All Projects → izhx → TC-YoukuVSRE

izhx / TC-YoukuVSRE

Licence: MIT license
天池2019阿里巴巴优酷视频增强和超分辨率挑战赛自用代码,EDVR、WDSR、ESRGAN三个模型。

Programming Languages

python
139335 projects - #7 most used programming language
Cuda
1817 projects
C++
36643 projects - #6 most used programming language

Projects that are alternatives of or similar to TC-YoukuVSRE

EDVR Keras
Keras implementation of EDVR: Video Restoration with Enhanced Deformable Convolutional Networks
Stars: ✭ 35 (-14.63%)
Mutual labels:  super-resolution, video-super-resolution
FISR
Official repository of FISR (AAAI 2020).
Stars: ✭ 72 (+75.61%)
Mutual labels:  super-resolution, video-super-resolution
Singan
Official pytorch implementation of the paper: "SinGAN: Learning a Generative Model from a Single Natural Image"
Stars: ✭ 2,983 (+7175.61%)
Mutual labels:  super-resolution, single-image-super-resolution
Waifu2x Extension Gui
Video, Image and GIF upscale/enlarge(Super-Resolution) and Video frame interpolation. Achieved with Waifu2x, Real-ESRGAN, SRMD, RealSR, Anime4K, RIFE, CAIN, DAIN, and ACNet.
Stars: ✭ 5,463 (+13224.39%)
Mutual labels:  super-resolution, video-super-resolution
tianchi-fashionai
FashionAI全球挑战赛——服饰关键点定位
Stars: ✭ 21 (-48.78%)
Mutual labels:  tianchi
tensorflow-bicubic-downsample
tf.image.resize_images has aliasing when downsampling and does not have gradients for bicubic mode. This implementation fixes those problems.
Stars: ✭ 23 (-43.9%)
Mutual labels:  super-resolution
MLSR
Source code for ECCV2020 "Fast Adaptation to Super-Resolution Networks via Meta-Learning"
Stars: ✭ 59 (+43.9%)
Mutual labels:  super-resolution
SRDenseNet-pytorch
SRDenseNet-pytorch(ICCV_2017)
Stars: ✭ 113 (+175.61%)
Mutual labels:  super-resolution
NRSR
Neighborhood Regression for Edge-Preserving Image Super-Resolution (ICASSP 2015)
Stars: ✭ 13 (-68.29%)
Mutual labels:  super-resolution
LFSSR-SAS-PyTorch
Repository for "Light Field Spatial Super-resolution Using Deep Efficient Spatial-Angular Separable Convolution" , TIP 2018
Stars: ✭ 22 (-46.34%)
Mutual labels:  super-resolution
tf-perceptual-eusr
A TensorFlow-based image super-resolution model considering both quantitative and perceptual quality
Stars: ✭ 44 (+7.32%)
Mutual labels:  super-resolution
WaifuLite
Super Resolution for Anime image, lightweight implementation
Stars: ✭ 20 (-51.22%)
Mutual labels:  super-resolution
ImSwitch
ImSwitch is a software solution in Python that aims at generalizing microscope control by providing a solution for flexible control of multiple microscope modalities.
Stars: ✭ 43 (+4.88%)
Mutual labels:  super-resolution
pytorch-gans
PyTorch implementation of GANs (Generative Adversarial Networks). DCGAN, Pix2Pix, CycleGAN, SRGAN
Stars: ✭ 21 (-48.78%)
Mutual labels:  super-resolution
sparse-deconv-py
Official Python implementation of the 'Sparse deconvolution'-v0.3.0
Stars: ✭ 18 (-56.1%)
Mutual labels:  super-resolution
MSG-Net
Depth Map Super-Resolution by Deep Multi-Scale Guidance, ECCV 2016
Stars: ✭ 76 (+85.37%)
Mutual labels:  super-resolution
EGVSR
Efficient & Generic Video Super-Resolution
Stars: ✭ 774 (+1787.8%)
Mutual labels:  super-resolution
FB
Multi-frame super-resolution via sub-pixel.
Stars: ✭ 55 (+34.15%)
Mutual labels:  super-resolution
Single-Image-Example-Based-Super-Resolution
Single image example-based super resolution. Improves the spatial and temporal resolution of an image using a direct mapping of LR HR patch pairs. C++, openCV.
Stars: ✭ 33 (-19.51%)
Mutual labels:  super-resolution
DAN
This is an official implementation of Unfolding the Alternating Optimization for Blind Super Resolution
Stars: ✭ 196 (+378.05%)
Mutual labels:  super-resolution

YoukuSR

“努力,要努力,我要变成万人迷!”

天池2019阿里巴巴优酷视频增强和超分辨率挑战赛自用代码,EDVR、WDSR、ESRGAN三个模型。有参考价值的东西,可能只有utils/y4m_tools.py

简介

第一次参加天池,还要期末考试压力好大嘤嘤嘤~

初赛GG了,比赛结束后发现与前排的思路一致,只是没卡没时间哇,2-stage、ensemble、flip都没做,只提交了baseline,不过此次参赛学习到了很多知识。

数据处理是自己手写的,读取y4m文件流,分帧转化为yuv444的;写了几个Dataset,分别给VSR和SISR用,VSR时做了场景分割(室友写的机器学习算法,暂时没专门学习场景检测的文献)以及帧序列padding的处理(在xintao大佬的策略上稍作修改),WDSR修改了一点点代码尝试单通道SR。输出生成y4m和输入差不多。

EDVR、WDSR的model architecture来自EDVRwdsr_ntire2018,自己写了训练代码。ESRGAN代码全部来自BasicSR,不得不说大佬所有东西都手写,代码很健壮,造轮子精神可嘉。

自己配置了Netflix的vmaf并且封装了函数,在utils/vmaf_tools.py中。

文件结构

├── README.md               // readme
├── dataset                 // 数据集
├── data                    // 数据代码
├── utils                   // 通用工具
├── model                   // 模型代码
├── models                  // 模型代码
├── optim                   // 优化器
├── options                 // 配置项
├── vmaf                    // vmaf
├── scripts                 // 
└── ...                     // 

编码规范

环境依赖等

Python 3.6.x ...

pytorch使用tensorboard.

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].