Inspiration
Images continue to make important contributions to education, healthcare and commerce. Enhancing the image quality would be one of the important use cases for most of the applications.
What it does
Smart resolution web application expects inputs with a width of 480, height of 270 and performs the enhancement of image with the help of Single Image Super Resolution (SISR) deep learning model which is available on Open Model Zoo. The model returns images with a width of 1920, height of 1080. The image sides are upsampled by a factor 4. The new image is 16 times as large as the original image. We can also download the enhanced image.
How we built it
We have built this app with the help of Opencv and Single Image Super Resolution model which is a deep learning model in python and Streamlit for UI.
Challenges we ran into
Finding correct version of Opencv library and upsampling image appropriately.
Accomplishments that we're proud of
We are proud of getting super resolution image for given input image.
What we learned
We have learned new technologies - deep learning, streamlit.
What's next for Smart Resolution
Enhance images of any dimensions.
Log in or sign up for Devpost to join the conversation.