Learning to Refine Human Pose Estimation
arXiv:1804.07909
Abstract
Multi-person pose estimation in images and videos is an important yet challenging task with many applications. Despite the large improvements in human pose estimation enabled by the development of convolutional neural networks, there still exist a lot of difficult cases where even the state-of-the-art models fail to correctly localize all body joints. This motivates the need for an additional refinement step that addresses these challenging cases and can be easily applied on top of any existing method. In this work, we introduce a pose refinement network (PoseRefiner) which takes as input both the image and a given pose estimate and learns to directly predict a refined pose by jointly reasoning about the input-output space. In order for the network to learn to refine incorrect body joint predictions, we employ a novel data augmentation scheme for training, where we model "hard" human pose cases. We evaluate our approach on four popular large-scale pose estimation benchmarks such as MPII Single- and Multi-Person Pose Estimation, PoseTrack Pose Estimation, and PoseTrack Pose Tracking, and report systematic improvement over the state of the art.
arXiv commentTo appear in CVPRW (2018). Workshop: Visual Understanding of Humans in Crowd Scene and the 2nd Look Into Person Challenge (VUHCS-LIP)
References in corpus (14)
- TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
- DeepPose: Human Pose Estimation via Deep Neural Networks
- Associative Embedding: End-to-End Learning for Joint Detection and Grouping
- Stacked Hourglass Networks for Human Pose Estimation
- Convolutional Pose Machines
- Cascaded Pyramid Network for Multi-Person Pose Estimation
- Towards Accurate Multi-person Pose Estimation in the Wild
- Learning Feature Pyramids for Human Pose Estimation
- Adversarial PoseNet: A Structure-aware Convolutional Network for Human Pose Estimation
- Cascade Residual Learning: A Two-stage Convolutional Neural Network for Stereo Matching
- Human Pose Estimation using Deep Consensus Voting
- Thin-Slicing Network: A Deep Structured Model for Pose Estimation in Videos
- Error Correction for Dense Semantic Image Labeling
- Mass Displacement Networks