Human Motion Transfer with 3D Constraints and Detail Enhancement

Abstract

We propose a new method for realistic human motion transfer using a generative adversarial network (GAN), which generates a motion video of a target character imitating actions of a source character, while maintaining high authenticity of the generated results. We tackle the problem by decoupling and recombining the posture information and appearance information of both the source and target characters. The innovation of our approach lies in the use of the projection of a reconstructed 3D human model as the condition of GAN to better maintain the structural integrity of transfer results in different poses. We further introduce a detail enhancement net to enhance the details of transfer results by exploiting the details in real source frames. Extensive experiments show that our approach yields better results both qualitatively and quantitatively than the state-of-the-art methods.

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Conditional Generative Adversarial Nets
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Alias-Free Generative Adversarial Networks
• OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
• Pose Guided Person Image Generation
• High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
• Video-to-Video Synthesis

Cited by in corpus (5)

• An Identity-Preserved Framework for Human Motion Transfer
• Robust Pose Transfer with Dynamic Details using Neural Video Rendering
• A 3D Mesh-based Lifting-and-Projection Network for Human Pose Transfer
• CorrNet3D: Unsupervised End-to-end Learning of Dense Correspondence for 3D Point Clouds
• A Shape-Aware Retargeting Approach to Transfer Human Motion and Appearance in Monocular Videos