BriefGPT.xyz
Dec, 2017
基于姿态的人类图像生成的可变形GANs
Deformable GANs for Pose-based Human Image Generation
HTML
PDF
Aliaksandr Siarohin, Enver Sangineto, Stephane Lathuiliere, Nicu Sebe
TL;DR
本文提出了一种基于GAN、可变形跳跃连接和最近邻损失的方法，用于合成给定姿势下的人物图像，并在各项指标上取得了最先进的结果。
Abstract
In this paper we address the problem of generating
person images
conditioned on a given
pose
. Specifically, given an image of a person and a target
→