sanwen211314 Goto Github PK

divergentsubset

Simultaneously Counting and Extracting Endmembers in Hyperspectral Images Based on Divergent Subsets; Endmember Extraction; Spectral unmixing; Endmember Estimation; Estimating the number of endmembers.

dl-cacti

Deep Learning for Video Compressive Sensing

dl_cs_ecg

Effect of sparse Dictionary learning on the quality of recovery in Compressive sensing

dmc

Optimal discrete matrix completion

dmc-1

Discrete Matrix Completion

dncnn

Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising (TIP, 2017)

dp-gmm-hsi

Hyperspectral Image Restoration under Complex Multi-Band Noises (Remote Sensing, 2018)

drrn_cvpr17

Code for our CVPR'17 paper "Image Super-Resolution via Deep Recursive Residual Network"

dtcwt-nlm

Dual-tree complex wavelet combined with non-local means ASL fMRI denoising is a software toolbox that can denoise MR images, especially ASL fMRI images.

dtn-net

Distribution-transformed Network for Impulse Noise Removal

dtsd

低照度增强

dtuphd14

MATLAB scripts for DTU PhD summer school 2014

ece697sp-hyperspectral-project

Our final class project. Hyperspectral image classification.

ecso

Entropy-Based Convex Set Optimization for Spatial–Spectral Endmember Extraction From Hyperspectral Images

eebq-algorithm-for-hyperspectral-endmember-extraction

Hyperspectral Endmember Extraction using Band Quality

ekmc

ensemble kerneled matrix completion

enhanced-3dtv

The code of enhanced 3DTV Regularization and Its Applications on Hyper-spectral Image Denoising and Compressed Sensing

enhancedlowrankmatrixapproximation

Low-rank matrix estimation using convex non-convex prior

et2ecn_2020

exploiting-global-low-rank-structure-and-local-sparsity-nature-for-tensor-completion

Exploiting Global Low-Rank Structure and Local Sparsity Nature for Tensor Completion (TCYB, 2019)

expvecedm

MATLAB code for solving the Euclidean Distance Matrix completion problem.

fastdenoising

This is a very simple denoising code for seismic data. It contains two different basic thresholding functions and works in continuous wavelet domain.

faster

Graphs are frequently used to model data. An example is a social network graph: people are represented by vertices and their mutual relationships are encoded in edges. One then can extract useful information about the encoded data by measuring various combinatorial quantities; traditional examples include shortest paths or graph cuts. On the other hand, graph themselves can be viewed as a resistive electrical networks. Electrical measures, and in particular the effective resistances between vertices, often capture information that is not readily available through combinatorial measures. However, computing effective resistances is a challenging computational task especially for very large graphs. In this report we discuss a MATLAB implementation of a near-linear time algorithm for the computation of effective resistance, discovered by Spielman and Srivastava. We explore the trade-offs between running time and approximation quality, and we propose a space-efficient variant of the method.

faster-fista

Source codes for paper "Faster FISTA" and "Improving FISTA: Faster, Smarter and Greedier''

faster_rcnn

Faster R-CNN

fastmri

Fast Magnetic Resonance Imaging, including 2d grappa, sense, compressive sensing

fasttvd-

Fast Total Variation Denoising and Speckle Denoising Utilizing GPUs and Multi-Core CPUs

fault_detection_diagnosis_project

The scope of this project will be to use A.I. methods to analyze the available data set of historic building energy fault data, reveal hidden trends and data structure with unsupervised learning, and use supervised learning to classify unique operating profiles and use classification learning to create a prototype A.I. model for accurately predicting fault conditions.

featurefusion_getfund

Sources and demos of the paper entitled: Feature Fusion From Multispectral And Hyperspectral Compressive Data For Spectral Image Classification

featurefusion_igarss2021

SUBSPACE-BASED FEATURE FUSION FROM HYPERSPECTRAL AND MULTISPECTRAL IMAGES FOR PIXEL-BASED CLASSIFICATION