Papers › DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model

DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model

10 May 2016arXiv:1605.03170archive 2025-07-28

Eldar Insafutdinov, Leonid Pishchulin, Bjoern Andres, Mykhaylo Andriluka, Bernt Schiele

The goal of this paper is to advance the state-of-the-art of articulated pose estimation in scenes with multiple people. To that end we contribute on three fronts. We propose (1) improved body part detectors that generate effective bottom-up proposals for body parts; (2) novel image-conditioned pairwise terms that allow to assemble the proposals into a variable number of consistent body part configurations; and (3) an incremental optimization strategy that explores the search space more efficiently thus leading both to better performance and significant speed-up factors. Evaluation is done on two single-person and two multi-person pose estimation benchmarks. The proposed approach significantly outperforms best known multi-person pose estimation results while demonstrating competitive performance on the task of single person pose estimation. Models and code available at http://pose.mpi-inf.mpg.de

PaperPDFCode

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

Code

16 repositories listed; official and paper-mentioned ones first.

Ayaanesmail/Test.- mentioned on GitHubtfLGPL-3.0 report
PJunhyuk/exercise-pose-analyzer mentioned on GitHubtfApache-2.0 report
PJunhyuk/people-counting-pose mentioned on GitHubtfApache-2.0 report
chongchen20/Deeplabcut mentioned on GitHubtfLGPL-3.0 report
eho-tacc/DeepLabCut mentioned on GitHubtfLGPL-3.0 report
eldar/deepcut mentioned on GitHub report
eldar/deepcut-cnn mentioned on GitHubNOASSERTION report
eldar/pose-tensorflow mentioned on GitHubtfLGPL-3.0 report
estelabalboa/Proyecto_Final_Pilates mentioned on GitHubtfLGPL-3.0 report
gsoykan/comp541_term_project mentioned on GitHubtfMIT report
gsoykan/deepercut-replication mentioned on GitHubtfMIT report
gyaansastra/DeepLab mentioned on GitHubtfLGPL-3.0 report
janbertelngo/count-people mentioned on GitHubtfApache-2.0 report
orkqueen/depplabseongil mentioned on GitHubtfLGPL-3.0 report
srini2dl/DogPoseEstimation mentioned on GitHubtf report
yttrilab/b-soid 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

Keypoint DetectionMulti-Person Pose EstimationPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Keypoint Detection MPII Multi-Person DeeperCut mAP@0.5 59.4% #9 of 9 Archive leaderboard report
Multi-Person Pose Estimation MPII Multi-Person DeeperCut AP 59.4% #9 of 9 Archive leaderboard report
Multi-Person Pose Estimation WAF DeeperCut AOP 88.1% #1 of 3 Archive leaderboard report
Pose Estimation Leeds Sports Poses ResNet-152 + intermediate supervision PCK 90.1% #13 of 18 Archive leaderboard report
Pose Estimation MPII Human Pose ResNet-152 + intermediate supervision PCKh-0.5 88.52 #33 of 46 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

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual Connection

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