Inspiration

We had this idea for a long time but never could implement it until now.

What it does

An user uploads an image up to the app, that connects to firebase servers and runs object detection in python. From python, the image is returned back to the app.

How we built it

We used firebase and an open source GitHub for the main detection of objects. Once we got objects, we built masks and inpainted.

Challenges we ran into

We ran into a lot of challenges setting up environments and regular bugs. A huge challenge we ran into and were unable to fix in time was a bug that caused a plot in matplotlib to always be blank when saved.

Accomplishments that we're proud of

We are proud of being able to get firebase to work perfectly between Xcode and python, as it took the majority of our time.

What we learned

We learned a lot about implementing firebase and being able to connect the backend with the frontend.

What's next for ImageReconstruction

We plan on letting users draw masks themselves, which should not be too hard to implement.

Presentation

https://spark.adobe.com/page/aDY7Jj9erEmB0/

Share this project:

Updates