Paper Info
Title
Liquid Warping GAN With Attention: A Unified Framework for Human Image Synthesis
Abstract
We tackle human image synthesis, including human motion imitation, appearance transfer, and novel view synthesis, within a unified framework. It means that the model, once being trained, can be used to handle all these tasks. The existing task-specific methods mainly use 2D keypoints (pose) to estimate the human body structure. However, they only express the position information with no ability to characterize the personalized shape of the person and model the limb rotations. In this paper, we propose to use a 3D body mesh recovery module to disentangle the pose and shape. It can not only model the joint location and rotation but also characterize the personalized body shape. To preserve the source information, such as texture, style, color, and face identity, we propose an Attentional Liquid Warping GAN with Attentional Liquid Warping Block (AttLWB) that propagates the source information in both image and feature spaces to the synthesized reference. Specifically, the source features are extracted by a denoising convolutional auto-encoder for characterizing the source identity well. Furthermore, our proposed method can support a more flexible warping from multiple sources. To further improve the generalization ability of the unseen source images, a one/few-shot adversarial learning is applied. In detail, it first trains a model in an extensive training set. Then, it finetunes the model by one/few-shot unseen image(s) in a self-supervised way to generate high-resolution ( <inline-formula><tex-math notation="LaTeX">$512 \times 512$</tex-math></inline-formula> and <inline-formula><tex-math notation="LaTeX">$1024 \times 1024$</tex-math></inline-formula> ) results. Also, we build a new dataset, namely Impersonator (iPER) dataset, for the evaluation of human motion imitation, appearance transfer, and novel view synthesis. Extensive experiments demonstrate the effectiveness of our methods in terms of preserving face identity, shape consistency, and clothes details. All codes and dataset are available on <uri>https://impersonator.org/work/impersonator-plus-plus.html</uri> .
Year
DOI
Venue
2022
10.1109/TPAMI.2021.3078270
IEEE Transactions on Pattern Analysis and Machine Intelligence
Keywords
DocType
Volume
Algorithms,Attention,Humans,Image Processing, Computer-Assisted
Journal
44
Issue
ISSN
Citations 
9
0162-8828
1
PageRank 
References 
Authors
0.35
30
6
Name
Order
Citations
PageRank
Wen Liu1493.57
Zhixin Piao211.36
Zhi Tu310.35
Wenhan Luo421419.48
Lin Ma591271.35
Shenghua Gao6160766.89