ccyzf

MANIQA

[CVPRW 2022] MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment

CompressedVQA

Deep Learning based Full-reference and No-reference Quality Assessment Models for Compressed UGC Videos

TCSVT-2022-BVQA

Blindly Assess Quality of In-the-Wild Videos via Quality-aware Pre-training and Motion Perception

Introspective-Learning

This repository consists the code for the paper titled Introspective Learning : A Two-Stage Approach for Inference in Neural Networks

FPR

Code for "No-Reference Image Quality Assessment by Hallucinating Pristine Features"

HFR-BVQA

RM3VQA

A No Reference Deep Learning based Model for Quality Assessment of UGC Videos

BVQA-HEKE

TCSVT-2022 / ACM MM-2021

keras-applications

Reference implementations of popular deep learning models.

tensornets

High level network definitions with pre-trained weights in TensorFlow

addons

Useful extra functionality for TensorFlow 2.x maintained by SIG-addons

aliyunpan

阿里云盘小白羊版 阿里云盘PC版 aliyundriver

vit-pytorch

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

deep-learning-models

Keras code and weights files for popular deep learning models.

Swin-Transformer

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

HRFormer

[ NeurIPS2021] This is an official implementation of our paper "HRFormer: High-Resolution Transformer for Dense Prediction".

docker-sample

A sample of building docker image.

MUSIQ

Unofficial implementation of MUSIQ (Multi-Scale Image Quality Transformer)

google-research

Google Research

video-swin-transformer-pytorch

Video Swin Transformer - PyTorch

longformer

Longformer: The Long-Document Transformer

scenic

Scenic: A Jax Library for Computer Vision Research and Beyond

triq

TRIQ implementation

VSFA

[official] Quality Assessment of In-the-Wild Videos (ACM MM 2019)

VIDEVAL

[IEEE TIP'2021] "UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content", Zhengzhong Tu, Yilin Wang, Neil Birkbeck, Balu Adsumilli, Alan C. Bovik

cnn-tlvqm

Source code for no-reference video quality model CNN-TLVQM

GREED

Official implementation for "ST-GREED: Space-Time Generalized EntropicDifferences for Frame Rate Dependent VideoQuality"

PatchVQ

Patch-VQ: ‘Patching Up’ the Video Quality Problem

RAPIQUE

[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

ChipQA-0