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 16 of 16 for “"implicit neural representation"”.
-
Implicit Neural Representation for Image Reconstruction
… role in almost every aspect of modern life. Neural network based approaches have recently emerged as highly effective solutions for this task. In particular, convolutional neural networks and transformer based architectures have demonstrated remarkable success in producing visually convincing …
-
Hyperspectral image compression using implicit neural representations
… data. In this thesis, we develop several neural compression-based methods for hyperspectral images. Our methodology relies on transforming hyperspectral images into implicit neural representations (INR), specifically neural functions that establish a correspondence between coordinates and …
-
ADVANCED ACQUISITION AND RECONSTRUCTION METHODS FOR CARDIAC QUANTITATIVE SUSCEPTIBILITY MAPPING AND CLINICAL APPLICATION
… based 3D spiral sequence together with an implicit neural representation learning based reconstruction framework was studied for motion-compensated cardiac QSM, and 4) cardiac QSM was applied for clinical studies including differential blood oxygen saturation and mitral annular …
-
Neural networks as data
<p>In machine learning, neural networks are typically treated as models to be used for various tasks such as classification, regression or generative modeling. In this thesis, we take a different perspective and treat neural networks as data instead of models.</p> <p>Indeed, in deep learning, data …
-
Integration of Model- and Learning-based Methods in Image Restoration
… a novel training strategy for deep convolutional neural networks (CNNs) that leverages theoretically concepts from transform domain and sparse representations. Its main idea consists of representing the convolutional kernels as linear combinations of predefined filter dictionaries where the …
-
Understanding and Modeling Explicit and Implicit Representations of the Visual World
… visual world with two main paradigms: training neural networks that model images explicitly with representation vectors, and training networks that model images implicitly in their own weights. In this thesis, I first discuss my work around explicit unsupervised image representation and …
-
Domain Knowledge as Motion-Aware Inductive Bias for Deep Video Synthesis: Two Case Studies
Deep neural networks have been part of many breakthroughs in computer graphics and vision research. In the context of visual content synthesis, deep learning models have achieved impressive performance in the image domain. However, adapting the successes of image synthesis models to the video …
-
Advanced Methods For Magnetic Resonance Image Reconstruction, Motion Artifact Correction And Quantitative Susceptibility Mapping
… whole-liver quantitative mapping using implicit neural representations, and susceptibility-based fibrosis assessment validated against histology. We first propose a temporal fusion network (tUnet) for motion correction of multi-echo gradient-echo (mGRE) images and further refine it using …
-
Perception-Aligned Representation Learning for 3D Visual Content
… by human observers. However, most existing 3D representations are designed for geometric accuracy or rendering efficiency, treating perceptual objectives as external post- rendering signals rather than properties modeled within the representation itself. This thesis studies perception-aligned …
-
A Regularized Deep Learning Framework for CFD Surrogate Modeling with Geometric Variability
L'abstract è presente nell'allegato / the abstract is in the attachment
-
Numerical Linear Algebra for Scientific Machine Learning: Neural Network Compression and Continuous Trace Estimation
… Iterative Model) Compression interleaves neural network training with repeated compression steps to remove excess capacity, reducing both training and inference time while maintaining accuracy. PruningAMR is an algorithm for efficiently visualizing implicit neural representations, which …
-
Differential-geometric methods for neural signed distance fields: Parameterized surface extraction and curvature regularization for CAD models
<p>Neural signed distance fields have emerged as a powerful framework for representing three-dimensional geometry through continuous and differentiable neural functions. Their flexibility, resolution independence, and compatibility with gradient-based optimization make them especially attractive …
-
Implicit Neural Representations for Multimedia Compression [Rappresentazioni neurali implicit per la Compressione di Multimedia]
Nelle rappresentazioni neurali implicite (INR) un segnale discreto viene interpretato come una funzione continua dalle coordinate ai campioni e una rete neurale viene poi allenata per approssimare questa funzione. I parametri della rete risultante possono essere compressi per ridurre la …
-
Learning robust and efficient point cloud representations
L'abstract è presente nell'allegato / the abstract is in the attachment
-
Machine perception and computer vision
… enhancement of 3D point cloud object representations, and perceptually interpretable ML. The prediction of visual attention on medical images is a research subject that has been limitedly studied. To tackle this problem, a novel and robust gaze estimation methodology based on …
-
Komprese objemných volumetrických dat pro interaktivní zobrazování s využitím hlubokého učení
… dat s využitím hlubokého učení. Řešení využívá implicitní neurální reprezentaci s kódováním vstupů pomocí víceúrovňové hašovací mřížky pro kompresi volumetrických dat rozdělených do bloků. Navržená struktura dat navíc umožňuje uchovávat komprimované bloky s několika úrovněmi komprese současně. …