Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 13 of 13 for “"Deep Image Prior"”.
-
Deep Image Prior for Disentangling Mixed Pixels
A mixed pixel in remotely sensed images measures the reflectance and emission from multiple target types (e.g., tree, grass, and building) from a certain area. Mixed pixels exist commonly in spaceborne hyper-/multi-spectral images due to sensor limitations, causing the signature ambiguity problem …
-
Debayerizace RAW fotografie pomocí hluboké neuronové sítě
… a to konkrétne debayerizáciou pomocou deep image prior. Deep image prior (DIP) je koncept riešenia bežných rekonštrukčných problémov použitím netrénovaných konvolučných neurónových sietí. Jedinou vstupnou informáciou je obrázok, ktorý bol nejakým spôsobom poškodený. Cieľom tejto práce …
-
Solving inverse problems with deep learning : from untrained to pre-trained models
… problems are often ill-posed, imposing useful prior beliefs about the unknown signals is key to accurate recovery. Recently, deep learning models have shown success in representing complex and high-dimensional data in a variety of domains such as time series and images. This dissertation …
-
Deep Learning of Geospatial Patterns for Remote Sensing Image Downscaling
Remote sensing image downscaling can be regarded as an inverse problem that each coarse pixel is corresponding to infinite combinations of fine pixels. With the increasing demanding of fine imagery in various fields, many researchers have devoted themselves to the studies of efficient downscaling …
-
Efficient Spatiotemporal Representation Learning Techniques for Videos and Remote Sensing Data
… reflects temporal dynamics. Similarly, satellite images in remote sensing offer spatial information over time, revealing changes and patterns. Given the time-consuming and expensive nature of acquiring labeled spatiotemporal data, this thesis initially focuses on exploiting abundant unlabeled data …
-
SCENE AND ACTION UNDERSTANDING USING CONTEXT AND KNOWLEDGE SHARING
… we also study depth completion using deep depth prior based on the deep image prior (DIP) technique. DIP shows that structure of convolutional neural networks (CNNs) induces a strong prior that favors natural images. Given color images and noisy or incomplete target depth maps, we …
-
Deep-learning-guided image generation, enhancement and analysis : with applications to nuclear medicine imaging
Modern nuclear medicine imaging pipeline involves image generation, enhancement, and analysis, each facing challenges in reconstruction fidelity, quantitative reliability, and interpretation. This thesis presents deep-learning approaches to overcome these limitations throughout the nuclear medicine …
-
Investigating the application of test-time machine learning methods for geophysics inverisons
… biomedical imaging. For instance, methods like Deep Image Prior (DIP) and Neural Fields (NFs), which are categorized as test-time learning methods, have been effective in tasks such as de-noising and 3D rendering without prior training. The hypothesis is that these implicit regularization …
-
Novel Machine Learning Methods for Prostate Image Analysis
… resonance (MR) and transrectal ultrasound (TRUS) images are vital for improving the effectiveness of prostate cancer diagnosis. However, the inherent differences in dimensionality and modality between 3D MR and 2D ultrasound images pose significant challenges for direct alignment and fusion. This …
-
Deep generative models for phase retrieval in computational microscopy
… and developing new vaccines. Recently, deep learning methods have garnered a lot of attention because of their surprising success at solving ill-posed problems where most of the iterative methods or traditional machine learning methods fail to perform satisfactorily. Subsequently, there …
-
Accelerated MRI with Un-trained Neural Networks
… Neural Networks (CNNs) are highly effective for image reconstruction problems. Typically, CNNs are trained on large amounts of training images. Recently, however, un-trained CNNs such as the Deep Image Prior and Deep Decoder have achieved excellent performance for image reconstruction problems …
-
Advancing Untrained Deep Neural Networks
High-quality images are essential for many safety-critical and practical domains, ranging from commercial and medical to military applications. Nevertheless, real-world images are frequently degraded by nuisance factors, leading to noise, blur, and other distortions. Image restoration, the task of …
-
Computational 3D Optical Imaging Using Wavevector Diversity
<p>The explosion in the popularity and success of deep learning in the past decade has accelerated the development of computationally efficient, GPU-accelerated frameworks, such as TensorFlow and PyTorch, for rapid prototyping of neural networks. In this dissertation, we show that these deep …