Learning to Refine Human Pose Estimation

Citations Over TimeTop 10% of 2018 papers

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.

Related Papers

• → 3D Head Pose Estimation Using Non-rigid Structure-from-motion and Point Correspondence(2006)10 cited
• → Cylindrical Model-Based Head Tracking and 3D Pose Recovery from Sequential Face Images(2006)13 cited
• → Vector-based monocular 3D pose estimation in handling self-occlusion and foreshortening(2012)
• → Simultaneous pose motion recovery and video object cutout(2009)
• Appearance-based person tracking and 3D pose estimation of upper-body and head(2010)