Image-super-resolution using Enhanced Deep Residual Networks for Single Image Super-Resolution(EDSR) and Wide Activation for Efficient and Accurate Image Super-Resolution(WDSR)
Image Super Resolution using EDSR and WDSR research papers
You can find Deployed Working model here
Find detailed blog of my project here
Note : If page is not loading then please paste above ipynb github link here. Now you can view ipynb notebook successfully !!
- EDSR paper is here
-
Proposed networks. We remove the batch normalization layers from our network as Nah et al presented in their image deblurring work. Since batch normalization layers normalize the features, they get rid of range flexibility from networks by normalizing the features, it is better to remove them.
-
Furthermore, GPU memory usage is also sufficiently reduced since the batch normalization layers consume the same amount of memory as the preceding convolutional layers. this baseline model without batch normalization layer saves approximately 40% of memory usage during training, compared to SRResNet. Consequently, we can build up a larger model that has better performance than conventional ResNet structure under limited computational resources.
- WDSR paper is here
- DIV2K dataset is a newly proposed high-quality (2K resolution) image dataset for image restoration tasks. The DIV2K dataset consists of 800 training images, 100 validation images, and 100 test images. As the test dataset ground truth is not released, we report and compare the performances on the validation dataset. We also compare the performance on some of the standard benchmark datasets named Set5 and Set14.
- More result you can find here
- More result you can find here
- More result you can find here
- More result you can find here
