| # SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimation | |
| <!-- [ALGORITHM] --> | |
| <details> | |
| <summary align="right"><a href="https://arxiv.org/abs/2107.03332">SimCC (ECCV'2022)</a></summary> | |
| ```bibtex | |
| @misc{https://doi.org/10.48550/arxiv.2107.03332, | |
| title={SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimation}, | |
| author={Li, Yanjie and Yang, Sen and Liu, Peidong and Zhang, Shoukui and Wang, Yunxiao and Wang, Zhicheng and Yang, Wankou and Xia, Shu-Tao}, | |
| year={2021} | |
| } | |
| ``` | |
| </details> | |
| ## Abstract | |
| <!-- [ABSTRACT] --> | |
| The 2D heatmap-based approaches have dominated Human Pose Estimation (HPE) for years due to high performance. However, the long-standing quantization error problem in the 2D heatmap-based methods leads to several well-known drawbacks: 1) The performance for the low-resolution inputs is limited; 2) To improve the feature map resolution for higher localization precision, multiple costly upsampling layers are required; 3) Extra post-processing is adopted to reduce the quantization error. To address these issues, we aim to explore a brand new scheme, called \\textit{SimCC}, which reformulates HPE as two classification tasks for horizontal and vertical coordinates. The proposed SimCC uniformly divides each pixel into several bins, thus achieving \\emph{sub-pixel} localization precision and low quantization error. Benefiting from that, SimCC can omit additional refinement post-processing and exclude upsampling layers under certain settings, resulting in a more simple and effective pipeline for HPE. Extensive experiments conducted over COCO, CrowdPose, and MPII datasets show that SimCC outperforms heatmap-based counterparts, especially in low-resolution settings by a large margin. | |
| <!-- [IMAGE] --> | |
| <div align=center> | |
| <img src="https://user-images.githubusercontent.com/13503330/189811385-6395d118-055b-4bad-89e8-f84ffa2c2aa6.png"> | |
| </div> | |