Papers › Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose

Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose

29 Nov 2018arXiv:1811.12004archive 2025-07-28

Daniil Osokin

In this work we adapt multi-person pose estimation architecture to use it on edge devices. We follow the bottom-up approach from OpenPose, the winner of COCO 2016 Keypoints Challenge, because of its decent quality and robustness to number of people inside the frame. With proposed network design and optimized post-processing code the full solution runs at 28 frames per second (fps) on Intel® NUC 6i7KYB mini PC and 26 fps on Coreᵀᴹ i7-6850K CPU. The network model has 4.1M parameters and 9 billions floating-point operations (GFLOPs) complexity, which is just ~15% of the baseline 2-stage OpenPose with almost the same quality. The code and model are available as a part of Intel® OpenVINOᵀᴹ Toolkit.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

2xic/openpose-pigs mentioned on GitHubpytorchSyntology: not harvested report
Daniil-Osokin/lightweight-human-pose-estimation-3d-demo.pytorch mentioned on GitHubpytorchSyntology: not harvested report
Daniil-Osokin/lightweight-human-pose-estimation.pytorch mentioned on GitHubpytorchSyntology: not harvested report
ModelBunker/Lightweight-OpenPose-PyTorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Single-Shot Multi-Person 3D Pose Estimation From Monocular RGB (arXiv:1712.03453; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
Rocketbase-AI/rockets-lightpose mentioned on GitHubpytorchSyntology: not harvested report
hsk9767/open_pose mentioned on GitHubpytorchSyntology: not harvested report
murdockhou/lightweight_openpose mentioned on GitHubtfSyntology: not harvested report
omkarbhope/Pose-Estimation mentioned on GitHubpytorchSyntology: not harvested report
osmr/imgclsmob mentioned on GitHubmxnetMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ResNeSt: Split-Attention Networks (arXiv:2004.08955; that paper's own run record: 28 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 0 violated, 21 with no contract checked; 7 where Syntology's instrument failed) · 20 unverified); nothing checks that they implement this paper's method. report
tyIceStream/lightweight-human-pose-estimation.OpenCV mentioned on GitHubpytorchSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

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

Tasks

Multi-Person Pose EstimationPose Estimation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

pc

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