全部 |
  • 全部
  • 题名
  • 作者
  • 机构
  • 关键词
  • NSTL主题词
  • 摘要
检索 二次检索 AI检索
外文文献 中文文献
筛选条件:

1. Enhanced Deep Image Prior for Unsupervised Hyperspectral Image Super-Resolution NSTL国家科技图书文献中心

Jiaxin Li |  Ke Zheng... -  《IEEE Transactions on Geoscience and Remote Sensing》 - 2025,63 - 1~18 - 共18页 - 被引量:2

摘要: image prior (DIP) allows us to achieve unsupervised |  establishment and a deep image generation (DIG) stage for |  low-resolution hyperspectral image (LrHSI), high | -resolution multispectral image (HrMSI), and corresponding |  high-resolution hyperspectral image (HrHSI), the
关键词: Electronics packaging |  Hyperspectral imaging |  Degradation |  Image reconstruction |  Zero shot learning |  Generators |  Training |  Noise |  Tensors |  Estimation

2. A retinex inspired deep image prior model for despeckling and deblurring of aerial and satellite images using proximal gradient method NSTL国家科技图书文献中心

Architha Shastry |  A. A. Bini... -  《International journal of remote sensing》 - 2025,46(3/4) - 1432~1466 - 共35页

摘要: Image Prior model (DIP) addresses these issues by |  ground truth and extensive training data. The Deep |  performing restoration tasks using a single image, relying |  despeckling and deblurring models using distinct image | ), Entropy, Global Contrast Factor (GCF), Natural Image
关键词: Deblurring |  despeckling |  proximal gradient descent ascent |  deep image prior |  retinex |  total variation

3. High-Order DIP-VBTV: An Image Restoration Model Combining a Deep Image Prior and a High-Order Total Variation on Vector Bundles NSTL国家科技图书文献中心

Batard, Thomas -  《Journal of mathematical imaging and vision》 - 2025,67(2) - 共27页

摘要: image prior (DIP), yielding a variational model for |  manifold. Then, we insert the high-order TV into the deep |  image restoration. The proposed model can be viewed as |  variational models for image restoration: high-order TV |  edges and fine structures of the original image
关键词: Image restoration |  Differential geometry |  High-order total variation |  Deep image prior

4. Fundamental study on improving the quality of X-ray fluorescence computed tomography images by applying deep image prior to projection images as a pre-denoising method NSTL国家科技图书文献中心

Kusakari, Sota |  Sato, Kazuki... -  《International journal of computer assisted radiology and surgery.》 - 2025,20(4) - 665~676 - 共12页

摘要: the quality of XFCT images by applying a deep image |  of biological functions. Improvements in image |  prior (DIP), which is a type of convolutional neural |  image quality and was superior to the DIP post |  and pixel values. Finally, image quality of the
关键词: X-ray fluorescence computed tomography |  Deep image prior |  Denoising |  Biofunctional imaging

5. Analysis of Deep Image Prior and Exploiting Self-Guidance for Image Reconstruction NSTL国家科技图书文献中心

Shijun Liang |  Evan Bell... -  《IEEE transactions on computational imaging》 - 2025,11 - 435~451 - 共17页

摘要:The ability of deep image prior (DIP) to |  measurements has made it popular in inverse problems in image |  suggests that incorporating a reference image as network |  input can enhance DIP's performance in image |  network input and reconstructed image. We demonstrate
关键词: Image reconstruction |  Electronics packaging |  Training |  Magnetic resonance imaging |  Noise reduction |  Kernel |  Overfitting |  Convolutional neural networks |  Inverse problems |  Information filters

6. Unsupervised Deep Learning for DAS-VSP Denoising Using Attention-Based Deep Image Prior NSTL国家科技图书文献中心

Yang Cui |  Umair Bin Waheed... -  《IEEE Transactions on Geoscience and Remote Sensing》 - 2025,63 - 1~14 - 共14页

摘要: method, denoising with a deep image prior (DIP)-based |  deep learning (DL) methods, the proposed approach | Distributed acoustic sensing (DAS) has emerged |  as a widely used technology in various applications | , including borehole microseismic monitoring, active source
关键词: Noise |  Noise reduction |  Training |  Kurtosis |  Feature extraction |  Background noise |  Noise measurement |  Training data |  Optical fibers |  Data processing

7. Blind Image Deblurring with Noise-Robust Kernel Estimation NSTL国家科技图书文献中心

Chanseok Lee |  Jeongsol Kim... -  《Computer Vision - ECCV 2024,Part XX》 -  European Conference on Computer Vision - 2025, - 188~204 - 共17页

摘要:-robust kernel estimation function and deep image prior |  problem involving the retrieval of a clear image and |  blur kernel from a single blurry image. The challenge |  strongly noisy blurry images given a clear image and |  generation of a clear image to leverage its natural image
关键词: Blind deblurring |  Deep image prior |  Gaussian noise

8. Deep Diffusion Image Prior for Efficient OOD Adaptation in 3D Inverse Problems NSTL国家科技图书文献中心

Hyungjin Chung |  Jong Chul Ye -  《Computer Vision - ECCV 2024,Part LXXV》 -  European Conference on Computer Vision - 2025, - 432~455 - 共24页

摘要:. In this work, we propose deep diffusion image prior |  deep image prior. Under this framework, we propose an | , adaptation of the prior is necessary when there exists a |  tasks from the generative prior trained only with | Recent inverse problem solvers that leverage
关键词: Diffusion models |  Inverse problems |  OOD adaptation

9. Spatial-temporal source term estimation using deep neural network prior and its application to Chernobyl wildfires NSTL国家科技图书文献中心

Antonie Brozova |  Vaclav Smidl... -  《Journal of hazardous materials》 - 2025,488(May 5) - 137510.1~137510.12 - 共12页

摘要: based on deep image prior utilizing the structure of a |  the whole 5D tensor, some prior information is |  deep neural network to regularize the inversion is |  prior covariance structure in the source term. The | The source term of atmospheric emissions of
关键词: Atmospheric inversion |  Spatial-temporal source |  Deep image prior |  Deep neural networks |  Chernobyl wildfires

10. Temporal compressive complex amplitude imaging based on double random phase encoding NSTL国家科技图书文献中心

Xu, Ning |  Qi, Dalong... -  《Optics and Lasers in Engineering》 - 2025,184(Jan. Pt.1) - 1.1~1.10 - 共10页

摘要: a plug-and-play-based deep image prior algorithm |  spatiotemporal information from a superimposed 2D image of a | Snapshot temporal compressive imaging offers a |  potent method for capturing high-dimensional |  dynamic scene. However, despite its notable bandwidth
关键词: Snapshot compressive imaging |  Temporal imaging |  Complex-amplitude imaging |  Compressive sensing |  Image reconstruction |  Deep image prior |  ALGORITHMS
检索条件Deep image prior
  • 检索词扩展

NSTL主题词

  • NSTL学科导航