Nov 25, 2018 · We propose a novel Partition-Controlled GAN to generate human images according to target pose and background.

In this paper, we propose a novel Partition-Controlled GAN to generate human images according to target pose and background. Firstly, human poses in the given ...

In this paper, we propose a novel Partition-Controlled. GAN to generate human images according to target pose and background. Firstly, human poses in the given ...

A novel Partition-Controlled GAN is proposed to generate human images according to target pose and background to extract and fuse appearance features, ...

PCGAN · Requirment · Clone repository · Training · Testing. Download checkpoints (https://drive.google.com/drive/folders/1xAzxIjLE8mWqOiueuKXK0A ...

PCGAN: Partition-Controlled Human Image Generation. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 8698-8705. https://doi.org ...

In this paper, a perceptual metrics guided GAN (PIGGAN) framework is proposed to intrinsically optimize generation processing for pose transfer task.

In this paper, we propose a novel human image generation framework called HIGSA that can utilize the position information from the input source image.

PCGAN: Partition-Controlled Human Image Generation · 1 code implementation • 25 Nov 2018 • Dong Liang, Rui Wang, Xiaowei Tian, Cong Zou. Human image generation ...

A novel Bipartite Graph Reasoning GAN (BiGraphGAN) block aims to reason the crossing long-range relations between the source pose and the target pose in a ...