Results for "keypoint-detection"
22 matches found.
usyd-community/vitpose-plus-base
Although no specific domain knowledge is considered in the design, plain vision transformers have shown excellent performance in visual reco...
ETH-CVG/lightglue_superpoint
No description available.
magic-leap-community/superpoint
No description available.
usyd-community/vitpose-base-simple
Although no specific domain knowledge is considered in the design, plain vision transformers have shown excellent performance in visual reco...
usyd-community/vitpose-plus-huge
Although no specific domain knowledge is considered in the design, plain vision transformers have shown excellent performance in visual reco...
stanfordmimi/synthpose-vitpose-huge-hf
No description available.
usyd-community/vitpose-plus-small
Although no specific domain knowledge is considered in the design, plain vision transformers have shown excellent performance in visual reco...
usyd-community/vitpose-plus-large
Although no specific domain knowledge is considered in the design, plain vision transformers have shown excellent performance in visual reco...
ETH-CVG/lightglue_disk
No description available.
vrg-prague/BBoxMaskPose
Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle ICCV 2025 + CVPR 2025...
stanfordmimi/synthpose-vitpose-base-hf
No description available.
qualcomm/MediaPipe-Pose-Estimation
Model Type: Modelusecase.poseestimation Model Stats: - Input resolution: 256x256 - Number of parameters (PoseDetector): 815K - Model size (P...
usyd-community/vitpose-base
Although no specific domain knowledge is considered in the design, plain vision transformers have shown excellent performance in visual reco...
qualcomm/HRNetPose
Model Type: Modelusecase.poseestimation Model Stats: - Model checkpoint: hrnetposenetFP32statedict - Input resolution: 256x192 - Number of p...
facebook/sapiens-pose-0.6b-torchscript
Sapiens is a family of vision transformers pretrained on 300 million human images at 1024 x 1024 image resolution. The pretrained models, wh...
qualcomm/Facial-Landmark-Detection
Model Type: Modelusecase.poseestimation Model Stats: - Input resolution: 128x128 - Number of parameters: 5.42M - Model size (float): 20.7 MB...
facebook/sapiens-pose-1b-torchscript
Sapiens is a family of vision transformers pretrained on 300 million human images at 1024 x 1024 image resolution. The pretrained models, wh...
KoniHD/Simple_CNN
No description available.
vismatch/xfeat
No description available.
vismatch/affine-steerers
No description available.
image-matching-models/eloftr
No description available.
vismatch/roma
No description available.