Learning to Refine Human Pose Estimation

21 Apr 2018  ·  Mihai Fieraru, Anna Khoreva, Leonid Pishchulin, Bernt Schiele ·

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.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Keypoint Detection MPII Multi-Person Refine mAP@0.5 78% # 4
Multi-Person Pose Estimation MPII Multi-Person Refine AP 78% # 4
Pose Estimation MPII Single Person Refine PCKh@0.5 92.1 # 2
Multi-Person Pose Estimation PoseTrack2018 Refine Mean mAP 73.8 # 3
Multi-Person Pose Estimation and Tracking PoseTrack2018 Refine MOTA 58.4 # 1

Methods


No methods listed for this paper. Add relevant methods here