All Projects → hhb072 → Waveletsrnet

hhb072 / Waveletsrnet

Licence: mit
A pytorch implementation of Paper "Wavelet-srnet: A wavelet-based cnn for multi-scale face super resolution"

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Waveletsrnet

Face And Image Super Resolution
Stars: ✭ 174 (-6.45%)
Mutual labels:  super-resolution, face
Psfrgan
PyTorch codes for "Progressive Semantic-Aware Style Transformation for Blind Face Restoration"
Stars: ✭ 185 (-0.54%)
Mutual labels:  super-resolution, face
Flame pytorch
This is a implementation of the 3D FLAME model in PyTorch
Stars: ✭ 153 (-17.74%)
Mutual labels:  face
Cognitive Face Windows
Windows SDK for the Microsoft Face API, part of Cognitive Services
Stars: ✭ 175 (-5.91%)
Mutual labels:  face
Anime Face Gan Keras
A DCGAN to generate anime faces using custom mined dataset
Stars: ✭ 161 (-13.44%)
Mutual labels:  face
Mmediting
OpenMMLab Image and Video Editing Toolbox
Stars: ✭ 2,618 (+1307.53%)
Mutual labels:  super-resolution
Knead proj
游戏中捏脸的实现
Stars: ✭ 169 (-9.14%)
Mutual labels:  face
Adafm
CVPR2019 (oral) Modulating Image Restoration with Continual Levels via Adaptive Feature Modification Layers (AdaFM). PyTorch implementation
Stars: ✭ 151 (-18.82%)
Mutual labels:  super-resolution
Mzsr
Meta-Transfer Learning for Zero-Shot Super-Resolution (CVPR, 2020)
Stars: ✭ 181 (-2.69%)
Mutual labels:  super-resolution
Lookatme
VideoView that plays video only when 👀 are open and 👦 is detected with various other features
Stars: ✭ 161 (-13.44%)
Mutual labels:  face
Gpufit
GPU-accelerated Levenberg-Marquardt curve fitting in CUDA
Stars: ✭ 174 (-6.45%)
Mutual labels:  super-resolution
Dpir
Plug-and-Play Image Restoration with Deep Denoiser Prior (PyTorch)
Stars: ✭ 159 (-14.52%)
Mutual labels:  super-resolution
A Pytorch Tutorial To Super Resolution
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network | a PyTorch Tutorial to Super-Resolution
Stars: ✭ 157 (-15.59%)
Mutual labels:  super-resolution
Dockerface
Face detection using deep learning.
Stars: ✭ 173 (-6.99%)
Mutual labels:  face
Frvsr
Frame-Recurrent Video Super-Resolution (official repository)
Stars: ✭ 157 (-15.59%)
Mutual labels:  super-resolution
Super resolution with cnns and gans
Image Super-Resolution Using SRCNN, DRRN, SRGAN, CGAN in Pytorch
Stars: ✭ 176 (-5.38%)
Mutual labels:  super-resolution
Pan
[Params: Only 272K!!!] Efficient Image Super-Resolution Using Pixel Attention, in ECCV Workshop, 2020.
Stars: ✭ 151 (-18.82%)
Mutual labels:  super-resolution
Video Super Resolution
Video super resolution implemented in Pytorch
Stars: ✭ 169 (-9.14%)
Mutual labels:  super-resolution
Fbrecog
An unofficial python wrapper for the Facebook face recognition endpoint
Stars: ✭ 184 (-1.08%)
Mutual labels:  face
Pytorch Zssr
PyTorch implementation of 1712.06087 "Zero-Shot" Super-Resolution using Deep Internal Learning
Stars: ✭ 180 (-3.23%)
Mutual labels:  super-resolution

WaveletSRNet

A pytorch implementation of Paper "Wavelet-srnet: A wavelet-based cnn for multi-scale face super resolution"

Prerequisites

  • Python 2.7
  • PyTorch

Run

Use the default hyparameters except changing the parameter "upscale" according to the expected upscaling factor(2, 3, 4 for 4, 8, 16 upcaling factors, respectively).

CUDA_VISIBLE_DEVICES=1 python main.py --ngpu=1 --test --start_epoch=0 --test_iter=1000 --batchSize=64 --test_batchSize=32 --nrow=4 --upscale=3 --input_height=128 --output_height=128 --crop_height=128 --lr=2e-4 --nEpochs=500 --cuda

Results

Citation

If you use our codes, please cite the following paper:

@inproceedings{huang2017wavelet,
  title={Wavelet-srnet: A wavelet-based cnn for multi-scale face super resolution},
  author={Huang, Huaibo and He, Ran and Sun, Zhenan and Tan, Tieniu},
  booktitle={IEEE International Conference on Computer Vision},
  pages={1689--1697},    
  year={2017}
}

The released codes are only allowed for non-commercial use.

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].