Bipartite Graph Reasoning GANs for Person Image Generation
arXiv:2008.04381
Abstract
We present a novel Bipartite Graph Reasoning GAN (BiGraphGAN) for the challenging person image generation task. The proposed graph generator mainly consists of two novel blocks that aim to model the pose-to-pose and pose-to-image relations, respectively. Specifically, the proposed Bipartite Graph Reasoning (BGR) block aims to reason the crossing long-range relations between the source pose and the target pose in a bipartite graph, which mitigates some challenges caused by pose deformation. Moreover, we propose a new Interaction-and-Aggregation (IA) block to effectively update and enhance the feature representation capability of both person's shape and appearance in an interactive way. Experiments on two challenging and public datasets, i.e., Market-1501 and DeepFashion, show the effectiveness of the proposed BiGraphGAN in terms of objective quantitative scores and subjective visual realness. The source code and trained models are available at https://github.com/Ha0Tang/BiGraphGAN.
13 pages, 6 figures, accepted to BMVC 2020 as an oral paper, fix typos
References in corpus (8)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Improved Techniques for Training GANs
- Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
- Semantic Image Synthesis with Spatially-Adaptive Normalization
- Dual Graph Convolutional Network for Semantic Segmentation
- RelGAN: Multi-Domain Image-to-Image Translation via Relative Attributes
- Progressive Pose Attention Transfer for Person Image Generation
- Exocentric to Egocentric Image Generation via Parallel Generative Adversarial Network
Cited by in corpus (8)
- Image-to-Image Translation: Methods and Applications
- PISE: Person Image Synthesis and Editing with Decoupled GAN
- Human Image Generation: A Comprehensive Survey
- Learning Semantic Person Image Generation by Region-Adaptive Normalization
- Intrinsic-Extrinsic Preserved GANs for Unsupervised 3D Pose Transfer
- A 3D Mesh-based Lifting-and-Projection Network for Human Pose Transfer
- 3D-Aware Semantic-Guided Generative Model for Human Synthesis
- GLocal: Global Graph Reasoning and Local Structure Transfer for Person Image Generation