Many image-to-image (I2I) translation problems are in nature of high diversity that a single input may have various counterparts. The multi-modal network can build many-to-many mapping between two visual domains has been proposed prior works. However, most them guided by sampled noises. Some others encode the reference image into latent vector, which would eliminate semantic information image. ...

Background: Cone-beam computed tomography (CBCT) scanners for image-guided radiotherapy are in clinical use today, but there has been no consensus on uniform acceptance to verify the CBCT image quality yet. The present work proposed new methods to fully evaluate the performance of CBCT in its three-dimensional (3D) reconstruction space. Materials and Methods: Compared to the traditional methods...