MUST-GAN: Multi-level Statistics Transfer for Self-driven Person Image Generation

by   Tianxiang Ma, et al.

Pose-guided person image generation usually involves using paired source-target images to supervise the training, which significantly increases the data preparation effort and limits the application of the models. To deal with this problem, we propose a novel multi-level statistics transfer model, which disentangles and transfers multi-level appearance features from person images and merges them with pose features to reconstruct the source person images themselves. So that the source images can be used as supervision for self-driven person image generation. Specifically, our model extracts multi-level features from the appearance encoder and learns the optimal appearance representation through attention mechanism and attributes statistics. Then we transfer them to a pose-guided generator for re-fusion of appearance and pose. Our approach allows for flexible manipulation of person appearance and pose properties to perform pose transfer and clothes style transfer tasks. Experimental results on the DeepFashion dataset demonstrate our method's superiority compared with state-of-the-art supervised and unsupervised methods. In addition, our approach also performs well in the wild.


page 1

page 3

page 4

page 6

page 7

page 8


Attention-based Fusion for Multi-source Human Image Generation

We present a generalization of the person-image generation task, in whic...

Pose Guided Person Image Generation with Hidden p-Norm Regression

In this paper, we propose a novel approach to solve the pose guided pers...

Multi-scale Attention Guided Pose Transfer

Pose transfer refers to the probabilistic image generation of a person w...

Two-Stream Appearance Transfer Network for Person Image Generation

Pose guided person image generation means to generate a photo-realistic ...

Open-World Pose Transfer via Sequential Test-Time Adaption

Pose transfer aims to transfer a given person into a specified posture, ...

Person-in-Context Synthesiswith Compositional Structural Space

Despite significant progress, controlled generation of complex images wi...

Unsupervised Person Image Generation with Semantic Parsing Transformation

In this paper, we address unsupervised pose-guided person image generati...

Please sign up or login with your details

Forgot password? Click here to reset