Results 21 to 30 of about 225,507 (258)
A Plug-and-Play Deep Image Prior [PDF]
ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021 Deep image priors (DIP) offer a novel approach for the regularization that leverages the inductive bias of a deep convolutional architecture in inverse problems. However, the quality of DIP approaches often degrades when the number of iterations exceeds a certain threshold due to overfitting.
Zhaodong Sun +3 more
openaire +1 more source
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
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
Image Deconvolution with Deep Image and Kernel Priors [PDF]
2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), 2019 Image deconvolution is the process of recovering convolutional degraded images, which is always a hard inverse problem because of its mathematically ill-posed property. On the success of the recently proposed deep image prior (DIP), we build an image deconvolution model with deep image and kernel priors (DIKP).
Zhunxuan Wang +3 more
openaire +2 more sources
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 ...
Xudong Ma +3 more
openaire +3 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
PET Image Reconstruction Using Deep Image Prior. [PDF]
IEEE Trans Med Imaging, 2019 Recently, deep neural networks have been widely and successfully applied in computer vision tasks and have attracted growing interest in medical imaging. One barrier for the application of deep neural networks to medical imaging is the need for large amounts of prior training pairs, which is not always feasible in clinical practice.
Gong K, Catana C, Qi J, Li Q.
europepmc +6 more sources
A Bayesian Perspective on the Deep Image Prior [PDF]
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019 CVPR ...
Zezhou Cheng +3 more
openaire +2 more sources
Early Stopping for Deep Image Prior
Trans. Mach. Learn. Res., 2021 Deep image prior (DIP) and its variants have showed remarkable potential for solving inverse problems in computer vision, without any extra training data. Practical DIP models are often substantially overparameterized. During the fitting process, these models learn mostly the desired visual content first, and then pick up the potential modeling and ...
Hengkang Wang +5 more
openaire +3 more sources
Combining Deep Image Prior and Second-Order Generalized Total Variance for Image Inpainting
Mathematics, 2023 Image inpainting is a crucial task in computer vision that aims to restore missing and occluded parts of damaged images. Deep-learning-based image inpainting methods have gained popularity in recent research.
Shaopei You +4 more
doaj +1 more source