Papers › DensePose: Dense Human Pose Estimation In The Wild

DensePose: Dense Human Pose Estimation In The Wild

1 Feb 2018CVPR 2018 6arXiv:1802.00434archive 2025-07-28

Riza Alp Güler, Natalia Neverova, Iasonas Kokkinos

In this work, we establish dense correspondences between RGB image and a surface-based representation of the human body, a task we refer to as dense human pose estimation. We first gather dense correspondences for 50K persons appearing in the COCO dataset by introducing an efficient annotation pipeline. We then use our dataset to train CNN-based systems that deliver dense correspondence 'in the wild', namely in the presence of background, occlusions and scale variations. We improve our training set's effectiveness by training an 'inpainting' network that can fill in missing groundtruth values and report clear improvements with respect to the best results that would be achievable in the past. We experiment with fully-convolutional networks and region-based models and observe a superiority of the latter; we further improve accuracy through cascading, obtaining a system that delivers highly0accurate results in real time. Supplementary materials and videos are provided on the project page http://densepose.org

PaperPDFConference PDFCode

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

Code

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

ARMUGHAN-SHAHID/MoboDensepose mentioned on GitHubcaffe2 report
M-Usman10/DenseSqueeze-RCNN mentioned on GitHubcaffe2 report
StupidmanTan/facebookresearch mentioned on GitHubcaffe2 report
UBC-Computer-Vision-Group/DwNet mentioned on GitHubpytorchNOASSERTION report
chengjiali/DensePose3 mentioned on GitHubcaffe2 report
chuanqichen/deepcoaching mentioned on GitHubpytorch report
dajes/DensePose-TorchScript mentioned on GitHubpytorch report
facebookresearch/DensePose mentioned on GitHubcaffe2 report
facebookresearch/detectron mentioned on GitHubpytorch report
facebookresearch/detectron2 mentioned on GitHubpytorch report
freedombenLiu/DensePose mentioned on GitHubcaffe2 report
hz-ants/DensePose mentioned on GitHubcaffe2 report
jarrodanderson/densepose mentioned on GitHubcaffe2 report
jiajunhua/facebookresearch-DensePose mentioned on GitHubcaffe2 report
jiajunhua/facebookresearch-Detectron mentioned on GitHubcaffe2 report
lncarter/Dencepose mentioned on GitHubcaffe2 report
sgoldyaev/DeepFashion.ADGAN mentioned on GitHubpytorch report
stimong/DensePose_python3 mentioned on GitHubcaffe2 report
svikramank/DensePose mentioned on GitHubcaffe2 report
ubc-vision/DwNet mentioned on GitHubpytorchNOASSERTION report
yongsheng268/DensePose mentioned on GitHubcaffe2 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

3D Human Pose EstimationMonocular 3D Human Pose EstimationPose Estimation

Datasets

Introduced by this paper, per the archive.

DensePose

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Pose Estimation DensePose-COCO DensePose + keypoints AP 55.8 #3 of 4 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

ConvolutionMask R-CNNRPNRoIAlignSoftmax

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