Excited to share the technical report for RadRotator, our latest #GenerativeAI tool, which enables the rotation of radiographs in 3D space💫 ✅Technical Report: 🔗 ✅Website: 🔗 ✅Online Demo: 🔗 (1/3)

At the core of RadRotator is a conditional #diffusion model trained on >15 million pairs of Digitally Reconstructed Radiographs (DRRs) derived from 5,000 CT volumes. This extensive training enables the model to rotate an input XR according to a specified 3D transformation. (2/3)

With many thanks to all the valuable help from @BrdKhsrv, who was my co-first author on this work, and the contributions of all colleagues and mentors from @Mayo_OSAIL and @MayoAILab. @ShahriarFaghani, @CodyWylesMD, @Slowvak, @MayoRadiology.

And here is the link to our paper on @huggingface Papers. Please Upvote if interested: @_akhaliq

Great work 💯

Thank you!🙏

@EliMahMD This is so incredible!!

@EliMahMD Thank you, Ayoosh!

just like luggage scanners 😀

It was a joy starting to read computer vision papers with this one. Though I didn't understand the RandHistogramShift despite trying a lot.