HaoLiu's Projects
In the field of FSR, pre-trained adaface is used to extract identity features and calculate cosine similarity, which is used to compare the help of FSR for downstream tasks
A comprehensive summary of deep face restoration methods.
Bicubic超分辨对比方法
2024年计算机保研夏令营&冬令营通知
2024年计算机保研预推免通知
🎓Automatically Update CV Papers Daily using Github Actions (Update Every 12th hours)
十八届智能汽车竞赛室外远程驾驶无人车赛数据测试结果
Pytorch implementation of Deep Face Super-Resolution with Iterative Collaboration between Attentive Recovery and Landmark Estimation (CVPR 2020)
Code for ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks
PyTorch version of the paper 'Enhanced Deep Residual Networks for Single Image Super-Resolution' (CVPRW 2017)
This is the source code for the MIT6.01 course
结合openface与关键点对数据集重新处理
崇新学堂开放性创新实践I硬件项目:基于STC89C51的电子万年历
ICNet implemented by pytorch, for real-time semantic segmentation on high-resolution images, mIOU=71.0 on cityscapes, single inference time is 19ms, FPS is 52.6.
cx
崇新学堂开放性创新实践I软件项目:基于SpringBoot和React的个人图书馆系统
2023 mathematical modeling B first prize in Shandong Province technical scheme
Face super-resolution commonly used quantitative evaluation index index calculation warehouse, including PSNR, SSIM, LIPIS
机器学习&深度学习传统算法实现
This repository contains PyTorch implementation of the following paper: Face Super-Resolution with Spatial Attention Guided by Multiscale Receptive-Field Features.
Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
A PyTorch implementation of SRGAN based on CVPR 2017 paper "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network"
SRGAN在FSR训练模式下的复现情况
sun0225SUN's profile with 172 stars and 210 forks 🎉
SwinIR: Image Restoration Using Swin Transformer (official repository)
TidyBot: Personalized Robot Assistance with Large Language Models
[CVPR 2022] Official implementation of the paper "Uformer: A General U-Shaped Transformer for Image Restoration".
Ultra-resolving face images by discriminative generative networks