Results 11 to 20 of about 1,132,388 (176)
PET Image Reconstruction Using Deep Diffusion Image Prior. [PDF]
IEEE Trans Med Imaging11 pages, 12 ...
Hashimoto F, Gong K.
europepmc +3 more sources
Neural architecture search for deep image prior [PDF]
Computers & Graphics, 2021 We present a neural architecture search (NAS) technique to enhance the performance of unsupervised image de-noising, in-painting and super-resolution under the recently proposed Deep Image Prior (DIP). We show that evolutionary search can automatically optimize the encoder-decoder (E-D) structure and meta-parameters of the DIP network, which serves as ...
Kary Ho +3 more
openaire +2 more sources
Dual Image Deblurring Using Deep Image Prior [PDF]
Electronics, 2021 Blind image deblurring, one of the main problems in image restoration, is a challenging, ill-posed problem. Hence, it is important to design a prior to solve it. Recently, deep image prior (DIP) has shown that convolutional neural networks (CNNs) can be a powerful prior for a single natural image. Previous DIP-based deblurring methods exploited CNNs as
Chang Jong Shin +2 more
openaire +1 more source
Unsupervised Image Fusion Using Deep Image Priors [PDF]
2022 IEEE International Conference on Image Processing (ICIP), 2022 A significant number of researchers have applied deep learning methods to image fusion. However, most works require a large amount of training data or depend on pre-trained models or frameworks to capture features from source images. This is inevitably hampered by a shortage of training data or a mismatch between the framework and the actual problem ...
Ma, Xudong +3 more
openaire +3 more sources
Blind Image Deconvolution Using Variational Deep Image Prior
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023 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 the training dataset. Thus, training image-specific models is important for higher generalization. Deep image prior
Dong Huo +3 more
openaire +3 more sources
Blind Image Deconvolution Using Deep Generative Priors [PDF]
IEEE Transactions on Computational Imaging, 2020 This paper proposes a novel approach to regularize the \textit{ill-posed} and \textit{non-linear} blind image deconvolution (blind deblurring) using deep generative networks as priors. We employ two separate generative models --- one trained to produce sharp images while the other trained to generate blur kernels from lower-dimensional parameters.
Muhammad Asim, Fahad Shamshad, Ali Ahmed
openaire +2 more sources
International Journal of Computer Vision, 2018 Deep convolutional networks have become a popular tool for image generation and restoration. Generally, their excellent performance is imputed to their ability to learn realistic image priors from a large number of example images. In this paper, we show that, on the contrary, the structure of a generator network is sufficient to capture a great deal of
Dmitry Ulyanov +2 more
openaire +2 more sources
Hyperspectral Image Superresolution via Subspace-Based Deep Prior Regularization
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2023 Hyperspectral imaging is able to provide a finer delivery of various material properties than conventional imaging systems. Yet in reality, an optical system can only generate data with high spatial resolution but low spectral one, or vice versa, at ...
Jianwei Zheng +5 more
doaj +1 more source
DIPPAS: a deep image prior PRNU anonymization scheme
EURASIP Journal on Information Security, 2022 Source device identification is an important topic in image forensics since it allows to trace back the origin of an image. Its forensics counterpart is source device anonymization, that is, to mask any trace on the image that can be useful for ...
Francesco Picetti +4 more
doaj +1 more source
UnDIP: Hyperspectral Unmixing Using Deep Image Prior
IEEE Transactions on Geoscience and Remote Sensing, 2022 In this article, we introduce a deep learning-based technique for the linear hyperspectral unmixing problem. The proposed method contains two main steps. First, the endmembers are extracted using a geometric endmember extraction method, i.e., a simplex volume maximization in the subspace of the data set.
Behnood Rasti +3 more
openaire +2 more sources