Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation

24 Nov 2019  ·  Jia Li, Wen Su, Zengfu Wang ·

We rethink a well-know bottom-up approach for multi-person pose estimation and propose an improved one. The improved approach surpasses the baseline significantly thanks to (1) an intuitional yet more sensible representation, which we refer to as body parts to encode the connection information between keypoints, (2) an improved stacked hourglass network with attention mechanisms, (3) a novel focal L2 loss which is dedicated to hard keypoint and keypoint association (body part) mining, and (4) a robust greedy keypoint assignment algorithm for grouping the detected keypoints into individual poses. Our approach not only works straightforwardly but also outperforms the baseline by about 15% in average precision and is comparable to the state of the art on the MS-COCO test-dev dataset. The code and pre-trained models are publicly available online.

PDF Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Pose Estimation COCO test-dev Simple Pose AP 68.1 # 25
APL 70.5 # 25
APM 66.8 # 18
AR 88.2 # 1
Keypoint Detection COCO test-dev Simple Pose APL 70.5 # 14
APM 66.8 # 9
AR 72.1 # 8
AR50 88.2 # 7
AP 68.1 # 3
Multi-Person Pose Estimation COCO test-dev Identity Mapping Hourglass AP 68.1 # 8
APL 70.5 # 6
APM 66.8 # 2
AR 72.1 # 2
AR50 88.2 # 2

Methods