This repository is an official PyTorch implementation of the paper "Learnable Triangulation of Human Pose" (ICCV 2019, oral). Proposed method archives state-of-the-art results in multi-view 3D human pose estimation!
Does heatmap i.e. alg_confidence in the code represent the confidence of the predicted 2D keypoints, which I found to keep a small value. If not, where can I get the confidence of 2D keypoints for 2D images?
Does heatmap i.e. alg_confidence in the code represent the confidence of the predicted 2D keypoints, which I found to keep a small value. If not, where can I get the confidence of 2D keypoints for 2D images?