Name: Thi Xiu Anne LE
Type: User
Company: Ecole Polytechnique
Bio: Currently Postdoctoral Researcher at Ecole Polytechnique, I'm working on image processing, based on Computer Vision, Machine Learning-AI & Digital Correlation
Location: 91120 Palaiseau
Blog: https://www.linkedin.com/in/thi-xiu-le-75125586/
Thi Xiu Anne LE's Projects
pure Python implement of BM3D
🏞 A content-based image retrieval (CBIR) system
Implementation of simple block matching, block matching with dynamic programming and Stereo Matching using Belief Propagation algorithm for stereo disparity estimation
Codes for Computer Vision using OpenCV & Scikit-image
VGG + Autoencoders + YOLO_v4 + Detectronn2 (Instance Segmentation)
code for dataHacker blog
Deep_Learning: Disparity_Map from Plenoptic_Images (Pytorch)
depth map computation
A image reconstruction and decomposition aloghrithm for Dual-energy Computed Tomography (DECT) based on deep learning.
EPI-based Oriented Relation Networks for Light Field Depth Estimation
EPINET: A Fully-Convolutional Neural Network using Epipolar Geometry for Depth from Light Field Images
Deeper Depth Prediction with Fully Convolutional Residual Networks (FCRN)
GPU-accelerated denoising with bm3d
GAN + Variational Autoencoders
[ECCV 2020] Spatial-Angular Interaction for Light Field Image Super-Resolution
Attention-based View Selection Networks for Light-field Disparity Estimation
PyTorch Implementation of "Light Field Image Super-Resolution with Transformers"
Fast and accurate 4D light field depth estimation via sparse reconstruction and diffusion.
Fiber distribution: aspect ratios + orientations (Le et al., in preparation)
ML_DeepCT is a machine learning and deep learning CT image processing pipeline, including: CT image reconstruction, registration, stitching, segmentation and digital image analysis
Patient-specific reconstruction of volumetric computed tomography images from few-view projections via deep learning
Collection of popular and reproducible image denoising works.
A list of data sets and other resources for light fields for computer vision
Semantic Segmentation; Segmentation of 3-phase media by considering their interfaces (Le et al., in preparation)
The Light-Field Imaging Toolkit (LFIT) is a collection of MATLAB functions designed to facilitate the rapid processing of raw light field images captured by a plenoptic camera. To cite this software publication: http://www.sciencedirect.com/science/article/pii/S2352711016300127
Calculate Disparity Map & 3D Points Cloud
Tomographic Reconstruction in Python