Repository files navigation

A PyTorch implementation of SRGAN based on CVPR 2017 paperPhoto-Realistic Single Image Super-Resolution Using a Generative Adversarial Network.

• Anaconda
• PyTorch

conda install pytorch torchvision -c pytorch

• opencv

conda install opencv

The train and val datasets are sampled fromVOC2012.Train dataset has 16700 images and Val dataset has 425 images.Download the datasets fromhere(access code:5tzp), and then extract it intodata directory.

The test image dataset are sampled from|Set 5 |Bevilacqua et al. BMVC 2012|Set 14 |Zeyde et al. LNCS 2010|BSD 100 |Martin et al. ICCV 2001|Sun-Hays 80 |Sun and Hays ICCP 2012|Urban 100 |Huang et al. CVPR 2015.Download the image dataset fromhere(access code:xwhy), and then extract it intodata directory.

The test video dataset are three trailers. Download the video dataset fromhere(access code:956d).

python train.pyoptional arguments:--crop_size                   training images crop size [default value is 88]--upscale_factor              super resolution upscale factor [default value is 4](choices:[2, 4, 8])--num_epochs                  train epoch number [default value is 100]

The output val super resolution images are ontraining_results directory.

python test_benchmark.pyoptional arguments:--upscale_factor              super resolution upscale factor [default value is 4]--model_name                  generator model epoch name [default value is netG_epoch_4_100.pth]

The output super resolution images are onbenchmark_results directory.

python test_image.pyoptional arguments:--upscale_factor              super resolution upscale factor [default value is 4]--test_mode                   using GPU or CPU [default value is 'GPU'](choices:['GPU', 'CPU'])--image_name                  test low resolution image name--model_name                  generator model epoch name [default value is netG_epoch_4_100.pth]

The output super resolution image are on the same directory.

python test_video.pyoptional arguments:--upscale_factor              super resolution upscale factor [default value is 4]--video_name                  test low resolution video name--model_name                  generator model epoch name [default value is netG_epoch_4_100.pth]

The output super resolution video and compared video are on the same directory.

Upscale Factor = 2

Epochs with batch size of 64 takes ~2 minute 30 seconds on a NVIDIA GTX 1080Ti GPU.

Image Results

The left is bicubic interpolation image, the middle is high resolution image, andthe right is super resolution image(output of the SRGAN).

• BSD100_070(PSNR:32.4517; SSIM:0.9191)

• Set14_005(PSNR:26.9171; SSIM:0.9119)

• Set14_013(PSNR:30.8040; SSIM:0.9651)

• Urban100_098(PSNR:24.3765; SSIM:0.7855)

Video Results

The left is bicubic interpolation video, the right is super resolution video(output of the SRGAN).

Upscale Factor = 4

Epochs with batch size of 64 takes ~4 minute 30 seconds on a NVIDIA GTX 1080Ti GPU.

Image Results

The left is bicubic interpolation image, the middle is high resolution image, andthe right is super resolution image(output of the SRGAN).

• BSD100_035(PSNR:32.3980; SSIM:0.8512)

• Set14_011(PSNR:29.5944; SSIM:0.9044)

• Set14_014(PSNR:25.1299; SSIM:0.7406)

• Urban100_060(PSNR:20.7129; SSIM:0.5263)

Video Results

The left is bicubic interpolation video, the right is super resolution video(output of the SRGAN).

Upscale Factor = 8

Epochs with batch size of 64 takes ~3 minute 30 seconds on a NVIDIA GTX 1080Ti GPU.

Image Results

The left is bicubic interpolation image, the middle is high resolution image, andthe right is super resolution image(output of the SRGAN).

• SunHays80_027(PSNR:29.4941; SSIM:0.8082)

• SunHays80_035(PSNR:32.1546; SSIM:0.8449)

• SunHays80_043(PSNR:30.9716; SSIM:0.8789)

• SunHays80_078(PSNR:31.9351; SSIM:0.8381)

Video Results

The left is bicubic interpolation video, the right is super resolution video(output of the SRGAN).

The complete test results could be downloaded fromhere(access code:nkh9).