Towards Precise 3D Human Pose Estimation with Multi-Perspective Spatial-Temporal Relational Transformers. (arXiv:2401.16700v1 [cs.CV])

3D human pose estimation captures the human joint points in three-dimensional
space while keeping the depth information and physical structure. That is
essential for applications that require precise pose information, such as
human-computer interaction, scene understanding, and rehabilitation training.
Due to the challenges in data collection, mainstream datasets of 3D human pose
estimation are primarily composed of multi-view video data collected in
laboratory environments, which contains rich spatial-temporal correlation
information besides the image frame content. Given the remarkable
self-attention mechanism …

applications arxiv challenges collection computer cs.cv data data collection human human-computer interaction information perspective relational space spatial temporal three-dimensional training transformers understanding