SRPose: Low-Resolution Human Pose Estimation with Super-Resolution
Smart innovation, systems and technologies(2023)
摘要
2D human pose estimation from given images has been an activate research area in computer vision. Existing methods based on deep learning rely on high-resolution input, which is not always available in many scenarios. To address the issues, a novel algorithm called Super-Resolved Pose estimation(SRPose) is proposed in this paper, which is composed of a super-resolution sub-network(SRN) and a following human pose estimation sub-network(HPEN). The SRN equipped with global residual learning and position-preserving block constructs a HR version from a LR input and then HPEN perform pose estimation. The whole SRPose is optimized with a unified loss in end-to-ento-en. Comprehensive experiments on public benchmarks verify the effectiveness and generalization of the proposed SRPose under the condition of the LR input.
更多查看译文
关键词
estimation,human,low-resolution,super-resolution
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要