TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Pose Transfer	Deep-Fashion	Progressive Pose Attention	SSIM	0.773	# 5
Pose Transfer	Deep-Fashion	Progressive Pose Attention	IS	3.209	# 7
Pose Transfer	Deep-Fashion	Progressive Pose Attention	DS	0.976	# 1
Pose Transfer	Deep-Fashion	Progressive Pose Attention	PCKh	0.96	# 2
Pose Transfer	Deep-Fashion	Progressive Pose Attention	Retrieval Top10 Recall	17.84	# 3
Pose Transfer	Market-1501	Progressive Pose Attention	DS	0.74	# 1
Pose Transfer	Market-1501	Progressive Pose Attention	IS	3.323	# 3
Pose Transfer	Market-1501	Progressive Pose Attention	PCKh	0.94	# 1
Pose Transfer	Market-1501	Progressive Pose Attention	SSIM	0.311	# 3
Pose Transfer	Market-1501	Progressive Pose Attention	mask-IS	3.773	# 2
Pose Transfer	Market-1501	Progressive Pose Attention	mask-SSIM	0.811	# 3

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/progressive-pose-attention-transfer-for/pose-transfer-on-market-1501)](https://paperswithcode.com/sota/pose-transfer-on-market-1501?p=progressive-pose-attention-transfer-for)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/progressive-pose-attention-transfer-for/pose-transfer-on-deep-fashion)](https://paperswithcode.com/sota/pose-transfer-on-deep-fashion?p=progressive-pose-attention-transfer-for)`

Progressive Pose Attention Transfer for Person Image Generation

CVPR 2019 · Zhen Zhu, Tengteng Huang, Baoguang Shi, Miao Yu, Bofei Wang, Xiang Bai ·

This paper proposes a new generative adversarial network for pose transfer, i.e., transferring the pose of a given person to a target pose. 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. Codes and models are available at: https://github.com/tengteng95/Pose-Transfer.git.

PDF Abstract CVPR 2019 PDF CVPR 2019 Abstract

Code

Add Remove Mark official

tengteng95/Pose-Transfer official

731

zsypotter/pose_transfer_keypoint

Tasks

Add Remove

Generative Adversarial Network

Image Generation

Person Re-Identification

Pose Transfer

Datasets

Market-1501

DeepFashion

DensePose

Results from the Paper

Edit

Ranked #1 on Pose Transfer on Market-1501

Get a GitHub badge

Task	Dataset	Model	Metric Name	Metric Value	Global Rank	Benchmark
Pose Transfer	Deep-Fashion	Progressive Pose Attention	SSIM	0.773	# 5	Compare
			IS	3.209	# 7	Compare
			DS	0.976	# 1	Compare
			PCKh	0.96	# 2	Compare
			Retrieval Top10 Recall	17.84	# 3	Compare
Pose Transfer	Market-1501	Progressive Pose Attention	DS	0.74	# 1	Compare
			IS	3.323	# 3	Compare
			PCKh	0.94	# 1	Compare
			SSIM	0.311	# 3	Compare
			mask-IS	3.773	# 2	Compare
			mask-SSIM	0.811	# 3	Compare

Methods

Add Remove

No methods listed for this paper. Add relevant methods here

Edit Social Preview

Progressive Pose Attention Transfer for Person Image Generation

Code Edit Add Remove Mark official

Tasks Edit Add Remove

Datasets Edit

Results from the Paper Edit

Methods Edit Add Remove

Code

Add Remove Mark official

Tasks

Add Remove

Datasets

Results from the Paper

Edit

Methods

Add Remove