Single-shot 3D multi-person pose estimation in complex images

Abdallah Benzine, Bertrand Luvison, Quoc Cuong Pham, Catherine Achard

Abstract: Highlights•Multi-person 3D human pose estimation in rich and complex environments.•2D and 3D human joints are predicted using heatmaps and Occlusion Robust Pose Maps.•The difficult problem of associating joints to people skeletons is managed using the associative embeddings method.•The proposed approach results surpass single-shot methods of the state of the art on the CMU Panoptic dataset and MuPoTS-3D datasets.•Experiments on the JTA Dataset show that complex urban scenarios with many people at different image resolution remains a challenge for our approach.