MultiPoseNet: Fast Multi-Person Pose Estimation Using Pose Residual Network

Creative Commons License


15th European Conference on Computer Vision, ECCV 2018, Munich, Germany, 8 - 14 September 2018, pp.437-453 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1007/978-3-030-01252-6_26
  • City: Munich
  • Country: Germany
  • Page Numbers: pp.437-453
  • Keywords: Multi-task learning, Multi-person pose estimation, Semantic segmentation, MultiPoseNet, Pose residual network


In this paper, we present MultiPoseNet, a novel bottom-up multi-person pose estimation architecture that combines a multi-task model with a novel assignment method. MultiPoseNet can jointly handle person detection, person segmentation and pose estimation problems. The novel assignment method is implemented by the Pose Residual Network (PRN) which receives keypoint and person detections, and produces accurate poses by assigning keypoints to person instances. On the COCO keypoints dataset, our pose estimation method outperforms all previous bottom-up methods both in accuracy (+4-point mAP over previous best result) and speed; it also performs on par with the best top-down methods while being at least 4x faster. Our method is the fastest real time system with similar to 23 frames/sec.