Progressive Pose Attention Transfer for Person Image Generation

Abstract

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.

To appear in CVPR 2019, oral presentation (21 pages, 15 figures including the supplementary materials)

References in corpus (12)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Auto-Encoding Variational Bayes
• Conditional Generative Adversarial Nets
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Improving neural networks by preventing co-adaptation of feature detectors
• Instance Normalization: The Missing Ingredient for Fast Stylization
• Conditional Image Synthesis With Auxiliary Classifier GANs
• Multi-View Image Generation from a Single-View
• Exemplar Guided Unsupervised Image-to-Image Translation with Semantic Consistency
• VITON: An Image-based Virtual Try-on Network
• Disentangled Person Image Generation
• Dense Pose Transfer

Cited by in corpus (13)

• Bipartite Graph Reasoning GANs for Person Image Generation
• Generative Adversarial Networks for Image and Video Synthesis: Algorithms and Applications
• Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generation
• Controllable Person Image Synthesis with Spatially-Adaptive Warped Normalization
• MM-Hand: 3D-Aware Multi-Modal Guided Hand Generative Network for 3D Hand Pose Synthesis
• Recapture as You Want
• PMC-GANs: Generating Multi-Scale High-Quality Pedestrian with Multimodal Cascaded GANs
• Direct May Not Be the Best: An Incremental Evolution View of Pose Generation
• Learning Semantic Person Image Generation by Region-Adaptive Normalization
• Semantically Multi-modal Image Synthesis
• EgoRenderer: Rendering Human Avatars from Egocentric Camera Images
• Intrinsic Temporal Regularization for High-resolution Human Video Synthesis
• MGD-GAN: Text-to-Pedestrian generation through Multi-Grained Discrimination