All Projects → zhangxiaoya → FB

zhangxiaoya / FB

Licence: MIT license
Multi-frame super-resolution via sub-pixel.

Programming Languages

C++
36643 projects - #6 most used programming language
CMake
9771 projects
c
50402 projects - #5 most used programming language

Projects that are alternatives of or similar to FB

Msrn Pytorch
This repository is a PyTorch version of the paper "Multi-scale Residual Network for Image Super-Resolution" (ECCV 2018).
Stars: ✭ 221 (+301.82%)
Mutual labels:  super-resolution
Jalali-Lab-Implementation-of-RAISR
Implementation of RAISR (Rapid and Accurate Image Super Resolution) algorithm in Python 3.x by Jalali Laboratory at UCLA. The implementation presented here achieved performance results that are comparable to that presented in Google's research paper (with less than ± 0.1 dB in PSNR). Just-in-time (JIT) compilation employing JIT numba is used to …
Stars: ✭ 118 (+114.55%)
Mutual labels:  super-resolution
pytorch-gans
PyTorch implementation of GANs (Generative Adversarial Networks). DCGAN, Pix2Pix, CycleGAN, SRGAN
Stars: ✭ 21 (-61.82%)
Mutual labels:  super-resolution
Zoom Learn Zoom
computational zoom from raw sensor data
Stars: ✭ 224 (+307.27%)
Mutual labels:  super-resolution
TEGAN
Generative Adversarial Network (GAN) for physically realistic enrichment of turbulent flow fields
Stars: ✭ 60 (+9.09%)
Mutual labels:  super-resolution
CSSR
Crack Segmentation for Low-Resolution Images using Joint Learning with Super-Resolution (CSSR) was accepted to international conference on MVA2021 (oral), and selected for the Best Practical Paper Award.
Stars: ✭ 50 (-9.09%)
Mutual labels:  super-resolution
Ranksrgan
ICCV 2019 (oral) RankSRGAN: Generative Adversarial Networks with Ranker for Image Super-Resolution. PyTorch implementation
Stars: ✭ 213 (+287.27%)
Mutual labels:  super-resolution
AI-Lossless-Zoomer
AI无损放大工具
Stars: ✭ 940 (+1609.09%)
Mutual labels:  super-resolution
Magpie
将任何窗口放大至全屏
Stars: ✭ 4,478 (+8041.82%)
Mutual labels:  super-resolution
MLSR
Source code for ECCV2020 "Fast Adaptation to Super-Resolution Networks via Meta-Learning"
Stars: ✭ 59 (+7.27%)
Mutual labels:  super-resolution
Srgan
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
Stars: ✭ 2,641 (+4701.82%)
Mutual labels:  super-resolution
SRCNN-PyTorch
Pytorch framework can easily implement srcnn algorithm with excellent performance
Stars: ✭ 48 (-12.73%)
Mutual labels:  super-resolution
SRDenseNet-pytorch
SRDenseNet-pytorch(ICCV_2017)
Stars: ✭ 113 (+105.45%)
Mutual labels:  super-resolution
Master Thesis Bayesiancnn
Master Thesis on Bayesian Convolutional Neural Network using Variational Inference
Stars: ✭ 222 (+303.64%)
Mutual labels:  super-resolution
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 (-58.18%)
Mutual labels:  super-resolution
Pytorch Lapsrn
Pytorch implementation for LapSRN (CVPR2017)
Stars: ✭ 215 (+290.91%)
Mutual labels:  super-resolution
ESPCN-PyTorch
A PyTorch implementation of ESPCN based on CVPR 2016 paper Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network.
Stars: ✭ 33 (-40%)
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 (-40%)
Mutual labels:  super-resolution
WaifuLite
Super Resolution for Anime image, lightweight implementation
Stars: ✭ 20 (-63.64%)
Mutual labels:  super-resolution
MSG-Net
Depth Map Super-Resolution by Deep Multi-Scale Guidance, ECCV 2016
Stars: ✭ 76 (+38.18%)
Mutual labels:  super-resolution

Board Status

FBSuperResolution

The implementation of multi-frame super resolution via sub-pixel. All reference are following.

Usage

  1. clone or download this repo to local
git clone [email protected]:zhangxiaoya/FB.git
  1. Make foler for build

Use OpenCV2

cd FB
mkdir build
cd build
cmake .. # or use cmake-gui for custom build example or not, default is build with example
make
  1. Test SR use example
./example/example_runtime

the low resolution images are store at data folder by default, and the high resolution result is store at result folder by default.

  1. Result

原始图像 超分辨率图像

References

  1. Fast and Robust Multiframe Super Resolution
  2. Pyramidal Implementation of the Lucas Kanade Feature Tracker, description of the algorithm
  3. MDSP Super-Resolution And Demosaicing Datasets
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].