GANerated Hands for Real-time 3D Hand Tracking from Monocular RGB

Abstract

We address the highly challenging problem of real-time 3D hand tracking based on a monocular RGB-only sequence. Our tracking method combines a convolutional neural network with a kinematic 3D hand model, such that it generalizes well to unseen data, is robust to occlusions and varying camera viewpoints, and leads to anatomically plausible as well as temporally smooth hand motions. For training our CNN we propose a novel approach for the synthetic generation of training data that is based on a geometrically consistent image-to-image translation network. To be more specific, we use a neural network that translates synthetic images to "real" images, such that the so-generated images follow the same statistical distribution as real-world hand images. For training this translation network we combine an adversarial loss and a cycle-consistency loss with a geometric consistency loss in order to preserve geometric properties (such as hand pose) during translation. We demonstrate that our hand tracking system outperforms the current state-of-the-art on challenging RGB-only footage.

References in corpus (11)

• ADADELTA: An Adaptive Learning Rate Method
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
• VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera
• Adversarial Discriminative Domain Adaptation
• Real-time Hand Tracking under Occlusion from an Egocentric RGB-D Sensor
• 3D Hand Pose Tracking and Estimation Using Stereo Matching
• Real-time Joint Tracking of a Hand Manipulating an Object from RGB-D Input
• Synthetic to Real Adaptation with Generative Correlation Alignment Networks
• Learning Human Pose Models from Synthesized Data for Robust RGB-D Action Recognition
• Back to RGB: 3D tracking of hands and hand-object interactions based on short-baseline stereo

Cited by in corpus (4)

• DenseAttentionSeg: Segment Hands from Interacted Objects Using Depth Input
• Neural Rendering and Reenactment of Human Actor Videos
• 3D Hand Pose Estimation using Simulation and Partial-Supervision with a Shared Latent Space
• DeepHPS: End-to-end Estimation of 3D Hand Pose and Shape by Learning from Synthetic Depth