LG AI Research· EXAONEResearch paper

[WACV 2024] UNSPAT: Uncertainty-Guided SpatioTemporal Transformer for 3D Human Pose and Shape Estimation on Videos

LG AI Research proposes a new framework for 3D human pose and shape estimation from video, incorporating Spatial Alignment Module, Space2Batch, and uncertainty-guided attention re-weighting, achieving state-of-the-art results on benchmarks and presented at WACV 2024.

From the source

In this study, we propose an efficient framework for 3D human pose and shape estimation in video [5] . Unlike previous video-based methods that use global average pooling to compress spatial information and then consider temporal relationships, we solved the excessive complexity of spatio-temporal attention through two modules: the 'Spatial Alignment Module' and 'Space2Batch.' We also utilized the uncertainty-guided attention re-weighting module to improve the robustness of the model in challenging environments such as occlusions and crowded backgrounds. Using these techniques, we achieved SOTA on widely used benchmark datasets and presented detailed results at WACV 2024, the leading conference in the computer vision.

lgresearch.ai