising and single image super-resolution. Deep learning techniques contributed to this significantly. The top methods differ in their formulations and assumptions, so even if their average performance may be similar, some work better on certain image types and image regions than others. This complementarity motivated us to propose a novel 3D convolutional fusion (3DCF) method. Unlike other methods adapted to different tasks, our method uses the exact same convolutional network arc…
Xformer: Hybrid X-Shaped Transformer for Image Denoising
Shanghai Jiao Tong University（上海交通大学）；Shanghai AI Laboratory（上海人工智能实验室）；University of Sydney（悉尼大学）；Shenyang Institute of Automation, Chinese Academy of Sciences（中国科学院沈阳自动化研究所）；ETH Zürich（苏黎世联邦理工学院）
In this paper, we propose a novel deep convolutional neural network to solve the general multi-modal image restoration (MIR) and multi-modal image fusion (MIF) problems. Different from other methods based on deep learning, our network architecture is designed by drawing inspirations from a new proposed multi-modal convolutional sparse coding (MCSC) model. The key feature of the proposed network is that it can automatically split the common information shared among different modalities, from the unique information that belongs to each single modality, and is therefore denoted with CU-Net, i.e.,…
Degradation-Robust Fusion: An Efficient Degradation-Aware Diffusion Framework for Multimodal Image Fusion in Arbitrary Degradation Scenarios
Department of Biomedical Engineering, Hefei University of Technology（合肥工业大学生物医学工程系）；Faculty of Information Engineering and Automation, Kunming University of Science and Technology（昆明理工大学信息工程与自动化学院）；School of Information Science and Technology, University of Science and Technology of China（中国科学技术大学信息科学技术学院）
Current video denoising methods perform temporal fusion by designing convolutional neural networks (CNN) or combine spatial denoising with temporal fusion into basic recurrent neural networks (RNNs). However, there have not yet been works which adapt gated recurrent unit (GRU) mechanisms for video denoising. In this letter, we propose a new video denoising model based on GRU, namely GRU-VD. First, the reset gate is employed to mark the content related to the current frame in the previous frame output. Then the hidden activation works as an initial spatial-temporal denoising with the help from …
University of Electronic Science and Technology of China（电子科技大学）；West China Hospital, Sichuan University（四川大学华西医院）；West China No.4 Hospital, Sichuan University（四川大学华西第四医院）
Being low-level radiation exposure and less harmful to health, low-dose computed tomography (LDCT) has been widely adopted in the early screening of lung cancer and COVID-19. LDCT images inevitably suffer from the degradation problem caused by complex noises. It was reported that deep learning (DL)-based LDCT denoising methods using convolutional neural network (CNN) achieved impressive denoising performance. Although most existing DL-based methods (e.g., encoder-decoder framework) can implicitly utilize non-local and contextual information via downsampling operator and 3D CNN, the explicit mu…
School of Computer and Communication Sciences, EPFL（洛桑联邦理工学院计算机与通信科学学院）
Following the performance breakthrough of denoising networks, improvements have come chiefly through novel architecture designs and increased depth. While novel denoising networks were designed for real images coming from different distributions, or for specific applications, comparatively small improvement was achieved on Gaussian denoising. The denoising solutions suffer from epistemic uncertainty that can limit further advancements. This uncertainty is traditionally mitigated through different ensemble approaches. However, such ensembles are prohibitively costly with deep networks, which ar…
In recent years, denoising methods based on deep learning have achieved unparalleled performance at the cost of large computational complexity. In this work, we propose an Efficient Multi-stage Video Denoising algorithm, called EMVD, to drastically reduce the complexity while maintaining or even improving the performance. First, a fusion stage reduces the noise through a recursive combination of all past frames in the video. Then, a denoising stage removes the noise in the fused frame. Finally, a refinement stage restores the missing high frequency in the denoised frame. All stages operate on …
We propose a patch-based method for the simultaneous denoising and fusion of a sequence of RAW multi-exposed images. A spatio-temporal criterion is used to select similar patches along the sequence, and a weighted principal component analysis permits to both denoise and fuse the multi exposed data. The overall strategy permits to denoise and fuse the set of images without the need of recovering each denoised image in the multi-exposure set, leading to a very efficient procedure. Several experiments show that the proposed method permits to obtain state-of-the-art fusion results with real RAW da…
Optical coherence tomography (OCT) is a prevalent imaging technique for retina. However, it is affected by multiplicative speckle noise that can degrade the visibility of essential anatomical structures, including blood vessels and tissue layers. Although averaging repeated B-scan frames can significantly improve the signal-to-noise-ratio (SNR), this requires longer acquisition time, which can introduce motion artifacts and cause discomfort to patients. In this study, we propose a learning-based method that exploits information from the single-frame noisy B-scan and a pseudo-modality that is c…
Self-Supervised Diffusion MRI Denoising via Iterative and Stable Refinement
School of Biomedical Engineering, Division of Life Sciences and Medicine, USTC（中国科学技术大学生命科学与医学部生物医学工程学院）；MIRACLE Center, Suzhou Institute for Advance Research, USTC（中国科学技术大学苏州研究院MIRACLE中心）；State Key Laboratory of Precision and Intelligent Chemistry, USTC（中国科学技术大学精准与智能化学国家重点实验室）；Key Laboratory of Intelligent Information Processing of CAS, Institute of Computing Technology, CAS（中国科学院计算技术研究所中国科学院智能信息处理重点实验室）
With the wide deployment of digital image capturing equipment, the need of denoising to produce a crystal clear image from noisy capture environment has become indispensable. This work presents a novel image denoising method that can tackle both impulsive noise, such as salt and pepper noise (SAPN), and additive white Gaussian noise (AWGN), such as hot carrier noise from CMOS sensor, at the same time. We propose to use low-rank matrix approximation to form the basic denoising framework, as it has the advantage of preserving the spatial integrity of the image. To mitigate the SAPN, the original…
