Pose Estimation
Pose Estimation is a task in the field of computer vision that aims to detect the position and posture of people or objects. This task achieves human pose estimation by predicting the locations of specific keypoints (such as hands, head, elbows, etc.). Pose Estimation has significant application value in areas like human-computer interaction, motion analysis, and virtual reality. Common benchmark tests include the MPII Human Pose dataset.
COCO test-dev
HRNet-W48+DARK
MPII Human Pose
PCT (swin-l, test set)
Leeds Sports Poses
OmniPose
OCHuman
ViTPose (ViTAE-G, GT bounding boxes)
CrowdPose
BUCTD-W48 (w/cond. input from PETR, and generative sampling)
COCO val2017
MogaNet-B (384x288)
AIC
MS COCO
OmniPose (WASPv2)
ITOP front-view
AdaPose
InLoc
GIM-DKM
ITOP top-view
DECA-D3
J-HMDB
SimpleBaseline + HANet
MPII Single Person
4xRSN-50
UPenn Action
OmniPose
SALSA
SubdivNet
300W (Full)
BRACE
HRNet fine-tuned on BRACE
COCO 2017 val
LOGO-CAP (Ours) HRNet-W48
DensePose-COCO
Parsing R-CNN + ResNext101
FLIC Elbows
Stacked Hourglass Networks
FLIC Wrists
Stacked Hourglass Networks
UAV-Human
AlphaPose
!(()&&!|*|*|
Nate
3DPW
ApolloCar3D
COCO minival
MSPN
KITTI 2015
GeoNet
MERL-RAV
SPIGA
MPII
OmniPose (WASPv2)
MS-COCO
UniHCP (finetune)
Pix3D
Mid-Level based