This repository contains the code for the paper BIRNAT: Bidirectional Recurrent Neural Networks with Adversarial Training for Video Snapshot Compressive Imaging (The European Conference on Computer Vision 2020) by Ziheng Cheng, Ruiying Lu, Zhengjue Wang, Hao Zhang, Bo Chen, Ziyi Meng and Xin Yuan.
PyTorch > 1.3.0
numpy
scipy
The training data for BIRNAT is generated from DAVIS2017 with random crop and data argumentation and final obtain 26000 data pairs. To train BIRNAT, should generate the data in train/.
The test data includes six simulation data in simulation_test file and three real data with its results for BIRNAT in result/real.
Run model without adversarial training:
python train.py
Run model with adversarial training:
python train_at.py
The adversarial training and discriminator reference this. Note that running model without adversarial training requires more than 27GB of memory and with adversarial training need 32GB which batch size is 3. Please make sure your GPU is available.
Run
python test.py
where will evaluate the preformance on simulation data using the pre-trained model in model/.