Papers › PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up,...

PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model

22 Mar 2018ECCV 2018 9arXiv:1803.08225archive 2025-07-28

George Papandreou, Tyler Zhu, Liang-Chieh Chen, Spyros Gidaris, Jonathan Tompson, Kevin Murphy

We present a box-free bottom-up approach for the tasks of pose estimation and instance segmentation of people in multi-person images using an efficient single-shot model. The proposed PersonLab model tackles both semantic-level reasoning and object-part associations using part-based modeling. Our model employs a convolutional network which learns to detect individual keypoints and predict their relative displacements, allowing us to group keypoints into person pose instances. Further, we propose a part-induced geometric embedding descriptor which allows us to associate semantic person pixels with their corresponding person instance, delivering instance-level person segmentations. Our system is based on a fully-convolutional architecture and allows for efficient inference, with runtime essentially independent of the number of people present in the scene. Trained on COCO data alone, our system achieves COCO test-dev keypoint average precision of 0.665 using single-scale inference and 0.687 using multi-scale inference, significantly outperforming all previous bottom-up pose estimation systems. We are also the first bottom-up method to report competitive results for the person class in the COCO instance segmentation task, achieving a person category average precision of 0.417.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

SAtacker/PosenetTflite mentioned on GitHubtfLGPL-3.0 report
google-coral/project-posenet mentioned on GitHubtfApache-2.0 report
jp-sm/jp-sm.github.io mentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Instance SegmentationKeypoint DetectionMulti-Person Pose EstimationPose EstimationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Keypoint Detection COCO (Common Objects in Context) PersonLab Test AP 66.5 #14 of 24 Archive leaderboard report
Multi-Person Pose Estimation COCO test-dev PersonLab AP 68.7 #8 of 15 Archive leaderboard report
Multi-Person Pose Estimation COCO test-dev PersonLab AP50 89.0 #8 of 15 Archive leaderboard report
Multi-Person Pose Estimation COCO test-dev PersonLab AP75 75.4 #8 of 15 Archive leaderboard report
Multi-Person Pose Estimation COCO test-dev PersonLab APL 75.5 #8 of 15 Archive leaderboard report
Multi-Person Pose Estimation COCO test-dev PersonLab APM 64.1 #8 of 15 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections