The state-of-the-art for monocular 3D human pose estimation in videos is dominated by the paradigm of 2D-to-3D pose uplifting. While the uplifting methods themselves are rather efficient, the true computational complexity depends on the per-frame 2D pose estimation. In this paper, we present a Transformer-based pose uplifting scheme that can operate on temporally sparse 2D pose sequences but still produce temporally dense 3D pose estimates. We show how masked token modeling can be utilized for temporal upsampling within Transformer blocks. This allows to decouple the sampling rate of input 2D poses and the target frame rate of the video and drastically decreases the total computational complexity. Additionally, we explore the option of pre-training on large motion capture archives, which has been largely neglected so far. We evaluate our method on two popular benchmark datasets: Human3.6M and MPI-INF-3DHP. With an MPJPE of 45.0 mm and 46.9 mm, respectively, our proposed method can compete with the state-of-the-art while reducing inference time by a factor of 12. This enables real-time throughput with variable consumer hardware in stationary and mobile applications. We release our code and models at https://github.com/goldbricklemon/uplift-upsample-3dhpe

本文提出了一种基于 Transformer 的姿势提升方案，能够处理时间上稀疏的二维姿势序列，但仍能产生时间上密集的三维姿势估计。其采用掩码令牌建模来实现 Transformer 块内的时间上采样，可以大大降低总计算复杂度。在 Human3.6M 和 MPI-INF-3DHP 上评估表明，相对于现有的方法，所提出的方法在保持准确性的同时将推理时间降低了12倍，这提高了在不同应用中使用可变消费者硬件的实时吞吐量。

通过-Uplifting-Transformers实现高效三维人体姿势估计的提升和上采样