Generative Partition Networks for Multi-Person Pose Estimation

Abstract

This paper proposes a new Generative Partition Network (GPN) to address the challenging multi-person pose estimation problem. Different from existing models that are either completely top-down or bottom-up, the proposed GPN introduces a novel strategy--it generates partitions for multiple persons from their global joint candidates and infers instance-specific joint configurations simultaneously. The GPN is favorably featured by low complexity and high accuracy of joint detection and re-organization. In particular, GPN designs a generative model that performs one feed-forward pass to efficiently generate robust person detections with joint partitions, relying on dense regressions from global joint candidates in an embedding space parameterized by centroids of persons. In addition, GPN formulates the inference procedure for joint configurations of human poses as a graph partition problem, and conducts local optimization for each person detection with reliable global affinity cues, leading to complexity reduction and performance improvement. GPN is implemented with the Hourglass architecture as the backbone network to simultaneously learn joint detector and dense regressor. Extensive experiments on benchmarks MPII Human Pose Multi-Person, extended PASCAL-Person-Part, and WAF, show the efficiency of GPN with new state-of-the-art performance.

References in corpus (8)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Deep Residual Learning for Image Recognition
• Associative Embedding: End-to-End Learning for Joint Detection and Grouping
• Stacked Hourglass Networks for Human Pose Estimation
• Convolutional Pose Machines
• Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Parts
• Towards Accurate Multi-person Pose Estimation in the Wild
• RMPE: Regional Multi-person Pose Estimation

Cited by in corpus (5)

• Self-supervised Keypoint Correspondences for Multi-Person Pose Estimation and Tracking in Videos
• Differentiable Hierarchical Graph Grouping for Multi-Person Pose Estimation
• Multi-person Articulated Tracking with Spatial and Temporal Embeddings
• Whole-Body Human Pose Estimation in the Wild
• Multi-task human analysis in still images: 2D/3D pose, depth map, and multi-part segmentation