English
Related papers

Related papers: Exploiting network optimization stability for enha…

200 papers

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…

Computer Vision and Pattern Recognition · Computer Science 2019-12-11 Zhihao Xia , Ayan Chakrabarti

Low Dose Computed Tomography (LDCT) is clinically desirable due to the reduced radiation to patients. However, the quality of LDCT images is often sub-optimal because of the inevitable strong quantum noise. Inspired by their unprecedent…

Image and Video Processing · Electrical Eng. & Systems 2021-02-02 Ti Bai , Dan Nguyen , Biling Wang , Steve Jiang

Modern digital cameras rely on the sequential execution of separate image processing steps to produce realistic images. The first two steps are usually related to denoising and demosaicking where the former aims to reduce noise from the…

Computer Vision and Pattern Recognition · Computer Science 2019-04-02 Filippos Kokkinos , Stamatios Lefkimmiatis

The success of deep denoisers on real-world color photographs usually relies on the modeling of sensor noise and in-camera signal processing (ISP) pipeline. Performance drop will inevitably happen when the sensor and ISP pipeline of test…

Computer Vision and Pattern Recognition · Computer Science 2021-03-19 Yue Cao , Xiaohe Wu , Shuran Qi , Xiao Liu , Zhongqin Wu , Wangmeng Zuo

Fully supervised deep-learning based denoisers are currently the most performing image denoising solutions. However, they require clean reference images. When the target noise is complex, e.g. composed of an unknown mixture of primary…

Image and Video Processing · Electrical Eng. & Systems 2020-08-03 Florian Lemarchand , Erwan Nogues , Maxime Pelcat

Recently, Self-supervised learning methods able to perform image denoising without ground truth labels have been proposed. These methods create low-quality images by adding random or Gaussian noise to images and then train a model for…

Image and Video Processing · Electrical Eng. & Systems 2021-04-07 Dongkyu Won , Euijin Jung , Sion An , Philip Chikontwe , Sang Hyun Park

Low-dose CT imaging requires reconstruction from noisy indirect measurements which can be defined as an ill-posed linear inverse problem. In addition to conventional FBP method in CT imaging, recent compressed sensing based methods exploit…

Image and Video Processing · Electrical Eng. & Systems 2025-11-14 Mehmet Ozan Unal , Metin Ertas , Isa Yildirim

Image denoising is a fundamental challenge in computer vision, with applications in photography and medical imaging. While deep learning-based methods have shown remarkable success, their reliance on specific noise distributions limits…

Computer Vision and Pattern Recognition · Computer Science 2025-08-28 Dongjin Kim , Jaekyun Ko , Muhammad Kashif Ali , Tae Hyun Kim

The quality of images captured by wireless capsule endoscopy (WCE) is key for doctors to diagnose diseases of gastrointestinal (GI) tract. However, there exist many low-quality endoscopic images due to the limited illumination and complex…

Image and Video Processing · Electrical Eng. & Systems 2020-03-17 Shaofeng Zou , Mingzhu Long , Xuyang Wang , Xiang Xie , Guolin Li , Zhihua Wang

Deep learning based PET image reconstruction methods have achieved promising results recently. However, most of these methods follow a supervised learning paradigm, which rely heavily on the availability of high-quality training labels. In…

Image and Video Processing · Electrical Eng. & Systems 2023-03-13 Rui Hu , Yunmei Chen , Kyungsang Kim , Marcio Aloisio Bezerra Cavalcanti Rockenbach , Quanzheng Li , Huafeng Liu

Training deep neural networks has become a common approach for addressing image restoration problems. An alternative for training a "task-specific" network for each observation model is to use pretrained deep denoisers for imposing only the…

Image and Video Processing · Electrical Eng. & Systems 2024-04-16 Tomer Garber , Tom Tirer

Conventional deconvolution methods utilize hand-crafted image priors to constrain the optimization. While deep-learning-based methods have simplified the optimization by end-to-end training, they fail to generalize well to blurs unseen in…

Image and Video Processing · Electrical Eng. & Systems 2023-06-07 Dong Huo , Abbas Masoumzadeh , Rafsanjany Kushol , Yee-Hong Yang

Recently, Deep Image Prior (DIP) has demonstrated strong capabilities for solving inverse imaging problems (IIPs) by optimizing a randomly initialized convolutional neural network in a training-data-free regime. However, DIP suffers from…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Chaoyan Huang , Cheng-Han Huang , Ismail R. Alkhouri , Rongrong Wang

Positron emission tomography (PET) is widely used in various clinical applications, including cancer diagnosis, heart disease and neuro disorders. The use of radioactive tracer in PET imaging raises concerns due to the risk of radiation…

Computer Vision and Pattern Recognition · Computer Science 2017-12-13 Junshen Xu , Enhao Gong , John Pauly , Greg Zaharchuk

The explosive rise of the use of Computer tomography (CT) imaging in medical practice has heightened public concern over the patient's associated radiation dose. However, reducing the radiation dose leads to increased noise and artifacts,…

Computer Vision and Pattern Recognition · Computer Science 2021-07-06 Sutanu Bera , Prabir Kumar Biswas

Image denoising (removal of additive white Gaussian noise from an image) is one of the oldest and most studied problems in image processing. An extensive work over several decades has led to thousands of papers on this subject, and to many…

Image and Video Processing · Electrical Eng. & Systems 2023-01-10 Michael Elad , Bahjat Kawar , Gregory Vaksman

Cross-dose denoising for low-dose positron emission tomography (LDPET) has been proposed to address the limited generalization of models trained at a single noise level. However, neural networks trained on a specific dose level often fail…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Yichao Liu , Zongru Shao , Yueyang Teng , Junwen Guo

We present a comprehensive overview of the Deep Image Prior (DIP) framework and its applications to image reconstruction in computed tomography. Unlike conventional deep learning methods that rely on large, supervised datasets, the DIP…

Image and Video Processing · Electrical Eng. & Systems 2026-02-24 Simon Arridge , Riccardo Barbano , Alexander Denker , Zeljko Kereta

Deep Image Prior (DIP) shows that some network architectures naturally bias towards smooth images and resist noises, a phenomenon known as spectral bias. Image denoising is an immediate application of this property. Although DIP has removed…

Image and Video Processing · Electrical Eng. & Systems 2023-08-29 Yilin Liu , Jiang Li , Yunkui Pang , Dong Nie , Pew-thian Yap

This paper proposes a deep learning architecture that attains statistically significant improvements over traditional algorithms in Poisson image denoising espically when the noise is strong. Poisson noise commonly occurs in low-light and…

Computer Vision and Pattern Recognition · Computer Science 2018-09-28 Po-Yu Liu , Edmund Y. Lam