liangbinxie Goto Github PK

awesome-neural-rendering

A collection of resources on neural rendering.

awesome-tips

Methodology of owning a fruitful phd career

basicsr

Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, BasicVSR, SwinIR, ECBSR, etc. Also support StyleGAN2, DFDNet.

bilibili_video_download

:rainbow:Bilibili_video_download-B站视频下载

colossalai

Colossal-AI: A Unified Deep Learning System for Large-Scale Parallel Training

convtransformer

A PyTorch implementation of ConvTransformer: https://arxiv.org/pdf/2011.10185v1.pdf

edvr

Winning Solution in NTIRE19 Challenges on Video Restoration and Enhancement (CVPR19 Workshops) - Video Restoration with Enhanced Deformable Convolutional Networks

eqvi

Winning solution of AIM2020 VTSR Challenge (video interpolation). EQVI-Enhanced Quadratic Video Interpolation.

face-renovation

Official repository of the paper "HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment".

ffhq-aging-dataset

FFHQ-Aging Dataset

flip

A tool for visualizing and communicating the errors in rendered images.

latex_paper_writing_tips

Tips for Writing a Research Paper using LaTeX

liangbinxie.github.io

mmsr

Open MMLab Image and Video Super-Resolution Toolbox, , including SRResNet, SRGAN, ESRGAN, EDVR, etc.

nerfies

This is the code for Deformable Neural Radiance Fields, a.k.a. Nerfies.

paper_writing_tips

piq

Measures and metrics for image2image tasks. PyTorch.

pytorch-opcounter

Count the MACs / FLOPs of your PyTorch model.

real-esrgan

Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

residual-attention-network

Residual Attention Network for Image Classification

stable-diffusion

supervision-by-registration

Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors

unet-stylegan2

A Pytorch implementation of Stylegan2 with UNet Discriminator

vqfr

ECCV2022, Oral, VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder

wct2

Software that can perform photorealistic style transfer without the need of any post-processing steps.