|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
Specifically, given an image of a person and a target pose, we synthesize a new image of that person in the novel pose.
#4 best model for Pose Transfer on Deep-Fashion
Generating novel, yet realistic, images of persons is a challenging task due to the complex interplay between the different image factors, such as the foreground, background and pose information.
#2 best model for Gesture-to-Gesture Translation on Senz3D
We address the problem of guided image-to-image translation where we translate an input image into another while respecting the constraints provided by an external, user-provided guidance image.
Unlike existing methods, we propose to estimate dense and intrinsic 3D appearance flow to better guide the transfer of pixels between poses.
This paper proposes the novel Pose Guided Person Generation Network (PG$^2$) that allows to synthesize person images in arbitrary poses, based on an image of that person and a novel pose.
#3 best model for Pose Transfer on Deep-Fashion