HeatER: An Efficient and Unified Network for Human Reconstruction via Heatmap-based TransformER. (arXiv:2205.15448v1 [cs.CV])

Recently, vision transformers have shown great success in 2D human pose
estimation (2D HPE), 3D human pose estimation (3D HPE), and human mesh
reconstruction (HMR) tasks. In these tasks, heatmap representations of the
human structural information are often extracted first from the image by a CNN,
and then further processed with a transformer architecture to provide the final
HPE or HMR estimation. However, existing transformer architectures are not able
to process these heatmap inputs directly, forcing an unnatural flattening of …

arxiv cv heatmap human network transformer