DHRNet: A Dual-Path Hierarchical Relation Network for Multi-Person Pose Estimation

TL;DR

DHRNet is a novel single-stage CNN approach for multi-person pose estimation that simultaneously models interactions between instances and joints, achieving state-of-the-art results on multiple challenging datasets.

Contribution

The paper introduces DHRNet, a dual-path hierarchical relation network that effectively captures cross-instance and cross-joint interactions for improved pose estimation.

Findings

Achieves state-of-the-art performance on COCO, CrowdPose, and OCHuman datasets.

Effectively models both instance-to-joint and joint-to-instance relations.

Outperforms existing methods in multi-person pose estimation accuracy.

Abstract

Multi-person pose estimation (MPPE) presents a formidable yet crucial challenge in computer vision. Most existing methods predominantly concentrate on isolated interaction either between instances or joints, which is inadequate for scenarios demanding concurrent localization of both instances and joints. This paper introduces a novel CNN-based single-stage method, named Dual-path Hierarchical Relation Network (DHRNet), to extract instance-to-joint and joint-to-instance interactions concurrently. Specifically, we design a dual-path interaction modeling module (DIM) that strategically organizes cross-instance and cross-joint interaction modeling modules in two complementary orders, enriching interaction information by integrating merits from different correlation modeling branches. Notably, DHRNet excels in joint localization by leveraging information from other instances and joints. Extensive evaluations on challenging datasets, including COCO, CrowdPose, and OCHuman datasets, showcase DHRNet's state-of-the-art performance. The code will be released at https://github.com/YHDang/dhrnet-multi-pose-estimation.