# Greedy Offset-Guided Keypoint Grouping for Human Pose Estimation Source: [Greedy Offset-Guided Keypoint Grouping for Human Pose Estimation]() Collection index: [llms.txt]() Data updated: 2025-12-24T16:19:59.847Z Authors: Jia Li, Linhua Xiang, Jiwei Chen, Zengfu Wang Published: 2021-07-07T09:32:01.000Z ## Abstract We propose a simple yet reliable bottom-up approach with a good trade-off between accuracy and efficiency for the problem of multi-person pose estimation. Given an image, we employ an Hourglass Network to infer all the keypoints from different persons indiscriminately as well as the guiding offsets connecting the adjacent keypoints belonging to the same persons. Then, we greedily group the candidate keypoints into multiple human poses (if any), utilizing the predicted guiding offsets. And we refer to this process as greedy offset-guided keypoint grouping (GOG). Moreover, we revisit the encoding-decoding method for the multi-person keypoint coordinates and reveal some important facts affecting accuracy. Experiments have demonstrated the obvious performance improvements brought by the introduced components. Our approach is comparable to the state of the art on the challenging COCO dataset under fair conditions. The source code and our pre-trained model are publicly available online. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Multi-Person Pose Estimation on COCO (test-dev)](): Multi-person Pose Estimation; COCO (test-dev); AP: 65.6. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()