Zhengzhong Tu's repositories
PerceptualSimilarity
LPIPS metric. pip install lpips
video-classification
Tutorial for video classification/ action recognition using 3D CNN/ CNN+RNN on UCF101
3D-ResNets-PyTorch
3D ResNets for Action Recognition (CVPR 2018)
arxivpy
Python wrapper for arXiv API
ava_downloader
:arrow_double_down: Download AVA dataset (A Large-Scale Database for Aesthetic Visual Analysis)
DMPHN-cvpr19-master
Pytorch Implementation of CVPR19 "Deep Stacked Multi-patch Hierarchical Network for Image Deblurring"
DualResidualNetworks
Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restoration
git-tips
:trollface:Git的奇技淫巧
github-slideshow
A robot powered training repository :robot:
GREED
Official implementation for "ST-GREED: Space-Time Generalized EntropicDifferences for Frame Rate Dependent VideoQuality"
image-quality-assessment
Convolutional Neural Networks to predict the aesthetic and technical quality of images.
internetarchive
A Python and Command-Line Interface to Archive.org
IQA-optimization
Comparison of IQA models in Perceptual Optimization
koniq
KonIQ-10k Deep Learning Models
koniq-PyTorch
A Pytorch implementation of No-Reference Image Quality Assessment (NR-IQA) models trained on the KonIQ-10k dataset
MSPFN
Multi-Scale Progressive Fusion Network for Single Image Deraining
PatchVQ
Patch-VQ: ‘Patching Up’ the Video Quality Problem
pix2pix-tensorflow
TensorFlow implementation of "Image-to-Image Translation Using Conditional Adversarial Networks".
QAGANS
Quality Aware Generative Adversarial Networks
shaping_datasets
Mixed Integer Linear Programming for selecting a subset of a dataset, while enforcing at the same time a particular distribution in each dimension. The code uses Matlab's "intlinprog" solver, which is part of the optimization toolbox.
SRNTT
Image Super-Resolution by Neural Texture Transfer
srntt-pytorch
A PyTorch implementation of SRNTT, which is a novel RefSR method.
triq
TRIQ implementation
VSFA
Quality Assessment of In-the-Wild Videos (ACM MM 2019)
Youtube-8M-WILLOW
Kaggle Youtube 8M WILLOW approach