Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation
This work addresses pose estimation for computer vision applications, offering an incremental improvement over existing methods.
The paper tackles multi-person pose estimation by improving a bottom-up approach, resulting in a 15% average precision gain over the baseline and competitive performance on the MS-COCO dataset.
We rethink a well-know bottom-up approach for multi-person pose estimation and propose an improved one. The improved approach surpasses the baseline significantly thanks to (1) an intuitional yet more sensible representation, which we refer to as body parts to encode the connection information between keypoints, (2) an improved stacked hourglass network with attention mechanisms, (3) a novel focal L2 loss which is dedicated to hard keypoint and keypoint association (body part) mining, and (4) a robust greedy keypoint assignment algorithm for grouping the detected keypoints into individual poses. Our approach not only works straightforwardly but also outperforms the baseline by about 15% in average precision and is comparable to the state of the art on the MS-COCO test-dev dataset. The code and pre-trained models are publicly available online.