Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach

Abstract

In this paper, we study the task of 3D human pose estimation in the wild. This task is challenging due to lack of training data, as existing datasets are either in the wild images with 2D pose or in the lab images with 3D pose. We propose a weakly-supervised transfer learning method that uses mixed 2D and 3D labels in a unified deep neutral network that presents two-stage cascaded structure. Our network augments a state-of-the-art 2D pose estimation sub-network with a 3D depth regression sub-network. Unlike previous two stage approaches that train the two sub-networks sequentially and separately, our training is end-to-end and fully exploits the correlation between the 2D pose and depth estimation sub-tasks. The deep features are better learnt through shared representations. In doing so, the 3D pose labels in controlled lab environments are transferred to in the wild images. In addition, we introduce a 3D geometric constraint to regularize the 3D pose prediction, which is effective in the absence of ground truth depth labels. Our method achieves competitive results on both 2D and 3D benchmarks.

arXiv commentAccepted to ICCV 2017

References in corpus (15)

• Deep Residual Learning for Image Recognition
• FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
• Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image
• Human pose estimation via Convolutional Part Heatmap Regression
• Stacked Hourglass Networks for Human Pose Estimation
• Convolutional Pose Machines
• MoCap-guided Data Augmentation for 3D Pose Estimation in the Wild
• Synthesizing Training Images for Boosting Human 3D Pose Estimation
• Structured Prediction of 3D Human Pose with Deep Neural Networks
• Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Video
• MonoCap: Monocular Human Motion Capture using a CNN Coupled with a Geometric Prior
• Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision
• Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose
• 3D Human Pose Estimation = 2D Pose Estimation + Matching
• 3D Shape Estimation from 2D Landmarks: A Convex Relaxation Approach

Cited by in corpus (29)

• BodyNet: Volumetric Inference of 3D Human Body Shapes
• Weakly-Supervised Discovery of Geometry-Aware Representation for 3D Human Pose Estimation
• Fast and Robust Multi-Person 3D Pose Estimation from Multiple Views
• 3D Human Pose Estimation in the Wild by Adversarial Learning
• Monocular Total Capture: Posing Face, Body, and Hands in the Wild
• Video Based Reconstruction of 3D People Models
• Learning to Estimate 3D Human Pose and Shape from a Single Color Image
• SMPLR: Deep SMPL reverse for 3D human pose and shape recovery
• Mo2Cap2: Real-time Mobile 3D Motion Capture with a Cap-mounted Fisheye Camera
• Integral Human Pose Regression
• PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation
• A Graph Attention Spatio-temporal Convolutional Network for 3D Human Pose Estimation in Video
• FBI-Pose: Towards Bridging the Gap between 2D Images and 3D Human Poses using Forward-or-Backward Information
• Cross-Domain Adaptation for Animal Pose Estimation
• Learning 3D Human Pose from Structure and Motion
• DeepSkeleton: Skeleton Map for 3D Human Pose Regression
• On the Robustness of Human Pose Estimation
• Single Image Human Proxemics Estimation for Visual Social Distancing
• StarMap for Category-Agnostic Keypoint and Viewpoint Estimation
• Ordinal Depth Supervision for 3D Human Pose Estimation
• Dense 3D Regression for Hand Pose Estimation
• Rethinking Pose in 3D: Multi-stage Refinement and Recovery for Markerless Motion Capture
• View Invariant 3D Human Pose Estimation
• Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning
• PedX: Benchmark Dataset for Metric 3D Pose Estimation of Pedestrians in Complex Urban Intersections
• Learning to Predict Diverse Human Motions from a Single Image via Mixture Density Networks
• Adversarial 3D Human Pose Estimation via Multimodal Depth Supervision
• Skeleton Transformer Networks: 3D Human Pose and Skinned Mesh from Single RGB Image
• Single-Shot Multi-Person 3D Pose Estimation From Monocular RGB