GenerativeModels
GenerativeModels copied to clipboard
Add image-to-image translation tutorial (T1 to T2)
Please add a tutorial illustrating how to train a model (e.g. 3d pix2pix, ..) to translate a T1 into a corresponding T2 (or CT, PS,...) image.
Dataset: IXI, ...
Any updates on translating a T1 into a corresponding T2 (or CT, PS,...) image?
This isn't being worked on at the moment. The closest we have would be repurposing this DDPM tutorial designed for segmentation. Replace the segmentation target with a paired T2 (or other modality) and you have image-to-image translation
Thank you.
Due to this issue being replied to and inactivity, I am closing this issue. On a last note, the ControlNet tutorial can also be applied to image-to-image translation tasks.