PoNA: Pose-guided Non-local Attention for Human Pose Transfer

Abstract

Human pose transfer, which aims at transferring the appearance of a given person to a target pose, is very challenging and important in many applications. Previous work ignores the guidance of pose features or only uses local attention mechanism, leading to implausible and blurry results. We propose a new human pose transfer method using a generative adversarial network (GAN) with simplified cascaded blocks. In each block, we propose a pose-guided non-local attention (PoNA) mechanism with a long-range dependency scheme to select more important regions of image features to transfer. We also design pre-posed image-guided pose feature update and post-posed pose-guided image feature update to better utilize the pose and image features. Our network is simple, stable, and easy to train. Quantitative and qualitative results on Market-1501 and DeepFashion datasets show the efficacy and efficiency of our model. Compared with state-of-the-art methods, our model generates sharper and more realistic images with rich details, while having fewer parameters and faster speed. Furthermore, our generated images can help to alleviate data insufficiency for person re-identification.

arXiv comment16 pages, 14 figures

References in corpus (9)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• 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
• Instance Normalization: The Missing Ingredient for Fast Stylization
• Self-Attention Generative Adversarial Networks
• Person Re-identification: Past, Present and Future

Cited by in corpus (7)

• Deep Person Generation: A Survey from the Perspective of Face, Pose and Cloth Synthesis
• AFFIRM: Affinity Fusion-based Framework for Iteratively Random Motion correction of multi-slice fetal brain MRI
• PISE: Person Image Synthesis and Editing with Decoupled GAN
• Human Image Generation: A Comprehensive Survey
• A 3D Mesh-based Lifting-and-Projection Network for Human Pose Transfer
• One-Shot Novel View and Pose Human Image Synthesis via 3D Prior Guided Diffusion Model
• GLocal: Global Graph Reasoning and Local Structure Transfer for Person Image Generation