image
Papers with tag image
2022
2021
2020
- Rethinking the Heatmap Regression for Bottom-up Human Pose EstimationZhengxiong Luo, Zhicheng Wang, Yan Huang, Tieniu Tan, and Erjin ZhouIn 2020
Heatmap regression has become the most prevalent choice for nowadays humanpose estimation methods. The ground-truth heatmaps are usually constructed viacovering all skeletal keypoints by 2D gaussian kernels. The standard deviationsof these kernels are fixed. However, for bottom-up methods, which need tohandle a large variance of human scales and labeling ambiguities, the currentpractice seems unreasonable. To better cope with these problems, we propose thescale-adaptive heatmap regression (SAHR) method, which can adaptively adjustthe standard deviation for each keypoint. In this way, SAHR is more tolerant ofvarious human scales and labeling ambiguities. However, SAHR may aggravate theimbalance between fore-background samples, which potentially hurts theimprovement of SAHR. Thus, we further introduce the weight-adaptive heatmapregression (WAHR) to help balance the fore-background samples. Extensiveexperiments show that SAHR together with WAHR largely improves the accuracy ofbottom-up human pose estimation. As a result, we finally outperform thestate-of-the-art model by +1.5AP and achieve 72.0AP on COCO test-dev2017, whichis com-arable with the performances of most top-down methods. Source codes areavailable at https://github.com/greatlog/SWAHR-HumanPose.
均衡不同距离的heatmap的高斯核大小
human image 2dpose@inproceedings{2012.15175, title = {Rethinking the Heatmap Regression for Bottom-up Human Pose Estimation}, author = {Luo, Zhengxiong and Wang, Zhicheng and Huang, Yan and Tan, Tieniu and Zhou, Erjin}, year = {2020}, tags = {human, image, 2dpose}, }