Name: Simone Zini
Type: User
Company: Imaging and Vision Laboratory | University of Milano - Bicocca
Bio: Ph.D. in Computer Science.
Research scientist in Image Processing, Computational Photography, Computer Vision and Deep/Machine Learning.
Location: Milan, Italy
Blog: http://www.ivl.disco.unimib.it/people/simone-zini/
Simone Zini's Projects
Official inference code of the paper "Deep Residual Autoencoder for Blind Universal JPEG Restoration"
COCOA - COmbining COlor constancy Algorithms
Framework for Bayesian optimization of contrast enhancement algorithms based on deep learning modeling of user preferences.
A technical report on convolution arithmetic in the context of deep learning
This is a deep-learning based pan-sharpening code package, we reimplemented include PNN, MSDCNN, PanNet, TFNet, SRPPNN, and our purposed network DIPNet.
A collection of algorithm for digital imaging in MATLAB
Dilated Convolution for Semantic Image Segmentation
Distributed ray tracer developen in c++
Code and resources for "FC4 : Fully Convolutional Color Constancy with Confidence-weighted Pooling" (CVPR 2017)
A refreshed version of Hyde for Jekyll 3.x and 4.x
Show attend and tell implementation in pytorch
Official implementation of the model from the paper "Laplacian encoder-decoder network for raindrop removal".
An Efficient Statistical Method for Image Noise Level Estimation, ICCV 2015, Python
Video discussing this curriculum:
Python Imaging Library (Fork)
Planckian Jitter data augmentation procedure from "Planckian jitter: enhancing the color quality of self-supervised visual representations".
Python tool for plotting logs from CNN trainings
Differentiable color conversion functions for pytorch
Image-to-image translation in PyTorch (e.g., horse2zebra, edges2cats, and more)
PyTorch Implementation of Fully Convolutional Networks.
Config files for my GitHub profile.
Official implementation of the paper "TreEnhance: A Tree Search Method For Low-Light Image Enhancement"
A pytorch implementation of Paper "Improved Training of Wasserstein GANs"