Recent Advances in Unsupervised Image-to-image Tranformation
Today's talk is by Xun Huang from Cornell University (and Nvidia) on 'Recent Advances in Unsupervised Image to Image Translation' and was given at Microsoft Research in Sept 2019.
Note that for the title of the post we're using HTC preferred terminology of Transformation for this subject area, since Translation is typically thought of as an affine transformation.
2: Here are some associated references for the talk.
Here's his paper on MultiModal Unsupervised Image-to-Image Translation (MUNIT).
Original Unsupervised Image-to-Image Translation Networks (UNIT) Nvidia paper is here.
Proposes coupled GANs architecture.
Here's a comparison of CycleGan and Unit github project.
From the following paper.
3: On a totally different topic, his PointFlow paper on 3D Point Cloud generation is pretty interesting.