Progressive Pose Attention Transfer for Person Image Generation (2019-04-06T00:00:00.000000Z)

TL;DR

A new generative adversarial network to the problem of pose transfer, i.e., transferring the pose of a given person to a target one, which can generate training images for person re-identification, alleviating data insufficiency.

Abstract

This paper proposes a new generative adversarial network to the problem of pose transfer, i.e., transferring the pose of a given person to a target one. The generator of the network comprises a sequence of Pose-Attentional Transfer Blocks that each transfers certain regions it attends to, generating the person image progressively. Compared with those in previous works, our generated person images possess better appearance consistency and shape consistency with the input images, thus significantly more realistic-looking. The efficacy and efficiency of the proposed network are validated both qualitatively and quantitatively on Market-1501 and DeepFashion. Furthermore, the proposed architecture can generate training images for person re-identification, alleviating data insufficiency.

Authors

X. Bai

25 papers

Zhen Zhu

3 papers

Baoguang Shi

4 papers

TL;DR

Abstract

Authors

References49 items

SwapNet: Image Based Garment Transfer

Dense Pose Transfer

Toward Characteristic-Preserving Image-based Virtual Try-On Network

Free-Form Image Inpainting With Gated Convolution

Human Appearance Transfer

Unsupervised Person Image Synthesis in Arbitrary Poses

Exemplar Guided Unsupervised Image-to-Image Translation

Synthesizing Images of Humans in Unseen Poses

A Variational U-Net for Conditional Appearance and Shape Generation

DensePose: Dense Human Pose Estimation in the Wild

Deformable GANs for Pose-Based Human Image Generation

Disentangled Person Image Generation

VITON: An Image-Based Virtual Try-on Network

Pose Guided Person Image Generation

A Generative Model of People in Clothing

The Pose Knows: Video Forecasting by Generating Pose Futures

Multi-View Image Generation from a Single-View

Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks

Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in Vitro

Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields

Image-to-Image Translation with Conditional Adversarial Networks

Conditional Image Synthesis with Auxiliary Classifier GANs

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

Instance Normalization: The Missing Ingredient for Fast Stylization

DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations

Improved Techniques for Training GANs

Perceptual Losses for Real-Time Style Transfer and Super-Resolution

Deep Residual Learning for Image Recognition

SSD: Single Shot MultiBox Detector

Scalable Person Re-identification: A Benchmark

Rethinking the Inception Architecture for Computer Vision

Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Adam: A Method for Stochastic Optimization

Conditional Generative Adversarial Nets

Very Deep Convolutional Networks for Large-Scale Image Recognition

ImageNet Large Scale Visual Recognition Challenge

2D Human Pose Estimation: New Benchmark and State of the Art Analysis

Auto-Encoding Variational Bayes

Articulated Human Detection with Flexible Mixtures of Parts

Improving neural networks by preventing co-adaptation of feature detectors

Robust object pose estimation via statistical manifold modeling

Rectified Linear Units Improve Restricted Boltzmann Machines

Inferring 3D body pose from silhouettes using activity manifold learning

Image quality assessment: from error visibility to structural similarity

GENERATIVE ADVERSARIAL NETS

Person re-identiﬁcation: Past, present and future

Rectifier Nonlinearities Improve Neural Network Acoustic Models

Realtime multi - person 2 d pose estimation using part affinity fields Elgammal and Chan - Su Lee . Inferring 3 d body pose from silhouettes using activity manifold learning

Field of Study

Journal Information

Name

Page

Venue Information

Name

Type

URL

Alternate Names