Video Super Resolution

A collection of state-of-the-art video or single-image super-resolution architectures, reimplemented in tensorflow.

Project uploaded to PyPI now. Try install from PyPI:

pip install VSR

Pretrained weights is uploading now.

Several referenced PyTorch implementations are also included now.

Quick Link:

• Installation
• Getting Started
• Benchmark

Network list and reference (Updating)

The hyperlink directs to paper site, follows the official codes if the authors open sources.

All these models are implemented in ONE framework.

*The 1st repo is by paper author.

**Y: included; -: not included; T: under-testing.

You can download pre-trained weights through prepare_data, or visit the hyperlink at √.

Link of datasets

(please contact me if any of links offend you or any one disabled)

Other open datasets: Kaggle ImageNet COCO

VSR package

This package offers a training and data processing framework based on TF. What I made is a simple, easy-to-use framework without lots of encapulations and abstractions. Moreover, VSR can handle raw NV12/YUV as well as a sequence of images as inputs.

Install

1. Prepare proper tensorflow and pytorch(optional). For example, GPU and CUDA10.0 (recommend to use conda):

   conda install tensorflow-gpu==1.15.0
   # optional
   # conda install pytorch

2. Install VSR package

   # For someone see this doc online
   # git clone https://github.com/loseall/VideoSuperResolution && cd VideoSuperResolution
   pip install -e .

Getting Started

1. Download pre-trained weights and (optinal) training datasets. For instance, let's begin with VESPCN and vid4 test data:

   python prepare_data.py --filter vespcn vid4

2. Customize backend cd ~/.vsr/ touch config.yml

   backend: tensorflow  # (tensorflow, pytorch)
   verbose: info        # (debug, info, warning, error)

3. Evaluate

   cd Train
   python eval.py srcnn -t vid4 --pretrain=/path/srcnn.pth

4. Train

   python prepare_data.py --filter mcl-v
   cd Train
   python train.py vespcn --dataset mcl-v --memory_limit 1GB --epochs 100

OK, that's all you need. For more details, use --help to get more information.

More documents can be found at Docs.