Differentiable Hierarchical Graph Grouping for Multi-Person Pose Estimation

07/23/2020
by   Sheng Jin, et al.
0

Multi-person pose estimation is challenging because it localizes body keypoints for multiple persons simultaneously. Previous methods can be divided into two streams, i.e. top-down and bottom-up methods. The top-down methods localize keypoints after human detection, while the bottom-up methods localize keypoints directly and then cluster/group them for different persons, which are generally more efficient than top-down methods. However, in existing bottom-up methods, the keypoint grouping is usually solved independently from keypoint detection, making them not end-to-end trainable and have sub-optimal performance. In this paper, we investigate a new perspective of human part grouping and reformulate it as a graph clustering task. Especially, we propose a novel differentiable Hierarchical Graph Grouping (HGG) method to learn the graph grouping in bottom-up multi-person pose estimation task. Moreover, HGG is easily embedded into main-stream bottom-up methods. It takes human keypoint candidates as graph nodes and clusters keypoints in a multi-layer graph neural network model. The modules of HGG can be trained end-to-end with the keypoint detection network and is able to supervise the grouping process in a hierarchical manner. To improve the discrimination of the clustering, we add a set of edge discriminators and macro-node discriminators. Extensive experiments on both COCO and OCHuman datasets demonstrate that the proposed method improves the performance of bottom-up pose estimation methods.

READ FULL TEXT

page 2

page 14

research
11/16/2016

Associative Embedding: End-to-End Learning for Joint Detection and Grouping

We introduce associative embedding, a novel method for supervising convo...
research
04/06/2021

Learning Spatial Context with Graph Neural Network for Multi-Person Pose Grouping

Bottom-up approaches for image-based multi-person pose estimation consis...
research
06/28/2020

Multi-Person Pose Regression via Pose Filtering and Scoring

Multi-person pose estimation is one of the mainstream tasks of computer ...
research
03/21/2019

Multi-person Articulated Tracking with Spatial and Temporal Embeddings

We propose a unified framework for multi-person pose estimation and trac...
research
07/07/2021

Greedy Offset-Guided Keypoint Grouping for Human Pose Estimation

We propose a simple yet reliable bottom-up approach with a good trade-of...
research
10/23/2020

Efficient grouping for keypoint detection

The success of deep neural networks in the traditional keypoint detectio...
research
03/08/2021

Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsing

To address the challenging task of instance-aware human part parsing, a ...

Please sign up or login with your details

Forgot password? Click here to reset