Image denoising methods must effectively model, implicitly or explicitly, the vast diversity of patterns and textures that occur in natural images. This is challenging, even for modern methods that leverage deep neural networks trained to regress to clean images from noisy inputs. One recourse is to rely on "internal" image statistics, by searching for similar patterns within the input image itself. In this work, we propose a new method for natural image denoising that trains a deep neural network to determine whether patches in a noisy image input share common underlying patterns. Given a pair of noisy patches, our network predicts whether different sub-band coefficients of the original noise-free patches are similar. The denoising algorithm then aggregates matched coefficients to obtain an initial estimate of the clean image. Finally, this estimate is provided as input, along with the original noisy image, to a standard regression-based denoising network. Experiments show that our method achieves state-of-the-art color image denoising performance, including with a blind version that trains a common model for a range of noise levels, and does not require knowledge of level of noise in an input image. Our approach also has a distinct advantage when training with limited amounts of training data.
This paper presents a parallel Salt and Pepper (SP) noise removal algorithm in a grey level digital image based on the Hypergraph Based Root Mean Square (HGRMS) approach. HGRMS is generic algorithm for identifying noisy pixels in any digital image using a two level hierarchical serial approach. However, for SP noise removal, we reduce this algorithm to a parallel model by introducing a cardinality matrix and an iteration factor, k, which helps us reduce the dependencies in the existing approach. We also observe that the performance of the serial implementation is better on smaller images, but …
Hanyang University（汉阳大学）；Chungnam National University（忠南国立大学）；SKT Vision AI Labs/T-Brain X（SKT视觉AI实验室/T-Brain X）
In this study, we propose a self-supervised video denoising method called "restore-from-restored." This method fine-tunes a pre-trained network by using a pseudo clean video during the test phase. The pseudo clean video is obtained by applying a noisy video to the baseline network. By adopting a fully convolutional neural network (FCN) as the baseline, we can improve video denoising performance without accurate optical flow estimation and registration steps, in contrast to many conventional video restoration methods, due to the translation equivariant property of the FCN. Specifically, the pro…
Coimbatore Institute of Technology（哥印拜陀理工学院）；Steps Rehabilitation Center (I), Steps groups（Steps康复中心（I），Steps集团）
Autism Spectrum Disorder (ASD) is found to be a major concern among various occupational therapists. The foremost challenge of this neurodevelopmental disorder lies in the fact of analyzing and exploring various symptoms of the children at their early stage of development. Such early identification could prop up the therapists and clinicians to provide proper assistive support to make the children lead an independent life. Facial expressions and emotions perceived by the children could contribute to such early intervention of autism. In this regard, the paper implements in identifying basic fa…
MoEDiff-SR: Mixture of Experts-Guided Diffusion Model for Region-Adaptive MRI Super-Resolution
Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）；Jiangsu Institute of Hematology（江苏血液学研究所）；The First Affiliated Hospital of Soochow University（苏州大学附属第一医院）；University Sorbonne Paris Nord（巴黎北索邦大学）；Henan University of Chinese Medicine（河南中医药大学）；German Cancer Research Center（德国癌症研究中心）；Athinoula A. Martinos Centre for Biomedical Imaging（阿西诺拉·A.马蒂诺斯生物医学成像中心）；Geneva University Hospital（日内瓦大学医院）；IDP Institute（IDP研究所）；University of Orleans（奥尔良大学）
The Biorobotics Institute（生物机器人研究所）；Scuola Superiore Sant’Anna（圣安娜高等学校）
Despite the recent developments that allowed neural networks to achieve impressive performance on a variety of applications, these models are intrinsically affected by the problem of overgeneralization, due to their partitioning of the full input space into the fixed set of target classes used during training. Thus it is possible for novel inputs belonging to categories unknown during training or even completely unrecognizable to humans to fool the system into classifying them as one of the known classes, even with a high degree of confidence. Solving this problem may help improve the security…
Pixel binning based Quad sensors have emerged as a promising solution to overcome the hardware limitations of compact cameras in low-light imaging. However, binning results in lower spatial resolution and non-Bayer CFA artifacts. To address these challenges, we propose a dual-head joint remosaicing and denoising network (DJRD), which enables the conversion of noisy Quad Bayer and standard noise-free Bayer pattern without any resolution loss. DJRD includes a newly designed Quad Bayer remosaicing (QB-Re) block, integrated denoising modules based on Swin-transformer and multi-scale wavelet transf…
Unsupervised Region-Based Image Editing of Denoising Diffusion Models
Institute of Information Science, Beijing Jiaotong University（北京交通大学信息科学研究所）；Pengcheng Laboratory（鹏城实验室）；University of Trento（特伦托大学）；Lanzhou Jiaotong University（兰州交通大学）
Shenzhen University（深圳大学）；Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳人工智能与机器人研究院）
Due to the diversity of attack materials, fingerprint recognition systems (AFRSs) are vulnerable to malicious attacks. It is thus important to propose effective fingerprint presentation attack detection (PAD) methods for the safety and reliability of AFRSs. However, current PAD methods often exhibit poor robustness under new attack types settings. This paper thus proposes a novel channel-wise feature denoising fingerprint PAD (CFD-PAD) method by handling the redundant noise information ignored in previous studies. The proposed method learns important features of fingerprint images by weighing …
Expert Validation of Synthetic Cervical Spine Radiographs Generated with a Denoising Diffusion Probabilistic Model
Cumming School of Medicine, University of Calgary（卡里尔大学医学学院）；Division of Neurosurgery, Department of Clinical Neurosciences, University of Calgary（卡里尔大学临床神经科学系神经外科部）；Department of Radiology, University of Calgary（卡里尔大学放射科）；Division of Neurosurgery, Department of Surgery, University of Toronto（多伦多大学外科系神经外科部）；Department of Medical Imaging, University of Toronto（多伦多大学医学影像科）；Project neuroArm, Department of Clinical Sciences, University of Calgary（卡里尔大学临床科学部neuroArm项目）
Parameter-Efficient Adaptation of Pre-Trained Vision Foundation Models for Active and Passive Seismic Data Denoising
Computation-based Science and Technology Research Center, The Cyprus Institute（计算科学与技术研究中心，塞浦路斯研究所）；Department of Geosciences, College of Petroleum Engineering and Geosciences, King Fahd University of Petroleum & Minerals（地质学系，石油工程与地质学院，国王法赫德石油与矿物大学）；Department of Intelligent Systems, Faculty of Electrical Engineering, Mathematics and Computer Science, Delft University of Technology（智能系统系，电气工程、数学与计算机科学学院，代尔夫特理工大学）；Department of Mathematics and Statistics, Faculty of Pure and Applied Sciences, University of Cyprus（数学与统计学系，纯应用科学学院，塞浦路斯大学）；Department of Geoscience and Engineering, Faculty of Civil Engineering and Geosciences, Delft University of Technology（地质科学与工程系，土木工程与地质科学学院，代尔夫特理工大学）
