Pinned Repositories
Awesome-Super-Resolution
Collect super-resolution related papers, data, repositories
CV-Backbones
CV backbones including GhostNet, TinyNet and TNT, developed by Huawei Noah's Ark Lab.
daily-paper-computer-vision
记录每天整理的计算机视觉/深度学习/机器学习相关方向的论文
ECBSR
Edge-oriented Convolution Block for Real-time Super Resolution on Mobile Devices, ACM Multimedia 2021
flops-counter.pytorch
Flops counter for convolutional networks in pytorch framework
HetConvolution2d_pytorch
HetConv: Heterogeneous Kernel-Based Convolutions for Deep CNNs simply implement
ImageEnhance_cGAN
Pytorch implementation of "Enhance Image as You Like with Unpaired Learning" (IJCAI 2021)
mmsr
Open MMLab Image and Video Super-Resolution Toolbox, , including SRResNet, SRGAN, ESRGAN, EDVR, etc.
NAIC2019-AI-4KHDR-
复赛Public榜15th， Private榜8th，晋级榜6th，决赛5th，本项目是复赛复现项目，运行于model/目录下，gpu为4块
OPDN
sxpro's Repositories
sxpro/HetConvolution2d_pytorch
HetConv: Heterogeneous Kernel-Based Convolutions for Deep CNNs simply implement
sxpro/ImageEnhance_cGAN
Pytorch implementation of "Enhance Image as You Like with Unpaired Learning" (IJCAI 2021)
sxpro/NAIC2019-AI-4KHDR-
复赛Public榜15th， Private榜8th，晋级榜6th，决赛5th，本项目是复赛复现项目，运行于model/目录下，gpu为4块
sxpro/Awesome-Super-Resolution
Collect super-resolution related papers, data, repositories
sxpro/CV-Backbones
CV backbones including GhostNet, TinyNet and TNT, developed by Huawei Noah's Ark Lab.
sxpro/daily-paper-computer-vision
记录每天整理的计算机视觉/深度学习/机器学习相关方向的论文
sxpro/ECBSR
Edge-oriented Convolution Block for Real-time Super Resolution on Mobile Devices, ACM Multimedia 2021
sxpro/flops-counter.pytorch
Flops counter for convolutional networks in pytorch framework
sxpro/mmsr
Open MMLab Image and Video Super-Resolution Toolbox, , including SRResNet, SRGAN, ESRGAN, EDVR, etc.
sxpro/OPDN
sxpro/resume
web/print
sxpro/sr-metric
Learning a No-Reference Quality Metric for Single-Image Super-Rolution
sxpro/sxpro.github.io
my resume
sxpro/Video-and-Single-Image-Deraining
categorize current rain removal methods and fairly evaluate their deraining ability based on diverse benchmark datasets