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.
Nate
HRNet fine-tuned on BRACE
I²R-Net (1st stage:HRFormer-B)
LOGO-CAP (Ours) HRNet-W48
MSPN
ViTPose (ViTAE-G, ensemble)
MogaNet-B (384x288)
BUCTD-W48 (w/cond. input from PETR, and generative sampling)
Parsing R-CNN + ResNext101
Stacked Hourglass Networks
Stacked Hourglass Networks
GIM-DKM
AdaPose
DECA-D3
SimpleBaseline + HANet
GeoNet
OmniPose
SPIGA
OmniPose (WASPv2)
PCT (swin-l, test set)
4xRSN-50
UniHCP (finetune)
HQNet (ViT-L)
Mid-Level based
SubdivNet
AlphaPose
OmniPose