Appearance and Pose-Conditioned Human Image Generation using Deformable GANs

04/30/2019
by   Aliaksandr Siarohin, et al.
0

In this paper, we address the problem of generating person images conditioned on both pose and appearance information. Specifically, given an image xa of a person and a target pose P(xb), extracted from a different image xb, we synthesize a new image of that person in pose P(xb), while preserving the visual details in xa. In order to deal with pixel-to-pixel misalignments caused by the pose differences between P(xa) and P(xb), we introduce deformable skip connections in the generator of our Generative Adversarial Network. Moreover, a nearest-neighbour loss is proposed instead of the common L1 and L2 losses in order to match the details of the generated image with the target image. Quantitative and qualitative results, using common datasets and protocols recently proposed for this task, show that our approach is competitive with respect to the state of the art. Moreover, we conduct an extensive evaluation using off-the-shell person re-identification (Re-ID) systems trained with person-generation based augmented data, which is one of the main important applications for this task. Our experiments show that our Deformable GANs can significantly boost the Re-ID accuracy and are even better than data-augmentation methods specifically trained using Re-ID losses.

READ FULL TEXT

page 1

page 4

page 8

page 10

page 12

page 13

page 14

page 15

research
12/29/2017

Deformable GANs for Pose-based Human Image Generation

In this paper we address the problem of generating person images conditi...
research
08/18/2020

Person image generation with semantic attention network for person re-identification

Pose variation is one of the key factors which prevents the network from...
research
01/02/2023

Learning Invariance from Generated Variance for Unsupervised Person Re-identification

This work focuses on unsupervised representation learning in person re-i...
research
12/06/2017

Pose-Normalized Image Generation for Person Re-identification

Person Re-identification (re-id) faces two major challenges: the lack of...
research
03/22/2021

Progressive and Aligned Pose Attention Transfer for Person Image Generation

This paper proposes a new generative adversarial network for pose transf...
research
06/06/2022

Scene Aware Person Image Generation through Global Contextual Conditioning

Person image generation is an intriguing yet challenging problem. Howeve...
research
02/19/2021

Pose Guided Person Image Generation with Hidden p-Norm Regression

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

Please sign up or login with your details

Forgot password? Click here to reset