Papers › OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association

OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association

3 Mar 2021arXiv:2103.02440archive 2025-07-28

Sven Kreiss, Lorenzo Bertoni, Alexandre Alahi

Many image-based perception tasks can be formulated as detecting, associating and tracking semantic keypoints, e.g., human body pose estimation and tracking. In this work, we present a general framework that jointly detects and forms spatio-temporal keypoint associations in a single stage, making this the first real-time pose detection and tracking algorithm. We present a generic neural network architecture that uses Composite Fields to detect and construct a spatio-temporal pose which is a single, connected graph whose nodes are the semantic keypoints (e.g., a person's body joints) in multiple frames. For the temporal associations, we introduce the Temporal Composite Association Field (TCAF) which requires an extended network architecture and training method beyond previous Composite Fields. Our experiments show competitive accuracy while being an order of magnitude faster on multiple publicly available datasets such as COCO, CrowdPose and the PoseTrack 2017 and 2018 datasets. We also show that our method generalizes to any class of semantic keypoints such as car and animal parts to provide a holistic perception framework that is well suited for urban mobility such as self-driving cars and delivery robots.

PaperPDFCode

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

Code

vita-epfl/openpifpaf officialmentioned in papermentioned on GitHubpytorch report
vita-epfl/openpifpaf_posetrack officialmentioned in papermentioned on GitHubpytorch report
openpifpaf/openpifpaf mentioned on GitHubpytorch report
openpifpaf/openpifpaf_posetrack mentioned on GitHubpytorch report
openpifpaf/openpifpafwebdemo mentioned on GitHub report
yasutomo57jp/openpifpaf_ros mentioned on GitHub 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

Car Pose EstimationKeypoint DetectionMulti-Person Pose EstimationPose EstimationSelf-Driving Cars

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Car Pose Estimation ApolloCar3D OpenPifPaf Detection Rate 86.1 #2 of 3 Archive leaderboard report
Keypoint Detection COCO test-dev OpenPifPaf AP 70.9 #8 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev OpenPifPaf APL 76.8 #8 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev OpenPifPaf APM 67.1 #8 of 16 Archive leaderboard report
Multi-Person Pose Estimation COCO (Common Objects in Context) OpenPifPaf AP 0.709 #7 of 15 Archive leaderboard report
Multi-Person Pose Estimation COCO (Common Objects in Context) OpenPifPaf Test AP 70.9 #7 of 15 Archive leaderboard report
Multi-Person Pose Estimation COCO (Common Objects in Context) OpenPifPaf Validation AP 71.0 #7 of 15 Archive leaderboard report
Pose Estimation CrowdPose OpenPifPaf AP 70.5 #7 of 12 Archive leaderboard report
Pose Estimation CrowdPose OpenPifPaf AP Easy 78.4 #7 of 12 Archive leaderboard report
Pose Estimation CrowdPose OpenPifPaf AP Hard 63.8 #7 of 12 Archive leaderboard report
Pose Estimation CrowdPose OpenPifPaf AP Medium 72.1 #7 of 12 Archive leaderboard report
Pose Estimation CrowdPose OpenPifPaf AP50 89.1 #7 of 12 Archive leaderboard report
Pose Estimation CrowdPose OpenPifPaf AP75 76.1 #7 of 12 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.

Methods

Composite Fields

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