Zhengzhong Tu's Projects
Tensorflow implementation for "Improved Transformer for High-Resolution GANs" (NeurIPS 2021).
Convolutional Neural Networks to predict the aesthetic and technical quality of images.
A Python and Command-Line Interface to Archive.org
Comparison of IQA models in Perceptual Optimization
MATLAB utility functions written by Kendrick Kay
KonIQ-10k Deep Learning Models
A Pytorch implementation of No-Reference Image Quality Assessment (NR-IQA) models trained on the KonIQ-10k dataset
iqa
This is the repository for LIVE-YouTube banding database.
[CVPR 2022] Unofficial repository for "MAXIM: Multi-Axis MLP for Image Processing". Official repo: https://github.com/google-research/maxim
[CVPR 2022 Oral] PyTorch re-implementation for "MAXIM: Multi-Axis MLP for Image Processing", with *training code*. Official Jax repo: https://github.com/google-research/maxim
MIMO-UNet - Official Pytorch Implementation
Official repository for "Multi-Stage Progressive Image Restoration" (CVPR 2021). SOTA results for image deblurring, deraining, and denoising.
Multi-Scale Progressive Fusion Network for Single Image Deraining
Source code for "From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality"
PaQ2PiQ in PyTorch
Patch-VQ: ‘Patching Up’ the Video Quality Problem
LPIPS metric. pip install lpips
TensorFlow implementation of "Image-to-Image Translation Using Conditional Adversarial Networks".
Quality Aware Generative Adversarial Networks
A Python implementation of RAISR
[IEEE OJSP'2021] "RAPIQUE: Rapid and Accurate Video Quality Prediction of User Generated Content", Zhengzhong Tu, Xiangxu Yu, Yilin Wang, Neil Birkbeck, Balu Adsumilli, Alan C. Bovik
Official repository for "Restormer: Efficient Transformer for High-Resolution Image Restoration". SOTA for motion deblurring, image deraining, denoising (Gaussian/real data), and defocus deblurring.
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.
Image Super-Resolution by Neural Texture Transfer
A PyTorch implementation of SRNTT, which is a novel RefSR method.
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
Implementation of temporal pooling methods studied in [ICIP'20] A Comparative Evaluation Of Temporal Pooling Methods For Blind Video Quality Assessment