3D Human Pose Estimation with 2D Marginal Heatmaps

Abstract

Automatically determining three-dimensional human pose from monocular RGB image data is a challenging problem. The two-dimensional nature of the input results in intrinsic ambiguities which make inferring depth particularly difficult. Recently, researchers have demonstrated that the flexible statistical modelling capabilities of deep neural networks are sufficient to make such inferences with reasonable accuracy. However, many of these models use coordinate output techniques which are memory-intensive, not differentiable, and/or do not spatially generalise well. We propose improvements to 3D coordinate prediction which avoid the aforementioned undesirable traits by predicting 2D marginal heatmaps under an augmented soft-argmax scheme. Our resulting model, MargiPose, produces visually coherent heatmaps whilst maintaining differentiability. We are also able to achieve state-of-the-art accuracy on publicly available 3D human pose estimation data.

Accepted in WACV 2019

References in corpus (13)

• DeepPose: Human Pose Estimation via Deep Neural Networks
• VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera
• A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay
• Stacked Hourglass Networks for Human Pose Estimation
• Human Pose Regression by Combining Indirect Part Detection and Contextual Information
• Multi-Context Attention for Human Pose Estimation
• LIFT: Learned Invariant Feature Transform
• A simple yet effective baseline for 3d human pose estimation
• Learning Feature Pyramids for Human Pose Estimation
• Adversarial PoseNet: A Structure-aware Convolutional Network for Human Pose Estimation
• Compositional Human Pose Regression
• Self Adversarial Training for Human Pose Estimation
• Learning 3D Human Pose from Structure and Motion

Cited by in corpus (6)

• Human Pose Regression by Combining Indirect Part Detection and Contextual Information
• How Robust is 3D Human Pose Estimation to Occlusion?
• Synthetic Occlusion Augmentation with Volumetric Heatmaps for the 2018 ECCV PoseTrack Challenge on 3D Human Pose Estimation
• SMPLR: Deep SMPL reverse for 3D human pose and shape recovery
• A Review on Human Pose Estimation
• DeepFuse: An IMU-Aware Network for Real-Time 3D Human Pose Estimation from Multi-View Image