TFPose: Direct Human Pose Estimation with Transformers

Abstract

We propose a human pose estimation framework that solves the task in the regression-based fashion. Unlike previous regression-based methods, which often fall behind those state-of-the-art methods, we formulate the pose estimation task into a sequence prediction problem that can effectively be solved by transformers. Our framework is simple and direct, bypassing the drawbacks of the heatmap-based pose estimation. Moreover, with the attention mechanism in transformers, our proposed framework is able to adaptively attend to the features most relevant to the target keypoints, which largely overcomes the feature misalignment issue of previous regression-based methods and considerably improves the performance. Importantly, our framework can inherently take advantages of the structured relationship between keypoints. Experiments on the MS-COCO and MPII datasets demonstrate that our method can significantly improve the state-of-the-art of regression-based pose estimation and perform comparably with the best heatmap-based pose estimation methods.

15 pages

References in corpus (6)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Rethinking on Multi-Stage Networks for Human Pose Estimation
• Multi-Context Attention for Human Pose Estimation
• DirectPose: Direct End-to-End Multi-Person Pose Estimation
• Human Pose Estimation with Spatial Contextual Information
• Rethinking the Heatmap Regression for Bottom-up Human Pose Estimation