Ordinal Depth Supervision for 3D Human Pose Estimation
arXiv:1805.04095
Abstract
Our ability to train end-to-end systems for 3D human pose estimation from single images is currently constrained by the limited availability of 3D annotations for natural images. Most datasets are captured using Motion Capture (MoCap) systems in a studio setting and it is difficult to reach the variability of 2D human pose datasets, like MPII or LSP. To alleviate the need for accurate 3D ground truth, we propose to use a weaker supervision signal provided by the ordinal depths of human joints. This information can be acquired by human annotators for a wide range of images and poses. We showcase the effectiveness and flexibility of training Convolutional Networks (ConvNets) with these ordinal relations in different settings, always achieving competitive performance with ConvNets trained with accurate 3D joint coordinates. Additionally, to demonstrate the potential of the approach, we augment the popular LSP and MPII datasets with ordinal depth annotations. This extension allows us to present quantitative and qualitative evaluation in non-studio conditions. Simultaneously, these ordinal annotations can be easily incorporated in the training procedure of typical ConvNets for 3D human pose. Through this inclusion we achieve new state-of-the-art performance for the relevant benchmarks and validate the effectiveness of ordinal depth supervision for 3D human pose.
arXiv commentCVPR 2018 Camera Ready
References in corpus (24)
- VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera
- Learning from Synthetic Humans
- Associative Embedding: End-to-End Learning for Joint Detection and Grouping
- Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image
- Stacked Hourglass Networks for Human Pose Estimation
- Convolutional Pose Machines
- MoCap-guided Data Augmentation for 3D Pose Estimation in the Wild
- Sparse Representation for 3D Shape Estimation: A Convex Relaxation Approach
- Attention to Scale: Scale-aware Semantic Image Segmentation
- Single-Image Depth Perception in the Wild
- A simple yet effective baseline for 3d human pose estimation
- Flowing ConvNets for Human Pose Estimation in Videos
- Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach
- Synthesizing Training Images for Boosting Human 3D Pose Estimation
- Learning Feature Pyramids for Human Pose Estimation
- Compositional Human Pose Regression
- Structured Prediction of 3D Human Pose with Deep Neural Networks
- Unite the People: Closing the Loop Between 3D and 2D Human Representations
- Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Video
- DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation
- MonoCap: Monocular Human Motion Capture using a CNN Coupled with a Geometric Prior
- Learning to Fuse 2D and 3D Image Cues for Monocular Body Pose Estimation
- Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision
- 3D Human Pose Estimation from a Single Image via Distance Matrix Regression